MoneyBall Medicine

Chapters00:00 Introduction and Company Updates02:49 The Digital Transformation of Ultrasound Imaging06:00 Advancements in Technology and Market Growth09:03 AI Integration in Medical Imaging14:50 Impact on Global Health and Humanitarian Efforts20:55 Challenges in Mainstream Adoption of Handheld Ultrasound29:43 Strategic Sales Approaches in Medical Devices34:11 Finding Product-Market Fit36:12 Simplicity in Medical Technology39:26 Unexpected Use Cases and Market Adoption45:24 Future Innovations in Handheld Ultrasound51:58 The Importance of Patient Data Ownership 

00:00 Introduction and Overview of Caristo Diagnostics09:08 The Technology Behind Carry Heart18:00 Clinical Implications and Risk Assessment27:27 Actionable Steps for Patients30:34 Optimizing Cardiovascular Drug Dosing32:31 AI in Cardiovascular Medicine33:50 Leveraging Historical Data for Risk Prediction36:25 AI's Role in Molecular Pathway Analysis39:03 GLP-1 and Cardiovascular Outcomes41:56 Targeted Therapies in Cardiovascular Treatment42:45 Building Trust in New Technologies49:16 Regulatory Approvals and Future Prospects54:15 Expanding Applications Beyond Cardiology57:16 Looking Ahead: The Future of Caristo Diagnostics 

In this episode of The Harry Glorikian Show, host Harry Glorikian welcomes back Jeff Elton, CEO of Concert AI, to discuss the latest advancements in AI-driven healthcare solutions. They reflect on the recent JP Morgan Healthcare Conference, highlighting the optimism surrounding AI's role in transforming drug development and oncology. Jeff shares insights into Concert AI's innovative data ecosystems, partnerships, and the introduction of Kera, an AI platform designed to enhance clinical decision-making. The conversation also explores the challenges and opportunities in the evolving landscape of healthcare technology, emphasizing the importance of collaboration and adaptability in the face of rapid change.Takeaways:The JP Morgan Healthcare Conference indicated a positive outlook for the industry.AI is becoming a central theme in healthcare discussions.Concert AI is developing a comprehensive data ecosystem for oncology.The introduction of agentic AI models is set to revolutionize data processing.Collaboration with NVIDIA is enhancing Concert AI's capabilities.Kera is a significant advancement in AI-driven healthcare solutions.The future of drug development will rely heavily on AI and data analytics.Healthcare organizations must adapt to the rapid pace of technological change.Building partnerships is crucial for addressing healthcare fragmentation.The integration of AI in clinical trials can significantly reduce timelines.Chapters 00:00 The Annual Healthcare Pilgrimage03:19 Optimism in the Pharma Industry06:07 The Rise of AI in Healthcare10:03 Concert AI's Evolution and Innovations15:10 2024: A Standout Year for Concert AI18:55 Balancing Growth and Innovation22:33 Scaling Across Therapeutic Areas26:26 The Future of Collaborations in Healthcare28:37 Integrating Immune Status and Data Collaboration31:04 Introducing Kera AI: The Future of Data Management35:24 Innovations in Clinical Trials and Data Solutions40:16 Rethinking Drug Development: Digital Twins and AI42:36 Navigating Market Shifts and Talent Challenges54:02 The Future of Concert AI and Healthcare Solutions  

Harry's guest this week is Raffi Krikorian, chief technology officer and managing director at Emerson Collective, the social change organization founded by Laurene Powell Jobs. Krikorian is the former vice president of engineering at Twitter (now X), where he was responsible for getting rid of the Fail Whale and making the company's backend infrastructure more reliable; the former director of Uber's Advanced Technology Center in Pittsburgh, where he oversaw the launch of the world's first fleet of self-driving cars; and then the chief technology officer at the Democratic National Committee, where he helped rebuild the party's technology infrastructure after the Russian hacking debacle of 2016. At Emerson Collective, Krikorian built the technology organization, leads the development of data products, and works to upgrade the back offices of the non-profits Emerson works with. On top of all that, he recently launched a podcast called Technically Optimistic, where he's taking a deep dive into the way AI is challenging us all to think differently about the future of work, education, policy, regulation, creativity, copyright, and many other areas. The show is a must-listen for anyone who cares about how we can build on AI to transform society for the better while minimizing the collateral damage. Harry talked with Krikorian about why he moved to Emerson Collective, why and how he started the podcast, and what he really thinks about what government should be doing to prepare for the waves of social change AI will bring.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts or Spotify! Here's how to do that on Apple Podcasts:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.On Spotify, the process is similar. Open the Spotify app, navigate to The Harry Glorikian Show, tap the three dots, then tap "Rate Show." Thanks!

Generative AI is going to change how we do things across the entire economy, including the fields Harry covers on the show, namely healthcare delivery, drug discovery, and drug development. But we're still just starting to figure out exactly how it's going to change things. For example, AI is already speeding up the process of discovering new biological targets for drugs and designing molecules to hit those targets—but whether that will actually lead to better medicines, or create a new generation of AI-driven pharmaceutical companies, are still unanswered questions. One thing that's for sure is that generative AI isn't magic. You can't just  sprinkle it like pixie dust over an existing project or dataset and expect wonderful things to happen automatically. In fact, just to use the data you already have, you have to you may have to invest a lot in the new infrastructure and tools needed to train a generative model. And that's the part of the puzzle Harry focuses on in today's interview with David Buniatyan. He's the founder of a company called ActiveLoop, which is trying to address the need for infrastructure capable of handling large-scale data for AI applications. He has a background in neuroscience from Princeton University, where he was part of a team working on reconstructing neural connectivity in mouse brains using petabyte-scale imaging data. At ActiveLoop, David has led the development of Deep Lake, a database optimized for AI and deep learning models trained on equally large datasets.Deep Lake manages data in a tensor-native format, allowing for faster iterations when training generative models. David says the company's goal is to take over the boring stuff. That means removing the burden of data management from scientists and engineers, so they can focus on the bigger questions—like making sure their models are training on the right data—and ultimately innovate faster.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts or Spotify! Here's how to do that on Apple Podcasts:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.On Spotify, the process is similar. Open the Spotify app, navigate to The Harry Glorikian Show, tap the three dots, then tap "Rate Show." Thanks!

If you learned that radiologists looking at CT scans for the traditional signs of coronary artery disease catch only 20 percent of the people who actually have a high risk of a heart attack, and if you learned that there's a new AI-based test that can catch subtle signs of inflammation in the other 80 percent of patients—well, you'd probably want to get that test yourself, right? Harry's guests this week, Frank Cheng and Keith Channon, are from a UK-based company that has developed just such a test. Cheng is the company's CEO, and Channon is co-founder and chief medical officer. And under their leadership, Caristo has introduced a test called CariHeart that applies machine learning to the data in a three-dimensional CT scan of the heart. It looks for otherwise invisible signs of inflammation in the fat tissue around the major coronary arteries, and then it predicts the chances that the patient will suffer a heart attack in the next eight years. Doctors can use that information to decide whether a patient needs to take a cholesterol-lowering drug like a statin or an anti-inflammatory drug like colchicine. Caristo's test is being used on an experimental basis in the UK, and it hasn't yet been approved for use in the US. But it's a leading example of the way AI, put together with fundamental advances in our understanding of human biology, is really beginning to change the practice of medicine. Cheng and Channon say Caristo's test isn't intended to put cardiologists or radiologists out of work—it's designed to help them be more effective. And given that cardiovascular disease is the number one cause of death around the world, any technology that can help catch signs of coronary artery disease earlier could save a lot of lives.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts or Spotify! Here's how to do that on Apple Podcasts:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.On Spotify, the process is similar. Open the Spotify app, navigate to The Harry Glorikian Show, tap the three dots, then tap "Rate Show." Thanks!

Investors and companies in the life science industry have been betting a lot of money over the last few years on a single idea: that computation will help us get a lot better at developing new drugs. But the word “computation” covers a pretty broad range of techniques. And the reason that there are dozens if not hundreds of computational drug discovery startups popping up is that everyone has their own hypothesis about what specific kind of computation is going to be the most powerful.For example, you might be convinced that the most important thing is to understand the physics of protein-protein interactions, at an atomic level. And so you would put your money into atomic-scale simulations that show how proteins fold or unfold to form different shapes under different conditions. Or you might think that it's more important to model proteins at the molecular scale, to make predictions about whether and how a particular drug molecule might dock with a target protein. Or you might think that it's smarter to try to model whole cells and see how different molecular pathways interact to affect different functions of the cell. Or you might not care about the details of physics- or chemistry-based models at all. In that case could just take a big generative AI model, similar to a large language model, and train it on huge amounts of unlabeled data about genes and proteins in diseases cells and healthy cells to see what kinds of predictions it comes up with.It's too early to say which of these computational approaches—and which level or scale of focus—is going to be the most fruitful. But maybe you don't have to choose. Maybe you can bet on all of these different ideas, all at once. Harry's guests this week are the CEO and CSO of a startup that's taking an all-of-the-above approach. It's called Deep Origin, and it was formed last year from the merger of two companies founded by theoretical chemist Garegin Papoian and software builder Michael Antonov. Antonov helped to found the virtual reality hardware company Oculus. After Facebook acquired Oculus, he got curious about longevity and how software could help untangle the trillions of gene-protein interactions that mediate health and disease. He founded a company called Formic Labs to dig into that problem, and last year the company changed its name to Deep Origin. Papoian, meanwhile, is a former academic scientist who's who also took the helm as CEO of his startup AI and who's interested in how to use software to model molecular dynamics and quantum chemistry. Recently Antonov and Papoian decided to join forces, and Biosim AI merged into Deep Origin. They say the company's philosophy is that physics-based modeling by itself won't be enough to build a powerful drug discovery engine. But neither will generative AI, which requires more training data than lab scientists will ever be able to provide. They think the only reasonable approach today is to combine the two, and use both physics and AI to try to get better at predicting which molecules could become effective drugs.Exactly how Antonov and Papoian came to their conclusion, and how that integration is playing out, was the main theme of this week's conversation. It's important stuff, because if Deep Origin is right, then a lot of other more specialized biotech and techbio startups could be going down the wrong path. For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts or Spotify! Here's how to do that on Apple Podcasts:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.On Spotify, the process is similar. Open the Spotify app, navigate to The Harry Glorikian Show, tap the three dots, then tap "Rate Show." Thanks!

If you look back at all the health-tech and drug development companies Harry has hosted on the show, an interesting pattern starts to emerge: a very large number of those companies have gone on to enormous growth and success in their markets. It could be that being on the podcast is like a catapult to success—or it could be that we're pretty good at finding companies that are already on a promising trajectory. Either way, there's no better example than Concert AI. The company's CEO, Jeff Elton, first spoke with Harry back in July of 2021. At that time, the company was already one of the leaders in gathering and analyzing broad collections of data about cancer patients involved in clinical trials for new treatments. Its specialty was, and is, going beyond the very specific endpoints measured in clinical trials and looking to electronic medical records, genome sequencing data, insurance claims data, and other sources in order to build a more comprehensive picture of cancer patients and their journeys through the healthcare system. That kind of data can be very useful to companies trying to track the performance of their drugs after they've reached the market, and to researchers planning new clinical trials. And since that first conversation, the company has grown by leaps and bounds. It's taken over management of more data sources, including the massive CancerLinq database formerly maintained by the American Society of Clinical Oncology. It's struck up partnerships with some of the leading technology startups, research centers, and drug companies working to beat cancer. And it's leaning hard into the new wave of deep-learning AI tools and their potential to help find patterns in vast amounts of data about patients. It's probably safe to say that ConcertAI has gathered up more data about cancer patients than any other company on the planet. And investors have been rushing to pour money into the company, on the conviction that data is going to be the key to getting more and better cancer drugs to market. That's certainly Jeff Elton's conviction too, as you'll hear in today's interview.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts or Spotify! Here's how to do that on Apple Podcasts:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.On Spotify, the process is similar. Open the Spotify app, navigate to The Harry Glorikian Show, tap the three dots, then tap "Rate Show." Thanks!

One of the most amazing successes in the battle against cancer over the last two decades has been the introduction of antibody drugs that harness the body's own immune system to kill tumor cells. Finding those drugs may sound like a biology problem rather than a machine learning or a big-data problem. But actually, these days, it's both. Harry's guest this week is Leonard Wossnig, who's the chief technology officer for a UK company called LabGenius. The company uses a combination of synthetic biology, high-throughput assays, and machine learning to hunt for new drugs within a subclass of antibody medicines called T cell engagers that, loosely speaking, can grab tumor cells with one end and then grab tumor-killing T cells from the bloodstream with the other end. And Wossnig says the key to the whole thing is having the best data possible—meaning, data about their candidate T cell engagers and how specifically they bind to their targets in the lab assays. LabGenius has built an automated platform called EVA that runs experiment after experiment and uses active learning to zero in on T cell engagers with just the right ability to bind to their intended targets. One of the big takeaways from the interview is that companies that want to use AI to speed up drug discovery need the biggest, cleanest, and most consistent data sets possible.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts or Spotify! Here's how to do that on Apple Podcasts:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.On Spotify, the process is similar. Open the Spotify app, navigate to The Harry Glorikian Show, tap the three dots, then tap "Rate Show." Thanks!

The combination of better data and more powerful computing is helping researchers reinvent the process of discovering new drugs. Within 5-10 years, we'll likely see a huge wave of new medicines that were either discovered or designed using AI—drugs that will finally help us get control of our most stubborn health problems, from cancer to cardiovascular disease to obesity and metabolic disorders to neurodegenerative diseases. And the biotech startups that will do most to contribute are the ones that have both proprietary data, and original ways to use AI to sift through that data. Harry's guests this week are from a startup called Pangea Bio that's working hard on both. As Pangea's co-founder and COO, John Boghossian, and its president of AI, Sona Chandra, explain, the company specializes in gathering data from the natural world, especially data about compounds manufactured inside the cells of plants and fungi. They narrow down the possibilities by working with indigenous cultures to find the plants or mushrooms that people have already been using for centuries in traditional medicine. They've also built three separate computational platforms that filter through all that data, to single out the small molecules that have the biggest effects in the human body, especially the central nervous system. For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.

There are about 30 trillion human cells in your body, but there are about 38 trillion bacterial cells, mostly hanging out in your large intestine. And that's not even counting all the viruses, fungi, protists, and other microbial cells that live on your skin, in your bloodstream, and all around your body. So in effect, what you think of as you is not really you. You're actually a walking colony of many different organisms. All of which cooperate peacefully, for the most part—unless the balance goes awry, and then you can get very sick, very fast.The microbiome has been getting more and more attention from researchers and doctors now that we're starting to have the tools we need to identify and measure all those microbes and see what they're up to. Harry's guest this week is serial healthcare and AI entrepreneur Leo Grady, whose company Jona is on a mission is to help patients and physicians keep up with the skyrocketing amount of scientific literature about the microbiome and try to translate it into real steps people can take to improve their health.If you're a Jona customer, you start by sending in a fecal sample. Then the company uses a large-scale gene sequencing technique called shotgun metagenomics to get a profile of all the microbes in your GI tract. Since everyone's microbiome contains a different mix of microbes, the next step is to use large language models to sift through the published science about the microbiome and find the studies that relate to the specific bugs in your microbiome. Then the company gives patients and their doctors a report that parses out whether their microbiome makeup might be contributing to their health problems, and whether there might be any health or nutritional interventions that would help. It's all in the early stages. And right now Jona's test is mostly available through concierge medical services, executive health clinics, and other offices that do a lot of cash-pay tests. But Grady thinks that over the long term the service has the potential to turn the microbiome from a former black box into something closer to what he calls an “organ of data"—meaning a part of the body that doctors can, in a sense, visualize and analyze in the same way we can use MRI and other forms of imaging to scan our other organs.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.

Quality control is one of those things that only a select few people pay attention to—until something goes wrong, then everyone cares. That's especially true in the drug manufacturing industry, where episodes like cross-contamination in a drug factory can shut down a production line and create instant shortages of important medicines. And if a contaminated medicines ever does get shipped out to clinics or stores, people's lives can be at stake. So drug makers are usually pretty receptive toward any new technology that can help them detect manufacturing problems before they get out of hand.That's the market opening that Harry's guest Taylor Chartier says she saw back in 2020, during the coronavirus pandemic. Chartier watched the stories about the Baltimore company Emergent BioSolutions, which was manufacturing vaccines for Johnson & Johnson and AstraZeneca and had to throw out millions of doses of both vaccines due to suspected cross-contamination, and thought: there has to be a better way. So she started her own company. And today her startup Modicus Prime is partnering with top pharma companies to use new machine vision and AI capabilities to catch drug manufacturing problems faster.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

There's a lot of talk out there about how artificial intelligence will change the way doctors and nurses take care of patients; you hear some of it right here on this show. But all of that still feels like a forecast rather than a present reality. When you look really closely, it's hard to find concrete examples where AI is already helping healthcare providers make better decisions that improve patient outcomes and take costs out of the system.That's why Harry wanted to have Nassib Chamoun on the show. Chamoun is the founder and CEO of Health Data Analytics Institute (HDAI), which has been working with a major healthcare system, Houston Methodist, to test out a working platform called HealthVision. It's a collection of AI-driven models that use huge amounts of data, both from Medicare and from Houston's own electronic health record system, to make predictions that help doctors and administrators spend less time poring over records and data, and more time interacting with actual patients and making good clinical and management decisions.Nassib has a way of talking about HDAI and HealthVision that leaves out the hype and focuses on the real-world problems AI can solve for doctors and administrators—like how to identify the patients discharged from hospitals to their homes or to skilled nursing facilities who are at the highest risk of complications, and which interventions could help keep them alive and prevent readmission. Nassib tells Harry that “AI is not magic" and points out that even the most famous large language models, like ChatGPT, are just massive statistical representations of data created, collected, or curated by humans. And while these models are powerful, Nassib argues they'll need guardrails around them to guarantee transparency and explainability and to prevent bias, before they can be useful in high-stakes fields like healthcare.HDAI has raised tens of millions of dollars of capital and spent seven years developing HealthVision, and now the company is getting ready to grow beyond Houston Methodist and deploy the system at other big healthcare institutions like the Cleveland Clinic and the Dana-Farber Cancer Institute—so more providers will get a chance to test whether AI can keep patients healthier and make healthcare delivery more efficient.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

There's a good chance that we're all going to live a lot longer than we think. Or at least, that's what Harry's guest Sergey Young argues in his book The Science and Technology of Growing Young. Young is an investor who leads a $100 million venture capital fund called the Longevity Vision Fund, and through his investing, he says he meets innovators who are coming up with the technologies that will extend our healthy lifespans not just by years but by decades. Those technologies include better drugs, of course, but also gene editing to rejuvenate our DNA and methods for regenerating or replacing old organs, just the way you'd replace the worn-out parts in an old car. All these technologies are coming faster than we think, Young says, and the big question is how widely they'll be available and whether everyone who wants them will have access to them. That's the theme of Young's work at the Longevity Vision Fund, which focuses on companies creating affordable and accessible life extension technologies.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

It's practically the theme of our show that AI is going to change almost everything about the way drugs get developed and the way healthcare gets delivered. But there's probably nobody better placed to see how this transformation is already happening than Harry's guest this week, Scott Penberthy. Scott works at Google Cloud, where he's the director of Applied AI in the Office of the CTO. He and his team work with Google's big corporate customers, including a variety of customers in healthcare and pharmaceutical R&D, to help them solve business problems that require large-scale computing and deep learning. Scott compares Google's cloud computing capabilities to a racecar that can be adapted to any type of race—whether that's a customer like Ginkgo Bioworks that leans on computation to reprogram bacterial cells to pump out pharmaceuticals and other products, or a giant health network like Anthem that uses AI to deliver personalized services to members. Because Scott helps set up these partnerships, and because he gets the first look at the Google's emerging products and services, he has a unique picture of how computing is changing the everyday practice of doing R&D and running a healthcare company. As he himself puts it, he's in the catbird seat. So listen along as Scott and Harry geek out about how far things have come in AI's transformation of healthcare, and how much more is just around the corner. For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

Building any kind of startup is hard. Starting a business in healthcare or medical technology is even more challenging, given the long timelines for product development and all the regulatory requirements companies have to meet. But imagine how much harder it would be to start a company if you were still just a senior in high school! Recently Harry learned about a company called Vytal that's building eye-tracking technology to measure brain health, and he knew he wanted to have the co-founders on the show. Not just because the technology is interesting, but because CEO Rohan Kalahasty and the CTO Sai Mattapali are both 18 years old, and both entering their senior years at Thomas Jefferson High School of Science and Technology in Fairfax County, Virginia. Very few teenagers have ten employees and over a million dollars in seed capital. But that's exactly where Rohan and Sai are right now. Some of the challenges they've faced have been absolutely typical—like how to build a network of partners and how to meet government standards for new medical devices. And others have been a little unusual, like how to get time off from school to meet with investors and how to convince their parents that the business won't take too much time away from their studies. Listen in to hear their whole startup story.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

If you're looking for help thinking about the implications of exponential change in all areas of technology, one of the best people you can turn to is Azeem Azhar. He's a writer, entrepreneur, and investor who publishes the incredibly popular and influential Substack newsletter Exponential View, which takes deep dives into AI and other subjects with world experts. In 2021 Azeem published a whole book along the same lines called The Exponential Age: How Accelerating Technology is Transforming Business, Politics, and Society, and he joined Harry on the show in early 2022 to talk about that. This summer, the book came out in paperback—and just this month, Azeem worked with Bloomberg Originals to launch a limited-run TV show and podcast called Exponentially with Azeem Azhar. So it seemed like a great time to revisit Harry's 2022 interview, which resonates with current events even more now than it did when we first aired it.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

It's been less than a year since OpenAI opened up ChatGPT to the general public, and less than six months since OpenAI introduced GPT-4, the large language model that currently powers ChatGPT. But in that brief time, the new crop of generative AI tools from OpenAI and competitors like Google and Anthropic has already started to transform the way we think about managing information. We're entering an era when machines can generate, organize, and access information with a level of accuracy, speed, and originality that matches or exceeds the abilities of humans.That doesn't mean machines are making humans obsolete. But it does mean that organizations that deal in information need to figure out how to equip their people to use the new generative AI tools effectively.  If they don't, they're going to get outperformed by competitors that do that better. And in Harry's view, professionals in drug discovery, drug development, and healthcare don't quite understand the scale of the change that's coming. They need to get up to speed right now if they want to incorporate generative AI into their work in a way that's effective and safe.Fortunately there are plenty of people in the life sciences industry thinking about how to help with that. And one of them is Harry's guest this week, Lana Feng. She's the CEO and co-founder of Huma.ai, and under her leadership the company has been working with OpenAI to find ways to adapt large language models for use inside biotech and pharmaceutical companies. GPT-4 and competing models are extremely powerful. But for a bunch of reasons that Lana explains in this episode, it wouldn't be smart to apply them directly to the kinds of data gathering and data analysis that go on in the biopharma world. Huma.ai is working on that problem. They're building on top of GPT-4 to make the model more private, more secure, more reliable, and more transparent, so that companies in drug development can really trust it with their data and not get tripped up by issues like the hallucination problem. Anybody who wants to understand how generative AI could change practices in the drug industry needs to know what the company is up to.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

Harry's guest this week is Joe DeVivo, the new CEO of Butterfly Network. The company's goal is to make it radically easier for doctors or medical technicians to perform an ultrasound exam on any part of the body, and radically cheaper for a patient to get one. The companyt makes an FDA-cleared, handheld ultrasound scanner called the Butterfly iQ. The first big thing that's different about the iQ is that it uses silicon-based microelectromechanical sensors, instead of a traditional piezoelectric crystal element, to generate and receive the ultrasound waves. That means the device is fully digital, rather than analog.  The second big thing that's different is that the iQ transmits the ultrasound data to a standard iPhone or iPad instead of a big, expensive ultrasound cart. The doctor or technician can see the live ultrasound image right on a handheld device, and use the image to aim the sensor correctly to get the best possible picture to make a diagnosis. All of that is bringing down the cost of equipping a clinic with ultrasound technology dramatically, and over time it should also bring down the cost of administering an ultrasound exam. It also opens up the possibility of adding AI assistance to the software, so that doctors or technicians can get usable images with less training. The net result is that Butterfly is making it economically feasible to use ultrasound for diagnostic imaging in a lot more places, including clinics in developing countries where ultrasound was out of reach before due to the high cost of the technology and a shortage of trained ultrasonographers.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

This week Harry's guest is....Harry! We're flipping the script and giving Harry a chance to wax eloquent about AI in healthcare and drug research, the growing role of personal health monitoring devices, the unique features of the Boston life science ecosystem, the meaning of the recent downturn in biotech investment, the most common mistakes made by new entrepreneurs, and much more. This week's guest interviewer is Wade Roush, who hosts the tech-and-culture podcast Soonish and has been the behind-the-scenes producer of The Harry Glorikian Show ever since Harry started the show in 2018.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

Harry's guest this week is Dr. Isaac Kohane, chair of the Department of Biomedical Informatics at Harvard Medical School and co-author of the new book The AI Revolution in Medicine: GPT-4 and Beyond. Large language models such as GPT-4 are obviously starting to change industries like search, advertising, and customer service—but Dr. Kohane says they're also quickly becoming indispensable reference tools and office helpmates for doctors. It's easy to see why, since GPT-4 and its ilk can offer high-quality medical insights, and can also quickly auto-generate text such as prior authorization, lowering doctors' daily paperwork burden. But it's all a little scary, since there are no real guidelines yet for how large language models should be deployed in medical settings, how to guard against the new kinds of errors that AI can introduce, or how to use the technology without compromising patient privacy. How to manage those challenges, and how to use the latest generation of AI tools to make healthcare delivery more efficient without endangering patients along the way, are among the topis covered in Dr. Kohane's book, which was co-written with Microsoft vice president Peter Lee and journalist Carey Goldberg.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

In the same way that written English is built around an alphabet of just 26 letters, all life on Earth is built around a standard set of just 20 amino acids, which are the building blocks of all proteins. And just as we've invented special characters like emoji to go beyond our standard letters, it turns out that biologists can expand their repertoire of powers using non-standard amino acids—those that either occur rarely in nature, or that can only be made in the lab. GRO Biosciences, a spinout from the laboratory of the renowned synthetic biology pioneer George Church at Harvard Medical School, is one of the companies working to explore the exciting applications of non-standard amino acids (NSAAs), and Harry's guest this weeks is GRO's co-founder and CEO, Dan Mandell. He says NSAAs could help overcome some of the limitations that keep today's gene and protein therapies from being used more widely, while also expanding the kinds of jobs that protein-based therapies can do.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

Owning a dog can be a joy, but one sad downside is that dogs are highly prone to cancer—six million of them are diagnosed with the disease in the U.S. each year. Harry's guest this week, Christina Lopes, is co-founder and CEO of a company called One Health that's working to improve cancer outcomes for our canine friends. The company offers a precision cancer diagnosis and treatment service called FidoCure that takes what we've learned about genomic testing of tumors in humans and uses it in veterinary clinics. Vets can submit a dog's tumor sample for DNA sequencing, and FidoCure's report will show whether the animal has specific mutations that could help determine which cancer drug will be most effective. Harry and Christina talk about how that process works, why dogs are more vulnerable to cancer in the first place, where she got the idea for the company, and how One Health's work could benefit dogs and humans alike.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

Unlike cancer, brain diseases like epilepsy, Alzheimer's disease, or depression don't tend to have  easily measured biomarkers that could help doctors tailor treatments, or that could help researchers develop more effective drugs. So in neurology and psychiatry, the precision medicine revolution hasn't really arrived yet. But Beacon Biosignals, where Harry's guest  Jacob Donoghue is the co-founder and CEO, is trying to change all that. Beacon is focused on making electroencephalography into a more reliable and useful data source for diagnosing and treating neurological disease. EEG is a non-invasive way to measure electrical activity in the brain, and it's been a common medical tool for almost 100 years. But takes a lot of training for a human doctor to interpret an EEG correctly. It's slow, it's expensive, and it's a bit of a dark art—all of which makes it the perfect candidate for machine learning analysis. Donoghue says the goal at Beacon Biosignals is to use computation to get more value out of existing EEG data. By peering deeper into the data, he thinks it should be possible to identify subtypes of problems like epilepsy or Alzheimer's, and help neurologists understand which patients will respond best to which therapies. On top of that, better EEG measurements could also give drug developers and regulators more clinical endpoints to measure when they're trying to evaluate the safety and efficacy of new drugs for CNS diseases. If Beacon's vision comes true, the precision medicine revolution might finally start to reach the brain.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

Large language models are already changing the business of search. But now they're about to change the practice of medicine. Harry's guests, Vivek Natarajan and Shek Azizi, are both researchers on the Health AI team at Google, where they're pushing the boundaries of what large language models can achieve in specialized domains like  health. This spring their team announced it would start rolling out a new large language model called Med-PaLM 2 that's designed to answer medical questions with high accuracy. (The model got an 85 percent score on the U.S. Medical License Exam, the test all doctors have to take before they're allowed to practice.)  It's been clear for a while that consulting with an AI would eventually become an indispensable part of every medical journey—whether you're a patient searching for information about your symptoms, or a doctor looking for an expert second opinion. And now that such a future is almost here, the work Vivek and Shek are doing at Google feels both exciting and a little bit scary.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

Harry's guests this week are Sri Kosaraju, the CEO of Inscripta, and Richard Fox, a former Inscripta scientist who just rejoined the company as its SVP of Synthetic Biology. In reabsorbing Infinome—the Inscripta spinout Fox described to Harry in a spring 2021 episode of the show—Inscripta is placing a big bet on biomanufacturing, the creation and fermentation of genetically customized microbes that can pump out medical, agricultural, and nutraceutical products, and more. Inscripta had previously focused on a benchtop "bio-foundry" machine called Onyx that that makes programmed edits to bacterial or yeast cells at thousands of different points in their genome in parallel. Now it's pivoting away from selling the machine and instead focusing on becoming a power user of its own technology. Its ultimate plan is market multiple biomanufactured products, starting with a synthetic form of bakuchiol, an alternative to the anti-aging compound retinol.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

Harry's guest this week, Jen Nwankwo, is the founder and CEO of a drug discovery company in Boston called 1910 Genetics. Her PhD is in pharmacology, which shows through in her practical focus on fixing the drug discovery process to get more and better therapies into the hands of doctors. To hear Jen tell it, 1910 Genetics is focused on finding the most promising new drug candidates for stubborn health problems—and it takes a refreshingly agnostic approach to everything else. The company doesn't hunt for just small-molecule drugs or just protein therapies. It explores both. It doesn't utilize just one form of neural networking or machine learning. It uses whatever model produces the best science for a given problem. It doesn't hunt for drugs using just wet lab data or just computational simulations. It does both. It isn't just assembling its own pipeline of drugs or just partnering with larger pharma companies. It's working on both. Jen wasn't even dead set on being an entrepreneur—she had to be talked into applying to the Y Combinator startup incubator and into accepting her Series A investment from Microsoft's venture fun.She says the way 1910 thinks about drug discovery is to start with the desired output -- say, a new molecule to block pain -- then figure out what sorts of data inputs exist. Then they find or create all the data they need to analyze the problem. Then they transform that data using whatever AI tools work best, until they get some decent drug candidates. She calls it Input, Transform, Output. It's never that simple, of course. But at a time when AI and machine learning focused drug discovery companies are sprouting up faster than dandelions—each one touting some specific reason why its model is better than all the others—1910 Genetics is has a more inclusive approach to solving classic problems in pharmacology, and it's one that should spread to other parts of the life science business. For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

Tears are a signal of more than just our emotions. The liquid in tears comes from blood plasma, and contains a lot of the same proteins and other biomolecules that circulate in the bloodstream. But what this liquid doesn't have are a lot of the extra components like antibodies that would get in the way if you were looking for specific biomarkers—such as the low-molecular-weight proteins released as a byproduct of the inflammation around tumors. Harry's guests Anna Daily and Omid Moghadam are from a startup called Namida Lab that's the first company to market a lab test using tears to predict cancer risk. Specifically, Namida's test assesses the short-term risk that a patient might have breast cancer, as a way of helping them decide how soon to go in for a mammogram. "Namida" is actually the Japanese word for tears, and beyond breast cancer, the company aims to build a whole business around risk assessment and diagnostics, using just the biomarkers in tears. Eventually it could be possible to collect a sample of your tears on a small strip of absorbent paper, send it in to Namida Lab, and find out whether you have colon cancer, pancreatic cancer, prostate cancer, or ovarian cancer. Namida's big vision, as Moghadam and Daily tell it, is to use tear testing to make precision medicine and diagnostics more accessible and affordable, including to patients who might live far away from tertiary care centers.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

It may feel like generative AI technology suddenly burst onto the scene over the last year or two, with the appearance of text-to-image models like Dall-E and Stable Diffusion, or chatbots like ChatGPT that can churn out astonishingly convincing text thanks to the power of large language models. But in fact, the real work on generative AI has been happening in the background, in small increments, for many years. One demonstration of that comes from Insilico Medicine, where Harry's guest this week, Alex Zhavoronkov, is the co-CEO. Since at least 2016, Zhavoronkov has been publishing papers about the power of a class of AI algorithms called generative adversarial networks or GANs to help with drug discovery. One of the main selling points for GANs in pharma research is that they can generate lots of possible designs for molecules that could carry out specified functions in the body, such as binding to a defective protein to stop it from working. Drug hunters still have to sort through all the possible molecules identified by GANs to see which ones will actually work in vitro or in vivo, but at least their pool of starting points can be bigger and possibly more specific.Zhavoronkov says that when Insilico first started touting this approach back in the mid-2010s, few people in the drug business believed it would work. So to persuade investors and partners of the technology's power, the company decided to take a drug designed by its own algorithms all the way to clinical trials. And it's now done that. This February the FDA granted orphan drug designation to a small-molecule drug Insilico is testing as a treatment for a form of lung scarring called idiopathic pulmonary fibrosis. Both the target for the compound, and the design of the molecule itself, were generated by Insilico's AI. The designation was a big milestone for the company and for the overall idea of using generative models in drug discovery. In this week's interview, Zhavoronkov talks about how Insilico got to this point; why he thinks the company will survive the shakeout happening in the biotech industry right now; and how its suite of generative algorithms and other technologies such as robotic wet labs could change the way the pharmaceutical industry operates.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

There have been a lot of stories in the news over the last few months about AI chatbots like ChatGPT that can respond to your questions with convincing and well-written answers. These so-called large language models can tell you how to build a treehouse, how to bake a cake, or how to sleep better. But notice that word large. Behind the scenes, these models have learned which word tend to cluster together by sifting through hundreds of billions of pieces of data—basically the entire Internet, in the cast of ChatGPT, including all of Wikipedia and thousands of published books. Now imagine that another chatbot came along that could learn how to generate convincing text response by studying only, say, 18 sentences. Something like that is what this week's guest Raphael Townshend, the founder and CEO of Atomic AI, has accomplished when it comes to predicting the structure of RNA molecules.RNA has been in the news a lot lately too. That's in part because some of the vaccines that helped us beat back the coronavirus pandemic were made from messenger RNA, a form of the molecule that instructs cells how to build proteins (in that case, antibodies to the virus). But RNA has many other functions in the body, and if we knew how to design small-molecule drugs to attach to binding pockets on any given RNA to interrupt or modulate its functions, it could open up a whole new realm of medical treatments. The problem is, if all you know about an RNA molecule is its nucleotide sequence, it's very hard to predict where those binding pockets might be and what kind of drug might fit into them. As a PhD student at Stanford, Townshend designed a deep learning model to tackle that problem. The model, called ARES, started with a proposed structure for an RNA molecule with a known nucleotide sequence, and predict how that proposal would compare to real-world data. ARES turned out to be stunningly accurate, and it acquired its skills by studying a remarkably small training set: just 18 examples of RNAs with known structures. So in a way, it was using the power of small data, together with a bit of physics. Now Atomic AI is building on that original model to create an engine for discovering new small-molecule drugs that could potentially interrupt any disease where RNA is a player.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

The medical news publication STAT calls Will Flanary “the Internet's funniest doctor.” The guests we bring on the show usually talk about how technology is changing healthcare, but Will and his wife Kristin are changing healthcare in a very different way—through comedy. A former standup comic who trained as an ophthalmologist and runs a successful ophthalmology practice in Oregon City, Oregon, Will is better known by his alter ego “Dr. Glaucomflecken.” His short videos have millions of views on YouTube and TikTok, and feature a cast of quirky characters, all played by Will himself, who lightly satirize medical culture and the idiosyncracies of the US healthcare system. And now Will and Kristin have a hybrid comedy and interview podcast called “Knock, Knock, Hi” where they bring on guests who share their own weird and hilarious medical stories.If you wanted to find a comparably successful crossover between medicine and comedy, you'd probably have to go all the way back to TV shows like M*A*S*H and Scrubs. But as funny as Will and Kristin's comedy work can be, it comes from a pretty serious place. Will's been on the patient side of medical care. He survived two bouts of testicular cancer. And in May of 2020, after WIll went into cardiac arrest, Kristin saved his life by administering CPR until emergency medical technicians could arrive and rush him to the hospital, where surgeons implanted a defibrillator. It was a nightmare experience. But Flanary's collision after the surgery with the health insurance bureaucracy may have been even worse. All of it became grist for his comedy sketches, and today the Glaucomfleckens videos and podcast range across topics like what goes on behind the scenes in emergency rooms, how oncologists deliver bad news, or why doctors in different specialties sometimes have a hard time communicating. The basic insight behind Will and Kristin's work is that in a country where the healthcare system often feels so broken and so full of crazy personalities, sometimes you just have to laugh.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

There's a quiet revolution happening in the field of genetic screening of newborns. Within the last couple of years it's become possible to sequence the entire genome of a newborn baby, all six billion base pairs of DNA, and diagnose potential genetic disorders in about 7 hours. That's already happening in a handful of hospitals, with a focus on babies who are showing symptoms of rare genetic disorders. But within five years, says Harry's guest, Dr. Stephen Kingsmore, it should be possible to extend this rapid whole-genome sequencing to every baby in every hospital, whether they're showing symptoms or not.Kingsmore earned his medical degrees in Northern Ireland, trained in internal medicine and rheumatology at Duke, and studied genomic medicine at Children's Mercy Hospital in Kansas City. And he's now the president and CEO of the Institute for Genomic Medicine at Rady Children's Hospital in San Diego. There, he's been leading an aggressive push to prove that rapid whole-genome sequencing and diagnosis can not only save the lives of newborns, but save the healthcare system a lot of money by making hospital stays shorter and therapies more directed. He's been able to use that argument to get Medicaid agencies in California and five other states, as well as a handful of private insurance companies, to cover whole-genome sequencing as the new standard of care for babies who end up in intensive care with unexplained illnesses. And if his newest project, BeginNGS, succeeds, it could lead to universal screening of all newborns for hundreds or even thousands of rare genetic disorders. For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

Last October, medical imaging company Arterys announced that it had been acquired by healthcare AI giant Tempus. That caught our attention here at The Harry Glorikian Show, because back in the fall of 2018—exactly 100 episodes ago, as it turns out—we welcomed Arterys co-founder and CEO Fabien Beckers as our guest. At the time, Arterys had recently won FDA clearance for a cloud-based software platform that used deep learning to help radiologists automatically locate the contours of the ventricles of the heart. The company would go on to apply similar technology to MRI and CT images of all sorts of tissue, including the breast, chest, brain, and lungs. What made the platform doubly unique was that doctors could access it over the web, so hospitals didn't have to maintain expensive on-premise software or hardware. Today it would be hard to find a health tech company that isn't using AI and cloud computing in some way, but it's easy to forget how recent those developments are; Arterys was the very first company to obtain FDA clearance for a cloud-based radiology platform. In light of the acquisition news, we decided to dip into the show's archives and bring that you that original interview with Fabien Beckers, who's now head of digital pathology for the Alphabet company Verily Life Sciences.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

You can wear an Oura ring or a WHOOP armband to tell you how your body is adapting to exercise. A continuous glucose monitor can send your phone information about your blood sugar levels are changing. And during the pandemic, a lot of people bought home pulse oximeters to monitor their blood oxygenation levels. But there's one part of the body where home health sensors haven't reached yet, and that's our brains. They're protected inside our thick skulls, which means it's pretty hard to measure what's going on in there. Until recently, the only real instruments available to doctors and neuroscientists were big hospital-based machines like X-Rays, CT-scans, EEGs, and MRIs.But that might finally be changing. Harry's guest this week is Ryan Field, chief technology officer at Kernel. The vision of the L.A.-based company is to develop a consumer device that would work like a pulse oximeter, but for your brain. The first version, Kernel Flow, is shaped like a bicycle helmet, and it contains more than 50 low-power lasers that beam light through your scalp into your skull, into the outermost layers of your brain. Hundreds of detectors built in the helmet collect the light that's scattered back to determine oxygen levels in the brain's blood supply, which is an indirect measure of neural activity.Field says the company isn't yet targeting specific consumer applications for the Kernel Flow. But it's already using the device in early studies designed to measure a user's level of focus on a specific task, or how their brain activity changes in response to pain therapy or psychedelic drugs. Field says what Kernel has done is sort of like building the very first iPhone -- but if the only app the device came with was Maps. Now it's up to developers to figure out what else to do with it.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

Out of all the dozens of types of cancer that occur in humans, we habitually screen for only five: breast, cervical, colon, prostate, and lung. But what if there were a single test that could detect 50 types of cancer, based on a simple blood draw? That's exactly what's possible today, thanks to the Galleri test, introduced by Illumina spinoff Grail in 2021. The $949 test, which won breakthrough designation from the FDA in 2019, uses machine learning to assess the patterns of methyl groups—molecules that attach to chromosomes and control gene activity—in free-floating DNA shed by tumors. This week Harry interviews Grail's president, Dr. Josh Ofman. He says that the company is working to bring down the price of the test, and that if multi-cancer early detection tests like Galleri are eventually approved for population-level screening, it could help avert 100,000 deaths per year.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

These days, there's an explosion of digital imaging technology for almost every part of the body. There are the familiar types of imaging everyone knows, like CT scans, MRIs, ultrasound, and of course, X-rays. But now doctors and medical researchers are also exploring newer types of digital imaging technology, such as Optical Coherence Tomography, or OCT.OCT uses near-infrared light that penetrates just a couple of millimeters into a tissue such as an artery wall or the retina of the eye. By collecting the light that scatters back, OCT can produce an incredibly high-resolution cross section or even a 3D reconstruction of the tissue. Ophthalmology is one of the fields putting OCT to use most aggressively, partly because it's perfect for showing cross-sections of the retina, the iris, the cornea, or the lens on the scale of micrometers.But as you can imagine, every time an ophthalmologist or optometrist uses an OCT scanner, the procedure generates a huge amount of digital data. Harry's guest, Carlos Ciller, started a company called RetinAI whose mission is to help eye doctors, eye surgeons, and scientists studying the eye manage and analyze all that information. And not just information from OCT, but from other types of eye imaging like fundus photography and fluorescent angiography.At one level, RetinAI is just doing its part to cure a huge headache we've talked about again and again on the show, which is the lack of standards and interoperability in the healthcare IT world. They want to make it possible to store and analyze digital images of the eye no matter what technology or device was used to capture it. But more intriguingly, once that data is stored in a structured way, it's possible to use machine learning and other forms of artificial intelligence to sort through image data and identify pathologies or double-check the judgments of human physicians. RetinAI is developing algorithms that could make it easier to diagnose and treat common conditions like age-related macular degeneration—a form of damage to the retina that causes vision loss in almost 200 million people around the world. Ciller told me he started out his career as a telecom engineer and never thought he'd wind up running a 40-person company that works to help people with vision problems. But at a time when there's so much new data available to diagnose disease rand identify the best treatments, journey's like his—from the computer lab to the clinic—are becoming more and more common.  For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

There are many causes for diabetes—chronicallly high blood sugar—but there's also a growing list of ways to prevent it, or manage it once it starts. Wearable technologies like continuous glucose monitors or CGMs are high on that list. These devices have tiny needles that penetrate the skin and measure glucose levels in the interstitial fluid between cells. They can send that data to a smartphone, where apps made by a variety of companies can record it and analyze it.January.ai is one such company, and co-founder and CEO Noosheen Hashemi joined Harry on the show back in July of 2021. It turns out that the same foods can have different effects on the blood glucose levels of different individuals, and January's app starts off using live CGM data to study those patterns using machine learning algorithms. Then it can start making predictions about a user's future blood glucose levels, even after they stop wearing a CGM. That can help them make smarter decisions about what, when, or how much to eat, or how much they need to exercise after eating.January's main goal is not to treat diabetes but actually to prevent it from arising in the first place in the tens of millions of people who have signs of pre-diabetes. Now Hashemi has helped to launch a second business, Eden's, that helps with that goal by promoting better gut health. The company makes a nutritional supplement that provides a blend of polyphenols, probiotics, and prebiotics to help improve the function of the bacteria that call your large intestine home. Probiotics, which live organisms introduced to change the makeup of your gut microbiome. Prebiotics are non-digestible substances that are fermented by beneficial bacteria like bifidobacteria and lactobacillus, breaking them down into useful nutrients like short-chain fatty acids. Altogether, the Eden's blend is designed to keep your gut microbiomes happy, which can have the useful side effect of helping to keep your blood glucose steady. Harry talked with Hashemi to talk about why that's so important, and about the work January has been doing this year to update its glucose monitoring app—and how the app works in concert with the Eden's supplements. For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

About half a million babies are born every year through IVF. That number would probably be a lot higher if the procedure were cheaper and more accessible—but making that happen would  mean transforming IVF from an artisanal craft into something more like a modern automated factory, with AI helping doctors and technicians make faster and better decisions at every step. And that's exactly what Harry's guest Mylene Yao, the co-founder of Univfy, is doing. Univfy helps patients with two aspects of the IVF process. The first is using machine learning to provide patients with a more accurate assessment of  the odds of success, before they decide whether to invest in one or more IVF cycles, which can cost up to $30,000 per cycle. The second is financing. Univfy works with a bank called Lightstream to provide up to $100,000 in financing for up to three rounds of IVF, with a large refund as part of the deal if the treatments don't result in a baby. Harry talks with Dr. Yao about the prospects for far broader access to IVF, now that the field is finally adopting more ideas from the worlds of technology and finance. For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

For the 100th episode of The Harry Glorikian Show, Harry welcomes Phil Febbo, chief medical officer at Illumina. The San Diego-based company is the leading maker of the high-speed gene sequencing machines that are at the core of the precision medicine revolution. The company has an 80 percent market share, which means that if you or your loved one has had any sequencing done for any reason, chances are your samples were sequenced on an Illumina machine. Gene sequencing is already a key part of both diagnostics and treatment decisions for many disease, but its use is only going to expand as the technology gets faster and cheaper.This fall, Illumina announced that it's coming out a new gene sequencing machine called the NovaSeq X that can sequence a genome more than twice as fast as Illumina's previous top-of-the-line machine, and at a lower cost. That's bound to speed up progress all across the field of genetic medicine, drug discovery, and life science research. And that's where Harry starts his interview with Febbo.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

In 1978, Louise Joy Brown was celebrated as the world's first "test tube baby," born as the result of in vitro fertilization (IVF). Today, Brown is 44 years old, and what was a technological triumph in 1978 is almost routine today, with half a million babies born every through IVF. But Harry's guest this week, gynecologist and investor David Sable, thinks IVF still isn't nearly as reliable or accessible as it should be. From his studies of infertility services, he's convinced that society is on the cusp of bringing down the cost and raising the success rate of IVF, so that it can finally become an affordable solution for millions more people every year who want to start or grow their families. And he thinks one of the keys to the next big wave of advances in IVF will be artificial intelligence. As you'll hear in this week's interview, Sable thinks most IVF labs today still operate almost like artisanal kitchens, with way too much riding on the judgment of individual doctors and technicians. He thinks machine learning algorithms could supplement human expertise at many points in the process, and turn what's essentially a craft into a truly automated and predictable industry. His central argument is that IVF won't truly be democratized until providers have “engineered the hell out of” the procedure, to increase success rates and lower the chances that patients will have to pay for more than one cycle of the treatment. At the same time, he says the concept of value-based care needs to make its way into the IVF world, so that patients and their insurers or their employers only pay when the procedure works, not when it fails. Stay tuned to future episodes for more discussion about the role of AI in IVF.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

“LinkedIn meets ZoomInfo meets Zocdoc, but for doctors." That's how H1 co-founder and CEO Ariel Katz describes the information service his company offers. It's a response to the fact that the healthcare is incredibly fragmented, with no central database or platform that everyone can use to share their professional profiles and get in touch with colleagues. (Physicians never adopted LinkedIn for this kind of networking because they just don't switch jobs very often.) Without a central directory, patients can have a hard time find the right doctors, and doctors can have a hard time finding each other—say, when they might be searching for research collaborators. It's an even bigger frustration for drug companies, who need to know which doctors can help them enroll the right patients for clinical trials. H1 is trying to solve all of those problems by building what Katz says will be the world's largest graph database of people in healthcare. After participating in the 2020 batch of startups at the Silicon Valley incubator Y Combinator, H1 has rocketed forward, raising almost $200 million in venture capital. This week Ariel joins Harry to talk about how and why H1 has grown so quickly, and how better networking could accelerate drug development and help patients find the best doctors for them.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

If you walked into a typical life science research lab at a university or a biotech startup, you might be surprised to see how much paper is still laying around. A lot of researchers still keep records of their experiments and studies in paper notebooks—in fact, along with doctor's offices, life sciences labs might be one of the last bastions of professional life that surrenders to digitization. But these labs are surrendering. And Harry's guest this week, Erwin Seinen, is helping to accelerate that shift. He's the founder and CEO of a company called eLabNext, whose core product is a Web-based software platform called eLabJournal that includes tools for inventory and sample tracking, managing experimental protocols and procedures, and recording experimental results.Seinen spent years building e-commerce tools before he went back to school and got his degree in medical genetics. So he knew how to write software, and to streamline his dissertation work, he built his own electronic lab notebook tool. He says his lab colleagues were so jealous that he realized every lab researcher needs a similar tool. And that's how eLabNext was born.But when absolutely everything goes digital, there's the danger of losing the special connection between mind, pen, and paper that goes with making old-fashioned handwritten notes. Harry talked with Seinen about that, as well as his vision of how an electronic lab notebook can fit together with other lab tools in an era where there's just too much data to print out everything on paper. If companies and universities manage this transition right, they can benefit from all the latest digital tools—without sacrificing any of the spontaneity, curiosity, or creativity that good science is all about.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

Harry's guest this week, Brian Pepin, says there haven't really been any advances in the treatment of Parkinson's Disease in a decade. The standard treatment is still the standard treatment—meaning various drugs to replace dopamine in the brain, since the loss of neurons that produce dopamine is one of the hallmarks of the disease.But there has been one important change during that decade. Thanks to new technologies, ranging from wearables like the Apple Watch to sophisticated deep brain implants from companies like Medtronic, we're now able to gather a lot more data about what's happening in the daily lives of patients with Parkinson's, and how the disease is affecting their brain function and their physical movement. Which means there's now the potential to make much smarter and more timely decisions about how to dose the drugs patients are taking, or whether they should think about joining a clinical trials.Gathering and analyzing that information and feeding it back to patients and their doctors in a user-friendly form is the mission of Rune Labs, where Pepin is CEO. He says we're on the edge of a new era of “precision neurology,” where data gives doctors the power to predict the course of a disease and muster a meaningful clinical response. And he wants Rune Labs to be at the leading edge of that change. For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

In most hospitals, the practice of radiology went digital years ago. Today you'll rarely find a radiologist examining a broken bone or a fluid-filled lung on a sheet of old-fashioned X-ray film. But pathology isn't as computerized. For a variety of cultural, technical, and regulatory reasons, many pathologists still prefer to look at tissue samples the old-fashioned way, on a slide under a microscope.Philadelpha-based Proscia is working to change that—and open up pathology to the power of remote work and automated image analysis—by building a cloud-based infrastructure for storing and sharing scanned pathology images. Harry's guest today is Proscia CEO David West, who says there are still strong cultural barriers to the adoption of digital pathology, but "the community is realizing this can be really great for them and their discipline." West says easier scanning, higher resolution, faster image delivery, and the ability to review images from anywhere and tap the power of artificial intelligence are powerful advantages driving adoption of Proscia's platform.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

We use our smartphones to communicate, shop, navigate, watch videos, take pictures, share our lives on social media, track our exercise, and listen to music and podcasts. So why shouldn't they also be the main interface to our healthcare experiences? That's the question P.J. Jain started out with in 2010 when he left behind a career in networking and telecommunications to start a company dedicated to mobile health. Called Vibrent Health, the company went on to win a game-changing contract in 2015 to help the National Institutes of Health build a mobile data-gathering infrastructure for a giant research program called All of Us.That's a 10-year project designed to gather medical data from more than a million people around the United States to help doctors make more customized health recommendations based on a patient's environment, lifestyle, family history, and genetic makeup. If you're going to try to recruit a million people into your research study and keep tabs on their health, and if those people are going to be from diverse backgrounds, and if they're going to be distributed around the country, then there's only one practical way to reach them, and that's on their smartphones. NIH asked Vibrent to build a mobile app and an online portal that would become the communications backbone and the central data gathering repository for the whole project. And now that NIH is six or seven years into the All of Us project, it's clear that in some ways the project, and Vibrent's front end, have leapfrogged over the rest of the US healthcare ecosystem. The app provides an easy way to gather and manage data from patients in the study, and to monitor and interact with them, while still protecting their privacy.  As Jain puts it, it meets All of Us participants "where they are" – meaning, on their phones. Technology like that still isn't part of the offering at most big health plans or hospital networks. But Vibrent is working to change that by partnering with health systems, academic health centers, pharmaceutical companies, public health organizations, and research organizations to get its mobile apps distributed more widely. If you believe that our phones are going to be a key element of personalized and precision medicine for everyone, then the work Vibrent is doing with NIH and its other customers is worth watching.For a full transcript of this episode, please visit our episode page at http://www.glorikian.com/podcast Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

Wet labs at life science companies look and work the same pretty much everywhere. They're full of incubators, refrigerators, centrifuges, liquid handlers, gene sequencers, DNA and RNA synthesizers, and all sorts of other complex equipment. And a lot of these machines are automated—but the larger workflow in a life sciences R&D lab is very much not automated. For the most part it's individual researchers who decide how and when to use each piece of equipment, and individuals who move samples and materials back and forth between the machines. And that's a problem, because if you're trying to collect evidence for a scientific paper or a regulatory filing or trying to manufacture a product that's verifiably safe, you need to make sure that the same procedure gets carried out exactly the same way every time.Our guest this week, Artificial CEO David Fuller, believes that life sciences labs will always revolve around manual labor, but thinks there's a way to orchestrate the process more precisely. Artificial makes software that allows lab managers to create what he calls a digital twin of their entire laboratory. Inside this digital twin, data structures track what's happening with each piece of lab equipment and keep them in sync, even if they're from different manufacturers. The software provides what Fuller calls “a single pane of glass that makes it easier to see the state of the equipment and the science as it's running in your lab”…meaning what's happening, why it's happening, and what errors may be cropping up. Humans will always stay in the loop, but Fuller says the benefit for companies who orchestrate their labs in this way is that the data and the products coming out of the lab will be more consistent. Which will be even more important as laboratories start to act more like factories, where a lot of the actual production of biologic drugs or other materials happens.For a full transcript of this episode, please visit our show page at http://www.glorikian.com/podcastPlease rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.

For people with common health problems like diabetes or high blood pressure or high cholesterol, progress in pharmaceuticals has worked wonders and extended lifespans enormously. But there's another category of people who tend to get overlooked by the drug industry: patients with rare genetic disorders that affect only one in a thousand or one in two thousand people. If you add up all the different rare genetic disorders known to medicine, it's a very large number; Harry's guest this week, Charlene Son Rigby, says there may be as many as 10,000 separate genetic disorders affecting as many as 30 million people in the United States and 350 million people worldwide. That's a lot of people who are being underserved by the medical establishment.Rigby is the head of a new non-profit organization called Rare-X that's trying to tackle a systematic problem that affects everyone with a rare disease: Data. In the rare disease world, Rigby says, data collection is so inconsistent that each effort to understand and treat a specific disease feels like reinventing the wheel. For longtime listeners of the show, that's a familiar story. Time and again, Harry has talked with people who point out the harms of storing patient data in separate formats in separate silos, and who have new ideas for ways to break down the walls between these silos. Rare-X is trying to do exactly that for the rare disease world, by building what Rigby calls a federated, cloud-based, cross-disorder data sharing platform. The basic idea is to take the burden of data management off of rare disease patients and their families and create a single central repository that can help accelerate drug development.Harry talked with Rigby about the challenges involved in that work, how it gets funded, how soon it might start to benefit patients, and what it might mean in a near-future world where every child's genome is screened at birth for potential mutations that could lead to the discovery of rare medical disorders.Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.TranscriptHarry Glorikian: Hello. I'm Harry Glorikian, and this is The Harry Glorikian Show, where we explore how technology is changing everything we know about healthcare.For people with common health problems like diabetes or high blood pressure or high cholesterol, pharmaceuticals has worked wonders and extended lifespans enormously.But there's another category of people who tend to get overlooked by the drug industry.And that's patients with rare genetic disorders.By definition, rare diseases are rare, meaning they might only affect one in a thousand or one in two thousand people. But here's the thing. If you add up all the different rare genetic disorders known to medicine, it's a very large number.My guest today, Charlene Son Rigby, says there may be as many as 10,000 separate disorders affecting small populations.And if you count everyone who has these conditions, it may add up to as many as 30 million people in the United States and 350 million people worldwide.That's a lot of people who are being underserved by the medical establishment.And Rigby is the head of a new non-profit organization called Rare-X that's trying to fix that.Now, there are a lot of rare disease organizations that are looking for a cure for a specific condition.Rigby actually came to Rare-X from one of those, the STXBP1 Foundation, which is searching for a treatment for a rare neurological condition that affects Rigby's own daughter Juno.But Rare-X is a little different. It's trying to tackle a systematic problem that affects everyone with a rare disease. The problem is data.Rigby says that in the rare disease world, data collection is so inconsistent that each effort to understand and treat a specific disease feels like reinventing the wheel. For longtime listeners, that'll be a very familiar story.Time and again I've talked with people who point out the harms of storing patient data in separate formats in separate silos, and who have new ideas for ways to break down the walls between these silos. Rare-X is trying to do exactly that for the rare disease world, by building what Rigby calls a federated, cloud-based, cross-disorder data sharing platform.The basic idea is to take the burden of data management off of rare disease patients and their families and create a single central repository that can help accelerate drug development.I talked with Rigby about the challenges involved in that work, how it gets funded, how soon it might start to benefit patients, and what it might mean in a near-future world where every child's genome is screened at birth for potential mutations that could lead to the discovery of rare medical disorders.Here's our full conversation.Harry Glorikian: Charlene, welcome to the show.Charlene Son Rigby: Thanks. Nice to be here, Harry.Harry Glorikian: So I've been reading about what you guys are doing. I mean, all of it sounds super exciting. I'm, you know, been looking into this space for a long time from a rare disease, but many different angles of it. But can you just start off, tell us a little bit about yourself and how you got active in this world of rare disease research?Charlene Son Rigby: Yeah, thanks for that question. So I've spent most of my career building scalable software solutions for analyzing big data, and that's been both in health care as well as enterprise software. And so I'm now the CEO at Rare-X where we're building a platform to analyze rare disease data cross-disorder. And prior to being at Rare-X, I was the chief business officer at a company called Fabric Genomics, where we developed artificial intelligence approaches to speed diagnosis of patients through genomics. We had a considerable focus on rare disease and contributed to projects like the 100,000 Genomes Project and also the work that Stephen Kingsmore is doing at Rady Children's with diagnosing critically ill newborns in the NICU. And so when I started at Fabric, my daughter Juno was ten weeks old. She's my second child. And it was kind of a fortuitous timing, in some ways kismet, because at when I started at Fabric, I didn't know that she was going to start experiencing issues with her development. But at around four months she started missing milestones. And that started us on a three and a half year journey to find an answer to what was going on with her. And so during that time, we went through many, many tests, including genetic tests, MRIs, all kinds of all kinds of things, and everything kept coming back as negative or inconclusive. And so I was working at a genomics company, and so I kept pushing for whole exome testing, which at that time was still not, not readily available clinically and by insurance was still considered experimental. So we were denied three times, until we finally were able to get authorization in 2015. And so in early 2016, we got my daughter's diagnosis and she has a mutation in a gene that's involved in communication between neurons and the genes called STXBP1.Charlene Son Rigby: And so it's very rare. Thirteen kids born a day somewhere in the world. So thinking about Juno and thinking about this from a science standpoint, that it was pretty interesting that when she was diagnosed because she didn't have a classic phenotype for STXBP1. So most kids, 90% of the kids have seizures. And she has more of the symptoms around developmental delay, low muscle tone, cognitive issues and delayed walking and motor issues. And, you know, this this kind of challenge around these atypical phenotypes, I think, is actually becoming much more common in disease generally, so in rare disease and also more broadly in more common conditions as we're really starting to understand kind of the true breadth of patients. So in terms of your original question about my journey through rare disease, so I went on to co-found the STXBP1 Foundation to accelerate the development of therapies for kids like my daughter. And then coming to Rare-X was really a kind of joining of my software background with my passion for rare disease and really wanting to do something more broadly for the rare disease community.Harry Glorikian: I have to tell you, like what you said, three and a half years, I'm like, oh, my God. Like, I would be I have so many stories. And like when I was at Applied Biosystems and, you know, we're doing all this work. It just boggles the mind that some of these things are not really readily available to help get over that diagnostic odyssey for especially parents, because you're going to do anything to help your child. I'm glad it's actually moving theoretically faster these days. I'm not sure if insurance has actually kept up, but we're, on the technology side, I know we're everybody's pushing the envelope now. But when we talk about rare disease and you did some of the numbers but we hear about these rare diseases, I think a lot of people think of like there's an n of 1, right? They assume that this disease only affects a tiny number of people. Right. Maybe just one or a handful worldwide. But I mean, the fact is, if you add up all these different rare genetic diseases that exist in the human population, the number of people is actually pretty big. I mean, can you sort of. Put that into some sort of scale for us in what you've seen.Charlene Son Rigby: Yeah, you're absolutely right. You know, rare disease is by definition rare. And so it's easy in some ways to be dismissive of a rare disease because, oh, it's only affecting a few people. And it's true that a single rare disease can affect a very small number of people, even down to the n of 1 case that you talked about. From a definition standpoint, so, in the US, rare disease is defined as a disease affecting fewer than 200,000 Americans. And in Europe, in the EU, it's defined as affecting no more than one in 2,000 people. So we even though for ultra rare or n of 1 diseases, we can be talking about a small number of people, or like in my daughter's disorder, we can be talking about low thousands, there are still thousands of rare diseases and the traditional number that we hear a lot is 7,000. So 7,000 rare diseases. Rare-X is about to come out with some research that indicates that there are over 10,000 individual rare diseases, and this is really due to our growing understanding of genetics. So previously we might have grouped together a set of disorders based on what the symptoms were like. But now we understand that those actually are due to a different genetic etiology or different cause at a genetic level. And so if you aggregate all of those people up, across those 10,000 rare diseases, you know, what we're looking at is one in ten, potentially one in ten people in the world. And so in the US that's about 30 million people and in total 350 million people worldwide. So it's really a huge number of people. And from an impact standpoint, it's staggering when you look at the impact from a health care standpoint and from an economic standpoint.Harry Glorikian: Yeah, I mean, if you can diagnose, I mean, if there is a way to treat someone, then you get to it faster. And the economic impact is huge and unfortunately, if there isn't, maybe it spurs a pharmaceutical company to, you know, start working on it or figure out a way to treat that patient better. But at least you, I always tell people, the better the diagnosis, the better the next step. I see people sometimes, it seems like they're throwing a dart, you know, and they're it's an educated guess, but it's not, you know, the accurate diagnosis that you'd like to have. So. But how and where, when was sort of Rare-X born and what are you trying to do with the organization? What do you want to fix?Charlene Son Rigby: Yeah. So Rare-X was a pandemic baby. The organization was started in early 2020 and I just joined the organization last year. But, you know, it's really been quite a journey being able to have the, launch the platform during COVID. And I know we can talk about that in a little bit, but the unsolved problem that we are working to address is really around collecting data for rare disease. And one might ask, well, why is this an issue? I'll give an example. From the early days of the STXBP1 Foundation. W e assembled our scientific advisory board and we got together for our first scientific meeting. And we were going to develop our roadmap so that that would guide our priorities in terms of scientific development. And we were all very focused on therapies. So my expectation going into the meeting was we were going to talk about all the mice models we were going to build. What did we need to do in the lab? How are we going to get to that first therapeutic candidate? And the number one priority that came out of that meeting was to build a prospective regulatory-compliant natural history study. And so it was a huge learning for me because if you look at the kind of canonical steps in terms of drug development, it's always preclinical and then you move into clinical. And what I think that kind of simple model misses is this foundational layer around the data that you need and the real kind of understanding of the symptoms and the disease progression that is critical to building effective therapies, developing effective therapies.Charlene Son Rigby: And so that's really what Rare-X was started to do, was to enable the gathering of this data, the structuring of this data and enable it to be shared and to do this at scale. So, cross-disorder. And there are several problems today that that make this challenging. And so maybe I can talk a little bit about that. There are three or four of these significant challenges. So today some of this data does exist, but it's often kind of trapped in data silos. So it was generated in an individual project that might have happened in academia or industry. And then the data is often really only accessible to the group that collected it. And in rare disease where we don't have that many patients, it really makes it challenging to create a kind of more comprehensive understanding and picture of the patients if that data is trapped in these individual silos. Charlene Son Rigby: Another challenge that that we've seen is the lack of usable data. So individual studies may not include the key data that's needed to drive drug development forward. So some of these data repositories, they might either be a symptom specific. So they're looking at a specific organ system that might have been of interest to that researcher. So they're an incomplete picture. Or some of these repositories or these registries were started by passionate parents. You talked about that, the urgency that one feels as a parent, that I feel as a parent. And the registry may have been structured or the questions may have been structured in a way that isn't necessarily immediately usable by researchers because of the fact that it was started by a parent who, like you, you might not have had a statistical analysis background, you might not have had a survey methodology background. And we so those can be challenges in terms of having the data be robust and usable later. Charlene Son Rigby: And then the other thing that can be challenging and probably is often the most challenging is, is especially in these very, very new diseases, there's no data, and it takes quite a bit of funding to start data collection. Often, often passionate parents are going around trying to get researchers interested in their disorder. But it's often that you have to have a little bit of data to get a researcher interested. And so this is a huge challenge in terms of implementing data collection. And the other thing that kind of underlies this is that patients often are not empowered in this process. And so that was a fundamental piece of the way that we've structured Rare-X and the way that we collect data and the way that we enable patients to participate in the process to power data collection.Harry Glorikian: Yeah. I mean, it's, you know, they make movies out of this, right? People trying to push this boulder up a hill. So, what are the new ideas that say Rare-X is bringing to the table? I mean, your organization has called for like, you know, the largest data collection and federated data system and analysis platform in rare disease. So, I think unpacking that statement because it's a big statement, right, of, you know, what are you doing to improve data collection? What do you mean by federated, for those people that are listening? And why is it important? A  nd how will the platform enable better analysis of this rare disease data?Charlene Son Rigby: Yeah. Great question. From a design perspective, the one of the things that we wanted to do was make sure that the platform was cross-disorder. So a lot of registries are started for an individual disorder. And what we really wanted to be able to do was given that number of 10,000 diseases, how do we scale to support so many disorders to accelerate therapies? And so a fundamental design principle was to do that cross- disorder. The other piece of this is that we are focused on patient-reported data. So typically a participant will join the research program, create an account on the platform and they are either a patient or a caregiver of a patient and providing information on their symptoms. There is a lot of other data out there in the ecosystem that could come from other related registries, or it could come from clinical data, it could come from many different types of studies. And so we really want to enable the aggregation of or federation of that data. So you asked me to define that term. It really means bringing together multiple different data sets in a way that enables those data sets to be analyzed together. And I think, again, going back to this theme that for any individual rare disorder, there aren't that many patients. And so analyzing that data, kind of individually, we are really missing the opportunity to maximally use the data that's been contributed by rare disease patients. And I would even argue that it's a moral imperative for us to do that as a rare disease community, because we urgently need to move these understanding of these disorders forward in development of therapies as well.Harry Glorikian: I almost wish I could take all the companies I know doing this and put them there so the n goes up for everybody. But I know that there's all sorts of reasons that that doesn't happen. But, you know, when you were saying we're pulling in patient-reported data, you know, the first thing, and we talk a lot about this from different groups on the show is, you know, would a wearable or one of these other devices that are now available give you more granular, real- time information that might be valuable to this sort of study. And have you guys considered things like that?Charlene Son Rigby: T he short answer is yes, because the our desire is to really continue to expand the types of data that are collected. And the I think that the nice thing about mobile, mobile devices, wearables, is that it makes it very easy to collect that data. And so we have a partnership with Huma. They do work in the mobile space. And we're definitely continuing to evaluate where we can develop partnerships there. I mean, our goal overall is to de- burden patients and so that the, if we can do that in a way that additive to an overall body of research, then we're huge proponents of it. And I think that it's also important that we're really trying to create an open system. So our partnership model is a very, very open partnership model in terms of who we can work with.Harry Glorikian: Yeah, I had a really extensive conversation with the head of data sciences at WHOOP yesterday and you know, they're pulling in somewhere between 50 and 100 megabytes of data per patient per day. I shouldn't say patient -- per individual per day. Right. I was like, that's a lot of data. And she was, you know, the kid in a candy store because they're she's like, we can really see what's happening with people. And you can ask questions at a scale that you couldn't ask before. Like she was saying, you know, the last one of the things that we're working on publishing is 300,000 people. You couldn't imagine that in the world of, say, a clinical trial of 300,000 people are just going to, you know, and you have all the data, almost 24/7 on this person that's delivered by this device, which is sort of interesting, you know, place to be. So, you know, I know that you don't have 300,000 people in one in one area, but it'd be interesting to have that sort of 24/7 data available from these kids if you could, you know, get a device that would lend itself to that. But what stage is the company at in building the platform and you know, I guess the killer question is, when will drug developers or other researchers be able to start using it? If they already are, do you have any early success stories you can share?Charlene Son Rigby: Yeah, yeah. It's really a very exciting time at Rare-X. So the platform launched last summer and we have over 25 communities on the platform. And those encompass several hundred participants already. So we're really starting to see some exciting numbers in terms of in terms of participants. So we are launching our researcher portal at the end of Q2. So very soon. And at that point, any researcher, so academic researchers, pharma researchers, will be able to access the data and be able to utilize analytical tools to really interrogate the data. I'm excited that we also have launched our first sponsored program, and that's with Travere. They're supporting the homocystinuria community to start data collection, to start a registry. And we just launched that at the end of February.Harry Glorikian: So I want to. Jump back, like just talking through some of the biggest technical challenges along the way. I mean I know one of your goals is like interconnecting all these disparate data sources. But one of the issues that always comes up is how do you clean up that that existing data so that you can store it all the same way. And then obviously that enables somebody to then do the analytics right after that. But the biggest issue that I hear from a lot of people is, man, it takes a lot of effort to make sure that that data is cleaned up and put in the right place.Charlene Son Rigby: Yes, the data munging. Yeah. I mean, I think that that is really the, a significant challenge, because creating research-ready data and then harmonizing data sets is a huge amount of upfront work that has to happen before you can actually do any of the analysis and the data mining. So what we have done with the core data that's being generated within Rare-X is that we have mapped it to data standards. So we utilize standards like the human phenotype ontology, OMIM, HL7, so that the data that we're producing already is mapped to all of these generally utilized standards. And then we would if we were working on a federation project, the same thing would need to happen with these other data sets to really enable that type of integrated that type of integrated analysis. And you're right, it's it can be a very brute force effort in terms of doing it accurately. And that's why I think that it's really important from a from an industry perspective to really start adopting these standards and putting them into the base model, you know, for assuming just making the assumption up front that the data is going to be federated and utilized downstream. I think that kind of traditional studies, a lot of the scope was more really looked at in terms of what are we doing with the data today? And we need to be really thinking about from a lifetime perspective, how is this data going to be used?[musical interlude]Harry Glorikian: Let's pause the conversation for a minute to talk about one small but important thing you can do, to help keep the podcast going. And that's leave a rating and a review for the show on Apple Podcasts.All you have to do is open the Apple Podcasts app on your smartphone, search for The Harry Glorikian Show, and scroll down to the Ratings & Reviews section. Tap the stars to rate the show, and then tap the link that says Write a Review to leave your comments. It'll only take a minute, but you'll be doing a lot to help other listeners discover the show.And one more thing. If you like the interviews we do here on the show I know you'll like my new book, The Future You: How Artificial Intelligence Can Help You Get Healthier, Stress Less, and Live Longer.It's a friendly and accessible tour of all the ways today's information technologies are helping us diagnose diseases faster, treat them more precisely, and create personalized diet and exercise programs to prevent them in the first place.The book is now available in print and ebook formats. Just go to Amazon or Barnes & Noble and search for The Future You by Harry Glorikian.And now, back to the show.[musical interlude]Harry Glorikian: Now if we go one step before like getting that data, I mean. I have to imagine there's a huge political, bureaucratic or organizational challenge when it comes to who controls that data. And I think I have to assume,  part of your job is convincing them to share it, right, despite its potential as intellectual property. Right. So how do you get on the phone and say, “Why don't you press send and shoot that over to me and so that we can take the next steps with it?”Charlene Son Rigby: Yeah, well, this is a really significant challenge, and I think that we're in a time of change in terms of attitudes around this. And part of it is what's been happening in terms of national programs to collect data. And people are starting to see the benefit of being able to share and really utilize these larger data sets. But the reality today is that in terms of the status quo, researchers control the data, and that's because the data was generated in a specific project that might have happened in academia or in industry. And there's a challenge with alignment of incentives. So on the academic side, I think that if one were to ask a researcher, do they want to hoard data, they don't want to hoard data. But the reality is, is that we still have this challenge with academic tenure and needing to publish or perish in that environment. And so researchers are still rightly concerned because of that paradigm that they have to write their paper and get their paper in before they can feel comfortable with allowing others to access the data. And so something really needs to happen there to that incentive system. Charlene Son Rigby: And in pharma, interestingly, I think that that's also an area where there has been a feeling that data is almost akin to intellectual property. But I think that especially in rare disease, there has been a growing understanding that accessing natural history data is not going to, at the end of the day, enable pharma to win because they're going to win on the quality of their therapeutic pipeline and how quickly they can get those therapies through to a successful market approval. And so what we've been really working to do is position natural history data as pre-competitive and for rare disease, frankly, it's too expensive to build these data sets, you know, alone. They're, as we scale to all of these disorders it's going to become untenable to for each company to build their own data set. The thing that we need to do and what Rare-X has been working to do with our collaborators is to transform the way that research has been done and initiated and break down these barriers and just show that the model of building these pre-competitive collaborations can work, both from a how does the business model work and then how is the data shared? And so I think that Rare-X being a nonprofit and a kind of neutral third party is really additive in terms of building those relationships so that this, this kind of public-private partnership model can really serve as a way to drive this type of change.Harry Glorikian: Now. Okay. So we've talked about industry sharing data, but I always I mean, especially in the last maybe 5 to 10 years, I keep thinking about, you know, how much of this comes directly or will come directly from patients, right? If they have control or access to their data, they have the ability, theoretically, the ability to then share that data. Right. And it could be just for the research in general as opposed to, not specifically to find a cure for a specific disease. So how do you get that data or convince patients to share it?Charlene Son Rigby: Yeah, well, I think that in in rare disease patients are typically highly motivated. You know, there are many rare diseases that can be pretty devastating in terms of the symptoms and the disease progression. And so overall, there is a a good portion of the rare disease population that is motivated to provide their data. And so what we do there and I think that that your points about the paradigms and thinking about it, that the patients are sharing their data, is really important. Because I think that that gets lost a lot. You know, a patient, and we've all signed up for some research study in our lives. You go and you fill out a survey or you contribute a blood sample or something, but oftentimes the patient contributions get forgotten because it becomes part of the researcher's data set. And so the what we're really trying to do is turn around that kind of paradigm with a core principle that patients are the ones who own their data and they're contributing their data. And so we enable them to, through an innovative consent process, we enable them to basically say that, yes, they're willing to share their data for these types of projects, and they can change that at any time. And we really feel that that changes the paradigm and allows them to have a real seat at the table. And then I wanted to also talk about, because obviously not everyone is — there is this proportion of folks who are motivated and trust and that's part of the reason that they will be willing to share their data — but there is also a portion of the population that might not be as motivated. And so it's important for us to be able to reach those populations and to build trust in the approach that we're taking and the value of it in terms of really being able to drive research. And so patient education is an important component of our model patient education, patient engagement. So we work directly with patient advocacy organizations and patient advocates to educate their communities on the value of data collection, how it really spurs and supports research. I think that that's a critical component to this as well.Harry Glorikian: Well, hopefully people will listen to this podcast worldwide and me that may spur someone to search you guys up on the web. But I noticed that another principle of the company is you don't sell patient data, right? Does that mean you're giving it away? And if that is true, what's the criteria of doing that? And do your data partners that you're giving it to have to meet certain standards?Charlene Son Rigby: Yeah, this is a great question because monetization models around data are very, very common today. Some companies have built significant valuations around data monetization. And for from a Rare-X standpoint, and this is part of the reason why we were started, is that the question was asked like, is that the right thing to do, especially for diseases where we're in the very early stages of understanding a disorder, and so I talked about this a little bit earlier, that if you have no data, getting any researcher interested is already then a huge challenge. And so we're here really to break down barriers to advancing rare disease research and encourage that research. And so I say sometimes that it's really important that we free the data. So we don't sell data at Rare-X. And we have an open access model for researchers to access the data. Charlene Son Rigby: And so there it is not, “we open the doors and anybody can come, come and access the data.” It's done in a responsible way. So one of the key things is that the data is de-identified. And so it is it is critical to do that, because we want the data to be utilized for research. It doesn't need to have identifiable information in it to drive that research forward. You know, the second thing is, is that researchers need to submit information on their project, and then that's reviewed by a data access committee. And the idea behind this data access committee is not to slow down things. It's a streamlined and efficient process. But the idea is that there is a review process. The researchers need to specify whether there's an IRB with whether that protocol has gone through an institutional review board review, and patients can opt to only have their data. As an example, patients can opt to only have their data shared with projects that have gone through IRB review. So there's really kind of a, since this is in many ways a two sided platform, there's really a way that patients can actively engage in terms of who's accessing their data. And then the researchers also in terms of the types of projects that they're that they're going to put forward.Harry Glorikian: Okay. So now you're giving away the data. Remember, I'm a venture capitalist, so you're giving away the data, right? First question somebody like me asks is, how do you pay for the operations? I mean, you're building this fairly sophisticated system that is, you know, you've got to clean the data, you've got to make it available. You're trying to talk to all these people. I mean, are you funded by let's say, I mean the typical stuff, grants? Is it member donations? Is it major gifts from individuals? You know, those are all the questions that that would cross my mind.Charlene Son Rigby: Yeah, absolutely. So frankly, it took me some time to get my arms around this, because my whole career has been in tech and venture backed companies. And so so I took some time to really think about this and think about this scalable model from a scalability standpoint before joining. So we get our funding largely through pharma and industry, as well as some grants. And the way that that funding happens is, it's basically platform investment. And I think that this is a really key thing from my perspective of, of thinking about the, the platform as something that is, if you will, a social good. Because they're investing in expanding the platform. They might invest, like Travere did, additionally to help to onboard specific groups or expand our capabilities in terms of being able to gather data in a particular disease area. But the funding that they're providing is to make the platform and the research program more robust. The data at the back end will be open in the way that we've we have talked about it. We have a unique ability to do that and create that kind of model as a nonprofit. And you're right that what we're doing, we're kind of blending this health tech company with this this nonprofit  tmodel. But I think that there are some good examples out there of public private partnerships that have been very successful in the long term in doing this. And that's the model that we're really pursuing.Harry Glorikian: This area is small. I feel like I've been in and around it for a long time because of, you know, being in and around genomics. But there's a small but sort of growing infrastructure of support for rare disease, you know, patients in the world, sort of nonprofits, NGOs, patient advocacy group. Tthere's Global Genes, right? There's the Rare and Undiagnosed Network, RUN. There's the Undiagnosed Disease Network Foundation, and then there's the n-Lorem Foundation. And so many others that I don't want to leave out, right, the long list. But how does your, or, does your group overlap with these? I mean, I was reading a press release that this summer you guys will launch a collaboration with RUN and the Undiagnosed Disease Network Foundation to launch something called the Undiagnosed Data Collection Program. I mean, if you could sort of talk about what that project is about. Is your real ambition to be the data infrastructure sharing platform for the entire community of rare disease patients and families?Charlene Son Rigby: Yeah, well, I love that you call it infrastructure because I think this is critical from a concept standpoint. Rare disease should not be a model where each rare disease is doing it on its own. That was one thing that really struck me, thinking again about my daughter's disorder, where we were looking at ways to ladder up to that prospective natural history study. And we were trying to do something. I talked to a few other genetic neurodevelopmental conditions that were kind of our cohort, if you will, and we were all doing it in different ways. And it's such an opportunity cost to be figuring out the model new each time. And so these groups like Global Genes, amazing organization, actually, the Rare-X founder, Nicole Boyce, was also the founder of Global Genes. And we were, the STXBP1 Foundation used every single resource possible that came out of Global Genes. You know, that there's this broad this really broad education and enablement that needs to happen for people who want to become rare disease advocates. And that Global Genes has really done that in a tremendous way for so many organizations and so many individuals. And so we partner with them in terms of, and are very complementary, in terms of providing that infrastructure where Rare-X is focused on this area of how do you accelerate research through data collection, and then we use that.Charlene Son Rigby: It's great that you saw the announcement on the work that we're doing with RUN and the UDNF. I'm particularly excited about this because Rare-X, we talked earlier about ultra rare diseases, about n of 1 diseases. The reason why Rare-X is able to collect data across all of these disorders is that we have a fundamental assumption in the way that we collect data, which is that we don't assume that anybody does or does not have any symptoms. So we start out with a very high level, head to toe type of set of questions that if you say yes to any of them, it leads into a more detailed set of questions to collect data on particular symptoms. And so this is really ideally suited to situations where there isn't a lot of characterization around or understanding of the symptoms in a disorder and where you don't have a diagnosis. Because then what we're really enabling an individual to do is to gather robust data about their individual symptoms and disease progression that then can be utilized for research. And so we're very excited about being able to work with and support RUN and UDNF in in that effort. Charlene Son Rigby: And so do we have, you asked about ambition? You know, do we have a goal of being the only data sharing platform? I would say that our goal is to be an incredibly robust comprehensive cross- disorder platform. We believe that the way that we are approaching things really is enabling us to support all rare diseases. And we're really focused on de- burdening patients. So we're enabling patient communities to get started very quickly. And they don't have to become experts in protocol development, they don't have to become experts in creating clinical outcome assessments, etc. At the same time, the world is large and that they're going to be groups who decide that they need specific solutions. They may want to take on the role of being a principal investigator, as an example. And so I think that that's also the reason why federation is an important component of what we're really bringing forward as a as a way to bring all of that data together.Harry Glorikian: So again, you know, being on the venture side, right. You can lead a horse to water, but you can't make them drink, right? So you can do a lot. You can improve clinical trial readiness. You can make sure the data is better about rare disease patients, and that it's available. But you can't force the drug discovery companies or the drug makers to sort of develop a cure for a specific disease. Right. How do you think about that as part of a rare disease problem? Is that is that part of the work that Rare-X is,are you making it less risky so that they are willing to take that next leap?Charlene Son Rigby: You're right that pharma is going to be making, I would say, rational business decisions based on commercial drivers. And the challenge with a lot of rare diseases is that no one knows about that individual rare disease, and there isn't much data on it. And so anything that can be done to de-risk that process for a pharma company  is huge in terms of increasing their interest or generating interest for them and then increasing their interest. And those things can include knowing that there's an activated community, you know, because if you have a clinical trial and nobody wants to participate in the clinical trial, that's going to be a huge problem in terms of being able to get that drug through an approval process. And so Rare-X, by building a very robust data set, is able to de-risk that process in terms of that investment, of trying to understand what the disorder is and also trying rto understand disease progression. And going back to that point about activation of the community, we're also able to help to demonstrate the activation of the community because of the number of people participating in the in the data collection.Harry Glorikian: I know it's not science fiction. I think it's right around the corner, hopefully, but I think, isn't an ideal future where we do either whole-exome or preferably whole genome on every newborn and scan for these genetic changes that are associated with rare diseases. I mean, I'm assuming that would really push this area much farther along. And if that is true, if that statement is true, how long do you think it'll take for us to get there?Charlene Son Rigby: Wow. You're reminding me of the Gattaca movie, but hopefully that's not the real future for us, you know. Winding things back. So my daughter was born, my daughter Juno was born in 2013. So that's nine years ago. And it took three years for us to get a diagnosis. And, you know, that's like an entire other podcast. But I think that the really, if we fast forward to 2022, we have groups like Stephen Kingsmore's group at Rady Children's where they're diagnosing newborns who are in the NICU, in less than 24 hours. And even standard exome testing, which it took us three months to get our results, the standard exome testing results are now returned in less than two weeks. You can also get it faster if you have an urgent testing and we have the tech. Illumina has long been dominant and continues to be dominant in the clinical area. But you have these new entrants with Oxford Nanopore, Element, Singular, and there are others that are entering now. And so these costs are coming down and this is really going to be a transformative in terms of becoming, I do think that this is going to become standard of care and it's closer than we think. I think that it's probably going to be in the next ten years, less than ten years.Charlene Son Rigby: We already have some analogs to this in terms of or precursors, I should say, in terms of newborn screening. And so what I think is going to happen is that genomic sequencing is is going to become a core newborn screening tool. And the interesting thing is that there are applications, not just in rare disease, but also in common conditions and the value of genomic sequencing. So today, 5% of rare diseases have a therapy, but there are right now hundreds of gene therapies that are currently in preclinical and clinical pipeline. So this picture is going to change enormously in the next five years. And so because the value of is going to grow, because there are therapies, the other important thing is therapeutic windows. So therapeutic windows are when we can intervene to have the most impact on a disorder. And so that's often when someone's young before the symptoms present or start or very early in that process. And so I think that this is going to become a reality in the next decade. And frankly, I think it's a very exciting time. I have always been a big believer that knowledge is power. And this is this is one of those great situations where we have the ability to do something because we know.Harry Glorikian: Yeah, I talk about some of this in my book and there's some, you know, interesting stories and it's a fascinating time. And when I think back, you know, to when we first started sequencing and people would say, why would you want to sequence anything? And now it's the complete opposite. And the price is coming down. It's becoming easier and faster. And I mean, at some point, I think the price is going to be low enough between the actual sequencing and then the analysis, that as my friend says, it's going to be a nothingburger. I mean, it's just going to be like, yeah, we should just do that because it gives us the information we need for the next step, which is sort of going to be interesting.Charlene Son Rigby: Yeah, absolutely. I think that the that is the challenges that I talked about, cost of sequencing. But you're right that, you know, the analysis is still quite expensive today. And that's something that we're also going to need to need to improve. I mean, AI and the growing knowledge bases is really going to help to address that. Yeah. And but that's a huge component of it as well today. Absolutely.Harry Glorikian: Yeah. I'm looking at a company that in this particular area of oncology, they've gotten the whole genome analytics down to about $60. So it's, you know, it's coming to a point where you're like, why wouldn't you do that? Like, what's stopping you from doing that? So it's been great having you. Great conversation. I wish you guys incredible success. A nd I'd love to keep up on how things are going with the organization.Charlene Son Rigby: That'd be great, Harry. Really enjoyed it today. Thanks.Harry Glorikian: Thank you.Harry Glorikian: That's it for this week's episode. You can find a full transcript of this episode as well as the full archive of episodes of The Harry Glorikian Show and MoneyBall Medicine at our website. Just go to glorikian.com and click on the tab Podcasts.I'd like to thank our listeners for boosting The Harry Glorikian Show into the top three percent of global podcasts.If you want to be sure to get every new episode of the show automatically, be sure to open Apple Podcasts or your favorite podcast player and hit follow or subscribe.Don't forget to leave us a rating and review on Apple Podcasts. And we always love to hear from listeners on Twitter, where you can find me at hglorikian.Thanks for listening, stay healthy, and be sure to tune in two weeks from now for our next interview.

Most fitness gadgets, like the Fitbit or the Apple Watch, encourage you to get out there every day and “close your rings” or “do your 10,000 steps.” But there's one activity tracker that's a little different. The WHOOP isn't designed to tell you when to work out—it's designed to tell you when to stop. Harry's guest this week is Emily Capodilupo, the senior vice president of data science and research at Boston-based WHOOP, which is based here in Boston. To explain why the company focuses on measuring what it calls strain, rather than counting steps or calories, she reaches all the way back to the beginning of the company in 2012. That's when founder and CEO Will Ahmed had just finished college at Harvard and was looking back at his experiences on the varsity squash team. Ahmed realized that had often underperformed because he had overtrained, neglecting to give his body time to recover between workouts or between matches. To this day, WHOOP designs the WHOOP band and its accompanying smartphone software around measuring the physical quantities that best predict athletic performance, and giving users feedback that can help them decide how much to push or not push on a given day.Capodilupo calls the WHOOP band “the first wearable that tells you to do less.” But it's really all about designing a safe and effective training program and helping users make smarter decisions. Meanwhile, the WHOOP band collects so many different forms of data that it can also help to detect conditions like atrial fibrillation, or even predict whether you're about to be diagnosed with Covid-19. It's not a medical device, but Capodilupo acknowledges that the line between wellness and diagnostics is shifting all the time.  And with the rise of telemedicine, which is spreading even faster thanks to the pandemic, she predicts that more patients and more doctors will want access to the kinds of health data that the WHOOP band and other trackers collect 24/7. The conversation touched on a very different way of thinking about fitness and health, and on the relationship between big data and quality of life—which is, after all, the main theme of the show.Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.TranscriptHarry Glorikian: Hello. I'm Harry Glorikian, and this is The Harry Glorikian Show, where we explore how technology is changing everything we know about healthcare.If you're a gadget lover and data aficionado like me, you've probably tried a lot of different fitness monitors and other wearable devices, like a Fitbit, or an Oura ring, or an Apple Watch.We've talked about a lot of these devices on the show. Usually they come with a smartphone app, or they run their own apps. And the job of the apps is to track your fitness progress and encourage you to get out there every day and “close your rings” or “do your 10,000 steps.”But there's one activity tracker that's a little different. It's the WHOOP band. The WHOOP is not designed to tell you when to work out. It's designed to tell you when to stop.My guest today is Emily Capodilupo. She's the senior vice president of data science and research at WHOOP, which is based here in Boston. And to explain why the company focuses on measuring what it calls strain, rather than counting steps or calories, she reaches all the way back to the beginning of the company in 2012.That's when founder and CEO Will Ahmed had just finished college at Harvard and was looking back at his experiences on the varsity squash team.I'll let Emily tell the whole story, but basically Will realized that had often underperformed because he had overtrained, neglecting to give his body time to recover between workouts or between matches.To this day, WHOOP designs its signature WHOOP band and its accompanying smartphone software around measuring the physical quantities that best predict athletic performance, and giving users feedback that can help them decide how much to push or not push on a given day.Emily calls the WHOOP band “the first wearable that tells you to do less.”But it's really all about designing a safe and effective training program and helping users make smarter decisions.Meanwhile, the WHOOP band collects so many different forms of data that it can also help to detect conditions like atrial fibrillation, or even predict whether you're about to be diagnosed with Covid-19.But it's not a medical device.But Emily acknowledges that the line between wellness and diagnostics is shifting all the time. And with the rise of telemedicine, which is spreading even faster thanks to the pandemic, she predicts that more patients and more doctors will want access to the kinds of health data that the WHOOP band and other trackers collect 24/7. It was a fascinating conversation that touched on a very different way of thinking about fitness and health, and on the relationship between big data and quality of life, which is, after all, the main theme of this show.So I want to play the whole interview for you now.Harry Glorikian: Emily, welcome to the show.Emily Capodilupo: Thanks so much for having me.Harry Glorikian: Yeah, I have to tell you, I was reading your background and I'm like, oh, my God, I'm so excited. She comes from like, you know, like real training in sleep. And we're going to talk about these devices. And it's one of the things I use them all for, as you can tell, like I'm I'm sort of geared up and I've got all of them and I and I cross correlate and I can tell when somebody has updated something and the algorithm, like I can see like all of a sudden they start moving apart from each other or being different from each other. But, you know, for those people who aren't, say, up to speed on the world of fitness monitors, I'd love for you to start, you know, by explaining you WHOOP's mission, and then maybe talk about different parts of your system, you know, like the band, the sensors, you know, the basic capabilities, that sort of stuff.Emily Capodilupo: Sure. So WHOOP's mission is to unlock human performance. And in a lot of ways it started out at the beginning. You really focus on athletic performance. Our origin story is very much in preventing overtraining. But as we started to do more and more research, we started to discover that the things that predict athletic performance at the sort of root physiological level are actually the same things that predict all kinds of performance. So we've seen them predict things like cognitive performance. We've seen them predict like emotional intelligence and, you know, like how short you are with people, stuff like that, you know, as well as like how people feel like they're performing at work or in their jobs, in their relationship, stuff like that. So while ...physical performance is, where a lot of those algorithms and sort of like our research started, we started to realize that without tweaking any of the algorithms at all, they started to be really good predictors of other elements of performance as well. So we've really broadened our mission. It's all about unlocking human performance in the broadest sense possible, and we do that with this device. Some of the things that we think are really important about our design as it compares to some of the other wearables, is that as you'll see, it's screenless. And we really think about the device just as this itty bitty little bit that slides out from the fabric.Emily Capodilupo: And so it's actually capable of being worn almost anywhere on your body. So we have clothing that totally hides it. You can wear it in your underwear, on your bra, on a t shirt, anything like that, as well as sort of the traditional wearable locations like on your wrist or bicep. And one of the reasons why we wanted that form factor is we really wanted to collect 24/7 data and be able to get this complete picture of your body. It actually charges wirelessly so you don't even have to take it off to charge it. And that allows us to get the most complete picture of what's going on. And so we don't miss like the 2 hours when you take it off to charge or you don't charge it overnight and then miss the sleep or anything like that. So it gives us this like really incredible picture. Kind of one of the other important differentiators just in the hardware itself is because we're not powering a screen, we're able to put 100% of the battery into driving the sensors and getting the most accurate signal. And so when you start with the most accurate signal, the most accurate raw data, you're then able to power better feedback, better coaching, because you're starting with something more reliable. And so we've done a lot on the coaching side and the algorithms side that other wearables just haven't been able to do.Harry Glorikian: Interesting. So Will Ahmed and John...and I'm going to try to pronounce it. Emily Capodilupo: Capodilupo.Harry Glorikian: Thank you. Started WHOOP in 2012, right? While John was at Harvard and Will had just graduated. Right. So, you know, I mean, maybe a little bit about the company's origin story or. I don't. God, that was you know, if I go back that far, the fitness monitoring market was like in its nascency.Emily Capodilupo: Yeah it was, the Jawbone Up had just come out, the original Fitbits had just come out. And not too long after that the Nike FuelBand started, which no longer exists, of course. And, you know, if you look at what wearables were doing at the time. Oh, and then, of course, there was this other class of wearables that had been around for a little bit, which were like the Garmin running watches. So it kind of GPS watches that you put on for the run or for a bike ride or whatever it is. It would capture all the GPS data, give you information about your pace, and then you take it off when the run was over. And so you kind of had those like two classes of wearables. We had these like 24-ish/7 step counters, and then you had the like more intense while you were working out data, but nobody was really bridging those things. But the sort of theme across all wearables, both of those different categories at the time, was this like push harder, more is more, faster is better, just do it, right. All of those kinds of messaging. And we weren't really seeing, at least with the like kind of step counter class of wearables, we weren't seeing any kind of adoption in like elite athletes or even like collegiate athletes because they didn't really need to be told do more.Emily Capodilupo: And actually what happened is, sort of the WHOOP origin story is, Will was captain of the Harvard squash team. And when he got named captain, he sort of committed that “I'm the captain. I should work harder than everybody else. That's what a leader does.” And he worked so, so hard that he overtrained, really burnt himself out and like did really poorly. And he had this moment of like, you know, I'm in a Division I school and I'm like the fanciest, you know, squash programs that there is. How come nobody knew I was overtraining and like, told me to stop. And like, who knew that this was a thing? Like, I always thought that if I worked harder, I'd get better. And actually, you can work too hard and working too hard is bad. And he found that like everybody on his team was really motivated to work hard and sort of motivating each other to work harder. And they didn't have that balancing voice of like, Oh, I should take a rest day and like sit out, even though like my teammates are practicing. That would have felt like very uncomfortable and like not being a team player or something like that. But he started digging into the data and it really did show that like actually when you need a rest day, you will be stronger for having taken the rest day, than you will be for like manning up and pushing through.Emily Capodilupo: And so he really set out to create the first wearable that was going to tell you to do less. It was very countercultural in that moment. But he was trying to address kind of the highly motivated market that needed almost like permission to pull back and to be told what their limits were. And so from day one, we were really focused on like, how can we create a recovery score that's going to tell you, like, you're better off resting today than you are like doing this program or that, like, a coach could use and see the data and say, okay, these four players, they're going to do an extra set or an extra drill or whatever it is. And these four players, they're actually going to stop 20 minutes early and, you know, go sit in the sauna or stretch or whatever it is. And by modulating people's training in response to their bodies, readiness to respond to that training, actually create like safer and more effective training programs. And that was where we started and then kind of evolved into the product we are right now. But a lot of that is very, very much, that philosophy is still kind of at the core of what we're doing.Harry Glorikian: Yeah, I definitely have questions. We definitely have to talk about the recovery score and sleep apnea, because I have a vested interest in understanding this better. Actually, it's funny, I try to talk about this with my doctor and he's like, “Man, you know more than I do about this.” But so, you know, thinking about how the company is evolving. It's been moving forward. I've been watching it. I mean, what is the company's sort of larger philosophy about like the role of technology in fitness and health. I mean, do you feel like we're headed towards a future where everybody is going to rely on their mobile and wearable devices for health advice?Emily Capodilupo: I think so. And I think that, you know, there's a big asterisk to that answer, which is I don't think that wearables are ever going to replace doctors, and I don't think that we're trying to do that either. But we do have a lot of information that doctors don't have. And there's a really, I think, exciting opportunity if the medical community were more open to it. And they're definitely shifting in that direction. And that's been accelerated by the pandemic and the rise of telemedicine, where there really is an opportunity. I mean, if you think about it, just like the really simple basic stuff like telemedicine appointments skyrocketed during the pandemic.Harry Glorikian: Right.Emily Capodilupo: Every other in-person doctor's appointment I've ever been to, the first thing they do is they take your vital signs right, often before you even get to see the doctor. They've taken your vital signs, or if you've a telemedicine appointment, they just totally skip it, right? And so it's like, well, you know, my wearable can tell you what my resting heart rate is, could tell you not just what it was this morning, but what it's been all month and all that kind of stuff. It also can tell you what my blood oxygen level is, my temperature. And that's a lot of information that's like, you know, is a lot better than having nothing. Which is what telemedicine has right now. And so it's not like let's throw out all the EKG machines and all of that.Emily Capodilupo: But, you know, there are a lot of situations where remote monitoring can add a lot of value. And then there's other places where even if the doctor was there to take your vital signs, sometimes vital signs in context have a lot more information than an isolated reading. So like we published a paper about a little over a year ago now where we were looking at respiratory rate in response to COVID-19 infections. And what we found was about three days before or up to three days before reported symptom onset, people's respiratory rates were starting to climb. And we would see this like because daily your respiratory rate when you're healthy, it doesn't change at all from night to night, it's super flat. And so it will be like the exact same thing night after night. And then all of a sudden you'd see this spike like two, three days before COVID-19 symptom onset. It would stay up or keep climbing. And then three days later, people would say, like, Oh, I don't feel well, whatever. They go get a COVID test, and lo and behold, it would be positive. And so it was this like interesting early warning sign. But what was really, really interesting about that study is that oftentimes people's respiratory rates were only going up like one or two breaths, which didn't make them like clinically like high respiratory rates, like clinically significant.Emily Capodilupo: It was only significant in how it was compared to your baseline. And so that's a case where like if I had gone to my doctor and they measured my respiratory rate, they would have said, this is a normal human respiratory rate, you know, between 12 and 20 breaths per minute, which is sort of normal. But like my baseline is about 14. So if it went up to 18, that's a huge, huge rise for me, but it's still technically clinically normal, so they would have completely missed that. But by having a wearable that's like passively monitoring my respiratory rate every single night, you could see like something's going on, and that can be a huge red flag that something's going on with your respiratory system. Right. And of course, COVID-19 is a lower respiratory tract infection primarily. So it's going to show up there. But we would expect to see similar things with somebody who had pneumonia or certain strains of the flu. And so these kind of like early warning signs that can show up in your vital signs before symptoms. You're not going to have a fever yet. You're not going to be complaining about not feeling well or have any other indication that you might have COVID. And so I think that's like an example of where a wearable paired with a doctor can provide information that like a doctor in their office wouldn't be able to provide alone.Harry Glorikian: Well, I mean, I think, you know, if you took respiratory rate plus a slow change in temperature, right now you have two biomarkers that you can use to show something is physiologically off.Emily Capodilupo: Yeah. What we were seeing was that respiratory rate was climbing before temperature was climbing, which was interesting.Harry Glorikian: Interesting. Okay. You know, another story. It's funny because I was talking to a friend of mine and he has A-fib [atrial fibrillation] and he knew he was going into A-fib and then he got together with his doctor and his doctor was actually digging into the data from the WHOOP to sort of see like when he was going into A-fib and sort of, you know, using the technology, because he wasn't wearing a Holter monitor or anything like that. This, this sort of acted as a way for him to peer into when it started, how long it lasted and things like that. So I think when a doctor wants to, it's interesting because some of these wearables like yours have that data available for them to, you know, interrogate.Emily Capodilupo: Mm hmm. Yeah. And I think A-fib is such an interesting example there because, like, people who have paroxysmal A-fib can go into A-fib for just, like a couple of minutes a month. And so your typical like seven-day or 48-hour Holter monitor reading could easily miss it. But A-fib puts you at risk of all kinds of things like stroke that you might want to be treating, and so like having 24/7 data collection over months and months and months can give you a better picture versus I don't really know too many people who are going to be willing to like or Holter monitor for a year.Harry Glorikian: Yeah. So I mean, I'm going back to your 24/7 and the wearable and the fact that you're driving all the power to the sensors, I mean, you guys collect, I think I saw the number, 50 to 100 megabytes of data per day, per user, which is a gigantic amount of data compared to maybe like a Fitbit or an Apple Watch. I mean. Why collect that much data? I mean, what do you do with it? I mean...Emily Capodilupo: Yeah, great question. You know, we keep all of the data because it has tremendous research value in addition to being able to power the features that we're providing today. You know, there's all kinds of fascinating early research, you know, different things like the shape that your pulse makes. So if you look at not just how fast your heart is beating, but literally, you know what that raw, we called PPG, photoplethysmography signal, looks like, you can actually tell a lot about the health of a cardiovascular system. And we published a paper a couple of years ago now where we're looking at age as a function of this like cardiovascular pulse shape. And we haven't productized that research yet, but stuff that we're exploring down the road and there's just there's so much, so much you can answer with large data sets that traditional academic research just hasn't been able to answer because they haven't had access to data like this. And so by keeping it all around, we're able to do a lot of research and move the field forward as well as create really, really feature rich experiences for our members.Harry Glorikian: Can I suggest, you know, custom consulting for guys like me who actually would love to dig into the data as as a service that that people would be willing to pay for. But correct me if I'm wrong -- the WHOOP doesn't really detect when I'm exercising. Right. I've got to tell it, no, I'm exercising.Emily Capodilupo: We detect when you're working out.Harry Glorikian: Because it seems like it's more accurate when I push the button first and it starts rather than wait for it to like if I'm about to start a weightlifting session, it's more accurate when I push the button, then when I wait for it to tell I'm doing something.Emily Capodilupo: Yeah. Well, with certain activities it's hard to get the exact start times right. And different people have different attitudes about things like warm ups and downs and if they should be included. So if you do have a strong preference about whether or not you want those included, we do give people the opportunity to manually trim the bounds of their workouts or to just start and stop them manually. But we do detect any activity with a strain above an eight that lasts at least 15 minutes will get automatically detected.Harry Glorikian: Okay. And by the way, I love the fact that you guys integrated with the Apple Watch because, like, because when I go on my treadmill, it automatically connects to the watch and then tracks the whole thing and then ports the info. That's great. That is fantastic. As a as an opportunity. But, you know, how do you think about WHOOP versus any of the competitive technologies? And I'll tell you why I say that when people say, well, what do you see is the difference? I'm like, you know, the Apple Watch is more of what what I think of as a data aggregation device in a sense, because it's sort of taking all sorts of stuff. You know, the WHOOP I think of almost like a coach in a sense, as opposed to it's pulling in data and pushing it out to different apps and I can do different things with it. So I don't want to misrepresent how you might frame it, but that's sort of how I think about it.Emily Capodilupo: No, I think that's totally spot on. I think that we have a very strong stance around not showing or generating data that we can't tell you what to do with it. And so we really want to be like your coach or your trainer or at a minimum like your workout buddy kind of thing, where it's somebody that or something you can kind of look to, to understand, you know, am I reaching my goals? What are the things that are helping and hurting me and sort of how do I then make changes to go forward? I think one of the biggest examples here is, we've been very much like countercultural in not counting steps and we've been asked a lot by our members, like, why don't you count steps? It's not actually that hard. It's not because we can't figure out how to do it. It's that we actually don't think that they're valuable. Steps count the same if you run them or walk them. If you walk them upstairs or flat. You don't get any steps if you swim for a mile and you certainly don't get any steps if you're wheelchair bound. And we didn't like any of those constraints, they didn't really make sense to us as a metric. And we also really didn't like this kind of arbitrary, like everybody needs 10,000 steps. Well, is that true if I'm 90 versus 19, is that true f I ran a marathon yesterday, should I still be trying to get 10,000 steps today? Is it different if I've been sitting on the couch for three days? And so we came up with this metric of strain where instead of being an external metric, like steps are sort of something that you did and you can count them and it's objective, we wanted an internal metric where it's like, How did your body respond to that thing that you did and how much flow did you take as a function of what you're capable of? And so sort of what strain does, it's very much like in opposition to what steps does, is they're internally normalized to reflect like if I ran versus walk to those steps, if I ran versus my brother ran and he's more fit than I am, or if I do a two mile run this weekend and then I train a whole bunch and get more fit and then do the same two mile run six months from now, I should actually get a lower strain when I do it, when I'm more fit than I did when I got did it this weekend. Like all of a sudden, strain becomes this very rich thing because it has this, like, natural comparison where like a higher strain actually mean something objectively, both within and across people, than a lower strain does. Whereas that that's not really true with steps. Right? I could walk fewer steps than you, but have done them up a mountain. And so I've actually put a lot more strain on my body than if I'd done the same number as you, but like flat pacing around my kitchen, eating snacks and making dinner or something like that.Harry Glorikian: Yeah, well, actually there was an interesting paper that it was a sort of a study that brought in all sorts of studies to show that, you know, at an older age, you actually, you know, you need less steps, and it has a difference in mortality. And, you know, if you're younger, then you want a higher level of steps. And, you know, so it was a good paper. I'll actually I'll send you the reference later. But you know, the interesting thing about strain is and this is the good part about the body and the bad part about the body, in a sense, is that it optimizes itself. Right. And so if you want to get the same strain goal and if you're fit, you really have to…I mean, at some point, I'm like I look at if I had an incredible night, which is rare and it's really in the green, I'm like, I'm never going to hit that. Like, I'm going to have to run ten miles to hit that, that goal. So, I mean, I try to like get out and lift that day and maybe get a run in, then get a walk in. And I'm still you know, when you can't hit that high mark, if you're actually in shape. When you're not in shape, sort of, you can get there a little bit easier because your body is has optimized itself in a sense. Which is great, I guess. But when you're when you're holding yourself up to that number, you're like, Oh, my God, I'm never going to hit that number.Emily Capodilupo: Yeah. I mean, it's super interesting how the human body works, right? There's almost like this weird kindness in how we work where it's like easier and more fun to make progress when you're brand new and starting out and it's harder to make progress the better you are.Harry Glorikian: I mean, it's an efficient machine. It has to optimize itself. Right. So, again, you were saying no display, no interface. All the information happens on the associated device, the phone. I mean, you mentioned some of the pros and cons, but are there any other that I haven't asked or I know that at some point it pings me and says like. You need to connect because it's been some time between connections. So is there an offloading time frame that it needs to...Emily Capodilupo: No, it can store up to three days of data on the device itself.Harry Glorikian: Oh, interesting. Okay.Emily Capodilupo: Yeah. So if you like went camping for the weekend or something and didn't have internet, we would just store the data locally and then transmit it all when you got back. But it tries to transmit the data more or less consistently, constantly throughout the day. What it's pinging you about is not that you're in any way in danger of losing the data, but just that you're behind. And so you might be missing any kind of analysis or getting credit for your strains. We want to make sure you're up to date so that if you want to look at your data from the day, you would have access to it.Harry Glorikian: Here's a question. Would it ever make sense to make a WHOOP app for the Apple Watch? Or is the device sort of inextricably linked to the app?Emily Capodilupo: Yeah. I mean, there's a lot of good reasons to think about something like that, right? You can make it a lot more affordable if you didn't tie it to hardware. Right now, we believe that we have the best hardware on the market, but there's sort of valid pushback that some people are willing to settle for something less than best in order to only wear one thing. And they want to wear their Apple Watch because they like the phone call notifications and the texting and email and all that kind of stuff. There's a lot of great features that Apple has that we don't. I'm certainly not trying to hate on the competitors at all. But I think like the way we kind of think about what we've done is like if Apple Watch does a lot of little things, you know, at like a relatively shallow depth, so it's like a lot of coverage, we do a small subset of those things, but we do them very, very, very well. And so by not doing things like putting on a screen and letting you text and all of those things, we're able to have all of the power of the device drive towards getting the most accurate signal data. And so we are sampling the heart rate more frequently than Apple is, and the device is more purpose built around optimizing both internally and externally for the sensors. So there's even little things like electrical coupling on the circuit board. When you try and shove too much functionality into something small, they kind of like run into each other. And, you know, so we're not trying to make room for a GPS chip or make room for a screen or like all of those things. And so it lets us lay out the hardware very specifically for this purpose. And so we believe that in data to support that, we're getting more and more accurate like metric data.[musical interlude]Harry Glorikian: Let's pause the conversation for a minute to talk about one small but important thing you can do, to help keep the podcast going. And that's leave a rating and a review for the show on Apple Podcasts.All you have to do is open the Apple Podcasts app on your smartphone, search for The Harry Glorikian Show, and scroll down to the Ratings & Reviews section. Tap the stars to rate the show, and then tap the link that says Write a Review to leave your comments. It'll only take a minute, but you'll be doing a lot to help other listeners discover the show.And one more thing. If you like the interviews we do here on the show I know you'll like my new book, The Future You: How Artificial Intelligence Can Help You Get Healthier, Stress Less, and Live Longer.It's a friendly and accessible tour of all the ways today's information technologies are helping us diagnose diseases faster, treat them more precisely, and create personalized diet and exercise programs to prevent them in the first place.The book is now available in print and ebook formats. Just go to Amazon or Barnes & Noble and search for The Future You by Harry Glorikian.And now, back to the show.[musical interlude]Harry Glorikian: So switching to sort of business model, because you sort of touched on that, is like it's a subscription model. You don't buy the device. If I'm not mistaken. The service starts at say 30 bucks a month and the package actually includes the WHOOP band. They'll just ship it to you like I'm wearing mine. Right. And so what was the rationale behind subscription versus just selling the device. If you have insight into, how did they pick 30 bucks? You know, I just wonder, like, you know, did they, is that something you guys felt reaches the broadest market sort of thing?Emily Capodilupo: Yeah, pretty much. So when we actually first launched, it was sold more like a traditional hardware product. So it was $500, one time fee, sort of use it as long as you want. And then we switched over to the subscription model in 2018. A nd we chose the price of $30. It was sort of designed to make the product accessible and lower the barrier of entry. $500 up front is a lot of money, especially for younger athletes. We want to make sure that people in college could afford it and stuff like that. And so we found just by market testing, that $30 was an approachable price point. And so after a couple of different market tests, that was what we landed with and more or less where we've been. We occasionally discount it and different things like that, and you can get a lower rate if you commit to more months upfront.Harry Glorikian: Yeah, I think I signed up for the maximum, which then brought it down to I think it was $18. Yeah. So here's a, you know, because this show is, you know, supposed to focus on AI and health care and things like that, I'm just sort of imagining in the back of my mind with that much data, you really have the opportunity to build some really cool analytics on top of it. You know, what role, if any, like does machine learning or other forms of AI play in you know how you analyze the data and then how do you, do you actually use that to personalize it back to the individual using it.Emily Capodilupo: Yeah, I mean, that's pretty much all my team is doing is machine learning. No, it plays a huge role in what we're doing, from like very traditional ML approaches, so like if you think about how we're doing our sleep staging, we have polysomnography is like the gold standard for getting sleep truth data. So that's like the stages when we know we're in REM sleep or slow-wave sleep. So we sent thousands and thousands of people into a clinical sleep lab with two straps on and they underwent a clinical sleep study. And then we took all of the data from the sleep study, lined it up with the WHOOP data, and then used all kinds of different traditional ML approaches in order to figure out how to get from a strap the same sleep staging information that we're able to get from this gold standard approach. Obviously the sort of gold standard sleep study uses a lot of sensors that we don't have right things. EEGs, which you need to be on someone's head to use. You can't get EEG from the wrist. EOGs, which you have to measure eye movement. So you need a little sensor there. And then we were able to find good proxies from the data that we can get at the wrist for all of those different signals and reconstruct the same sleep stage information.Emily Capodilupo: So that's a super fun ML problem. We also do things like when we detect a workout, we can figure out what, which sport or exercise modality you're using. And so the ability to classify those workouts is kind of again like a traditional ML like time series classification problem where you can tell the difference just from the heart rate and accelerometer signals. Are you doing basketball or CrossFit or running or anything like that? And then so those are kind of more traditional ML approaches. And then we've also done a lot around trying to understand behavioral impacts and how your body responds to different things. And then we're doing things like much, much more personalized. So we have a feature called The Journal where every day you fill out this little diary and you answer a bunch of questions about what you've done in the last 24 hours and can self report things like when you were eating, if you did different like kind of wellness activities like, meditate, journal. You know.Harry Glorikian: How much alcohol you had. I always wonder, like how honestly somebody answers that question.Emily Capodilupo: Any of those kinds of things. And then we look at the sort of signals in your data and try and separate out which of the things are helping you, which are hurting you, so that we can then recommend the things that are good for you, and for the things that are less good for you, maybe help you quantify the cost of those things that you can deploy them strategically. We certainly don't expect everybody to become like a teetotaller and never drink again, even though we're going to tell you it's bad for you, because it's pretty much always what shows up in the data. But we do want to help people make those informed decisions because a lot of people think like, Oh, I can have two drinks and it won't affect me tomorrow. And like, okay, here's the effect. And if tomorrow's not that important, go for it. And you have that really important meeting tomorrow, maybe don't. Y rou know, we're not trying to kill all the fun by any means, but we do want to make sure that people are empowered by data to know understand what they're doing to their body and then make decisions accordingly.Harry Glorikian: So I'm throwing in sort of like something important to me, right? Which is, you know, I have sleep apnea. Right. And it's funny because my wife diagnosed me, but then, you know, all the devices at some point, my Apple Watch actually asked me once, you know, have you ever been diagnosed with sleep apnea, which was interesting. But I've noticed like, the recovery number, if don't wear my CPAP, my recovery number tends to be much higher than if I do wear my CPAP. And I always wonder, does the positive air pressure cause a difference in how much your heart actually rests or not? Because it is pushing, it is positive air pressure on you all the time. So even in between apneas, you don't really maybe not rest as much. And I'm wondering if you have any insight on that.Emily Capodilupo: Yeah, we, we haven't specifically dug into why, but we have seen that as an unexpected pattern. You're not the only person to report that. It's on the to do list to better understand what's going on there. I think your theory is a valid one. We haven't verified or ruled it out yet, but I think there's a lot to be learned there. And I think one of the things that's exciting about the data that we're collecting is that if you wear a CPAP is one of the things you can report in our journals. We do have a tremendous amount of data on that and therefore the ability to kind of tease that apart and get insights that haven't been made available yet by traditional academic research.Harry Glorikian: Oh, I didn't know I could add CPAP in there. I have to go back and and check. But yeah, because my strain score ends up, my recovery score ends up lower. So it's like, you know, then of course, I always exceed on the strain side because I'm going to go work out the next day. And you know, it is what it is. But the other thing that you guys offer is like WHOOP for teams. And I don't know if you mean sports teams. You mean organizations. I'm not 100% sure because obviously I don't use that. I'm using it as an individual. Can you explain the additional value that provides when a group of people are using it together?Emily Capodilupo: Yeah. So all the above, we do it corporate teams as well as athletic teams, and there's a couple of different layers of the added value. So sometimes it's just accountability. I'm on a team with my family and it's just kind of fun, make fun of each other when our recovery scores are poor and, you know, cheer each other on when we have particularly good strain scores. And, you know, there's a lot of data to support that when you have a workout buddy or an accountability buddy or anything like that, that you tend to stick with things longer. And so creating just like a really friendly way for people to compete and cheer for each other just helps with the accountability and motivation keeping people on track. And deeper and more importantly, we do have a lot of people who create teams around different kinds of research initiatives or trying to understand a certain life stage. Like we create teams for people based on the month that their babies are due. So pregnant women can join a team of all the women on WHOOP who are expecting a baby in June 2022 can join this team together and pregnancy is this like very foreign weird moment in your body where everything's changing all the time and it just creates, like, a way for people to connect and be, like, this weird thing that's happening to me, is it normal? Like, who else is sleeping funny? And I think it's just very comforting to know that, like, all these weird things happening to your body aren't so weird. And then with like the sports teams and different things like that, what we're seeing is that the coaches are using the information to make better training or like decisions because now they actually have information that they didn't have access to before.Emily Capodilupo: So we've done a lot of work with different like collegiate programs and professional programs where they do things like if you're red, they will have you do a lighter version of the practice or skip a section of the practice in order to give your body a chance to recover. And if you're green, they might have you push a little bit harder. And so by modulating the training to where your body is today, we've actually shown in a project we completed a little over two years ago that you can reduce injury without reducing performance gains over the course of like an eight week training period. And so by reducing your training, when you're red, so your recovery score is below 33%, you actually like you will reduce injury without reducing performance gains. We've shown this. And so there's like literally zero value for those coaches to like push the athletes to complete the program or the day's rtraining. And so we've seen a lot of coaches make those different training plans as well as game day decisions about who should start. You know, somebody might be your best player ordinarily, but if they're red, they're not all that primed on game day to perform. And so being able to make those kinds of different decisions. And then on the corporate side, people have used it in order to triage different access to supportive resources. So we've seen people offer like breaks to people who have been red for a number of different days in a row or things like that suggest that somebody might be burning out or overwhelmed or something like that.Harry Glorikian: Okay, so. Everywhere it states that it is not a medical device, is not intended to diagnose, monitor any disease or medical condition. Right. What's the line in your mind between, say, a fitness monitor and a medical device, because I think I always think that line is getting….because you guys and others like you guys have so much data, the level of insight that I've seen when I've gone into some of these is crazy. So. What what is that line in your mind?Emily Capodilupo: Yeah. I mean, I think that there's you know, it's always been the case that technology moves faster than the law. And so, like, you know, I think a lot of these things are going to shift as the technology is going to force them to shift. But, you know, like you said, we have a lot of data that's quite similar. The official line is what the FDA says is the line. And the FDA has carved out this like space that they've you know, they've called this wellness devices. They've sort of reserved the right to change their mind at any time, and we very much expect them to. But WHOOP falls into their definition of what a wellness device is, not a medical device, which is why we can say things like, this is your heart rate, but we can't say, because then you would cross into a medical device, like “Your heart rate is healthy, your heart rate is unhealthy,” right? You can't give those kinds of any kind of diagnoses or any kind of, like, you will prevent a heart attack if you do these things or something like that. So we have to keep the recommendations a bit more general, a little bit more vague in order to not cross over into that regulated health space. One of the things that we're seeing that's interesting, is that there's been a movement in wearables to get these like SAMD clearances, Software as a Medical Device, where pieces of wearables need different features or different algorithms do end up going through an FDA process and getting clearance to make certain claims in different settings.Emily Capodilupo: And I think that that's going to really accelerate over the next couple of years. These are very long processes, and then the lines are going to get more and more blurry because you're going to have this like hybrid consumer medical device, which is something that until a couple of years ago we really didn't have. There was like step counters and GPS watches and they were over here and then there was like medical stuff that didn't look cool and wasn't comfortable or easy to use and was very, very expensive. And it was all over here. And now we're seeing them kind of come into the middle where more and more the medical stuff cares about being like all the human factors like that's comfortable to use and that people want to wear it and they can get good compliance. And the wellness devices are finding more and more applications for their data in the health care space. So I think a lot of it's going to come down to what doctors end up getting trained on. If they're willing to look at this data, if they have any clue how to use it, sort of by being in the medical world and science training their whole lives, a lot of them just don't have the education and training to understand big data and to understand technology in that way. So they're not being trained on how to make use of the data or how to apply it. And I think that that's something that might change in the next couple of decades.Harry Glorikian: Well, it's interesting, right, because I always tell people I'm like, this is a medical device. Like I you know, I mean, you know, you may think it's not, but it really has certain capabilities that allow it to get FDA clearance in a particular area. Right. And they're picking their space one by one. But the amount of data that you guys pick up on all of these devices, I mean, you know, we've seen atrial fibrillation. I'm sure that tachycardia shows up on there. You know, there's different things that they, because it's 24/7, it's looking, right and it's monitoring and it's got multiple sensors which you can now cross-correlate. There's so much insight that comes from this that I would almost like love to encourage the companies to think about moving down this road because I think it would be so helpful to patients. But, you know, jumping to a different thing. So. How do you guys define success for WHOOP? If you hit all your product and sales goals and for the next, say, 2 to 5 years, what does success look like for the organization?Emily Capodilupo: Yeah. I mean, I'll let the finance team worry about the sales goals and things, but I mean, for me in my team, like what success really comes down to is like, can we help people make actually better decisions? I think like a lot of the first generation of wearables, like it was this stream of fun facts. And we're all obsessed with ourselves, right? Like humans are sort of naturally narcissists, at least to a certain extent. And so it's like fun to be like, ooh, I slept for 7 hours or like, ooh, I ran a mile. But it's like kind of you maybe already knew that, right? And I think, like, what we're trying to do and like where we see a lot of success is, can we tell you something that you don't know? And can we convince you that you should do something about it? And then can we make you, like, realize, like, oh, wow, this, like, incredible thing happened and I feel so much better. And the features that we get the most excited about are like the sort of user stories are not, like, “Wow, it's so much fun to see my sleep data” or like, “This was fun.” But like when we released our paper showing that this respiratory rate spike sort of predicted or often preceded COVID symptom onset and therefore COVID infection, the paper came out like right before Thanksgiving and we saw so many people tell us that like because they had a respiratory rate spike, they didn't go home for Thanksgiving or they didn't travel and then like they tested positive a few days later and they were like, my grandma was at Thanksgiving or like my uncle who's in his eighties or stuff like that.Emily Capodilupo: And you know, those kind of moments where it's like, we educated you, we showed you this vital sign that like, you never would have felt anything. You didn't know you were sick, you weren't feeling bad. It's not like you went to go get a test because you weren't feeling good, like you just saw this in your WHOOP data and you're like, You know what? I'm going to stay home and not risk like seeing grandma because WHOOP said so, right? And then like, who knows how many COVID infections didn't happen and like what kind of role we played there. And like, it was probably like the most meaningful thing we did that year. And we did a lot of other cool stuff, but to think that by helping people notice that pattern, potentially they saved a relative's life and all the like crappy things that would happen if you thought you were responsible for killing your grandma and how much that ruins your own life as well? I think like we just get really excited about that. And one of the features that we released is last year was we were looking at how your reproductive hormones is part of your menstrual cycle affect your ability to respond to training. And I was an athlete my whole life. I was a gymnast, like before I could walk, and like nobody asked me a single time when my last period was or anything like that. That was just totally not part of like the coach-athlete relationship. But we know that like your ability to put on muscle and your ability to recover from training is totally different during the follicular phase, the first half of your menstrual cycle, than it is during the luteal phase, which is the second half. And if we modulate your training so that you're training more during the first half of the cycle than the second half, you can way more efficiently build muscle and strength, have fewer injuries, make more efficient gains. And if we now we do coach, in our product, women to do this, and we've gotten this incredible feedback of like people saying they feel so much better and like they're, well, you know, their training is going more smoothly and they feel like their body so much less random, it feels more predictable and they kind of understand what's going on. Nobody ever told them that reproductive hormones were relevant beyond their role in reproduction, but they actually affect everything we do. Like when progesterone is elevated in the back half of our menstrual cycle during the luteal phase, we sweat more and we lose a lot of salt by doing that. And so we need to eat more salty foods and we need to be more careful about hydrating, which is really important if you're an athlete, but nobody's telling us this. And so like we can connect these by looking at big data because we are tracking your menstrual cycle around the clock or around the month.Emily Capodilupo: We can put that into the product and then we see people are making better training decisions, understanding their body, feeling like things are less random. Right. And that's so empowering. And I think like female athletes in particular have been so underrepresented in research. There's a paper that came out eight months ago that said that just 6% of athletic performance research focused on women, 6%. And it was looking at all research between 2014 and 2020. And it was trending down, not up. So it was worse in like 2018, '19 and '20 than it had been like earlier in the twenty-teens. And so it's like completely neglected. And there is all this data that like wearables and WHOOP are sitting on and we're able to create features around that and just help people understand their bodies in a way that nobody else is doing right now. And so those are the features that, like I really define as like big successes. If we made our sleep staging accuracy 1% more accurate or we caught one more workout, like those are obviously like from a pure data science perspective, they can feel like wins. But what we really care about is like, am I helping you, cheesily going back to our mission, am I helping you unlock your performance in some way by helping you understand your body and making a better decision? Like, are you better off for having been on WHOOP? That's what, internally, those are the KPIs that we track the most closely.Harry Glorikian: Yeah. And I mean I would encourage you as well as all the other companies to, you know, peer reviewed papers, get them out there. Right. I mean, just when I search the space or peer reviewed journals for things utilizing the technologies, I mean, there's not a whole lot out there. And then the other thing is, is sometimes I read the devices they're using, I'm like, whoa, what is that? I've never heard of that device. And if I haven't heard about it, it must be on the fringe sort of thing. So I would highly encourage it because, you know, people like me would love to be looking at that sort of data. Because I'm constantly investing in the space, constantly working with the different technologies, you know, constantly talking to people through the podcast or writing a book, you know. So that information is incredibly useful to someone like me as, as, as well as the average person. So if you could send a message back through time to yourself in 2013 when you joined the company, you know. What would you say? What have you learned about the wearables and fitness market that you know you wish you knew then?Emily Capodilupo: Oh, what a fun question. You know, I think, like. It's hard to know what I wish I knew earlier because like in so many ways and I feel so lucky that this is true, like the vision that Will pitched me on when I met him, like when he was like, “Come join WHOOP, this is why it's super cool,” is exactly what we're doing. And so, like, I did trust him. I guess my message in a lot of ways would be trust him that like this is for real. I think the space has been so exciting and just there's so much opportunity. I came from doing academic sleep research and I would work on these papers where we had like 14 subjects and it was like, “Oh, that's a, that's a good size sleep study. Like that'll get into a good journal.” And everyone was like excited. And then it's like, you know, I just, I'm working on a paper right now and we have 300,000 people's data in it. We're looking at like a year of data at a time. So we've got just like millions and millions of sleeps and workouts in this data set that we're combing through. When we did this project, which was published in the British Medical Journal last year, where we were looking at the menstrual cycle phases and how they affected your training, we looked at 14,000 menstrual cycles, like just the orders of magnitude more data than what you can do in traditional academic research. And that's what I got really excited about. It's why I became a data scientist because I realized that like the most interesting questions that there are to answer about how humans work are going to require larger datasets than we've had access to before.Harry Glorikian: So I'm putting in a plug for sleep apnea, man, if you get a chance, I'd love to see a study on that one.Emily Capodilupo: No, sleep apnea, it's definitely on the list. About 80% of sleep apnea is believed to be undiagnosed. And it does have tremendous effects on long term health when it goes undiagnosed, especially in later stages. And so anything we can do around helping people realize that they might have sleep apnea and then helping them treat it once they do and better understand the disease progression. And all of that has a huge quality of life implications down the road.Harry Glorikian: I will happily volunteer. So great to speak to you. Very insightful discussion. I'm going to tell my wife about the whole menstrual cycle thing and working out and this is exactly why she eats salty food like at certain times. But this is great. I'm so glad to have you on the show and I look forward to seeing the progress of the company and the technology.Emily Capodilupo: Awesome. Well, thank you so much for having me. This is such a fun conversation.Harry Glorikian: Thank you.Harry Glorikian: That's it for this week's episode. You can find a full transcript of this episode as well as the full archive of episodes of The Harry Glorikian Show and MoneyBall Medicine at our website. Just go to glorikian.com and click on the tab Podcasts.I'd like to thank our listeners for boosting The Harry Glorikian Show into the top three percent of global podcasts.If you want to be sure to get every new episode of the show automatically, be sure to open Apple Podcasts or your favorite podcast player and hit follow or subscribe. Don't forget to leave us a rating and review on Apple Podcasts. And we always love to hear from listeners on Twitter, where you can find me at hglorikian.Thanks for listening, stay healthy, and be sure to tune in two weeks from now for our next interview. 

When your doctor prescribes a new medicine, there's a pretty good chance that some snafu will crop up before you get it filled. Either your pharmacy doesn't carry it, or your insurance provider won't cover it, or they'll say you need "prior authorization," or your out-of-pocket cost will be sky-high. The basic problem is that the electronic health record systems and e-prescribing systems at your doctor's office don't include price and benefit information for prescription drugs. All of that information lives on separate systems at your insurance company and your health plan's pharmacy benefit manager, or PBM. And that's the gap that a company called RxRevu is trying to fix. Harry's guest on today's show RxRevu CEO Kyle Kiser, who explains the work the company has done to bring EHR makers, insurers, and PBMs together to make drug cost and coverage information available at the point of care, so doctors and patients can shop together for the best drug at the best price.Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.TranscriptHarry Glorikian: Hello. I'm Harry Glorikian, and this is The Harry Glorikian Show, where we explore how technology is changing everything we know about healthcare.If you live in the United States and you've ever had your doctor prescribe a new medication, you've probably had the following experience.You drive from the doctor's office to the pharmacy.And when you get there, you find out that the pharmacy doesn't carry that particular drug. Or that they do carry it, but your insurance provider doesn't cover it. Or your insurance does cover it, but they require prior authorization. Which means you have to get back in touch with your doctor and ask them to tell the insurance company that you really do need the medicine.Or you already have prior authorization, but you haven't met your annual deductible yet, so your out-of-pocket cost is much more than you expected.If any one of these problems crops up, the chances that you'll actually get your prescription filled on the day you need it go way down.And it's not uncommon for several of these snafus to happen all at once.Fundamentallythat's because the electronic health record systems and the electronic prescribing systems at your doctor's office don't include price and benefit information for prescription drugs.All of that information lives on separate systems at your insurance company and your health plan's pharmacy benefit manager, or PBM.And that's the gap that a company called RxRevu is trying to fix.My guest on today's show is the CEO of RxRevu, Kyle Kiser.We talked about the software they've built to make drug cost and coverage information available within the major EHR systemsWhen doctors can see in real time which drugs are covered, at what price, for a specific patient, it    obviously solves a huge pain point for patients, because it means they're more likely to get the drugs they need at an affordable price.But it also solves a big problem for doctors. Because, fairly or not, they're the ones who usually shoulder the blame when it turns out the medication they just prescribed is too expensive or isn't available.The kind of information RxRevu provides is going to be more and more important as the U.S. enters into an era of far greater price transparency, as mandated by the federal No Surprises Act, which went into effect on January 1 of this year.RxRevu is based in Denver, Colorado, and I reached Kyle Kiser at his home in Seattle, Washington. Here's our full conversation.Harry Glorikian: Kyle, welcome to the show.Kyle Kiser: Thanks, Harry. Happy to be here.Harry Glorikian: So, you know, we were just talking. You're in Seattle and I'm in Boston. I don't think we could be much farther apart when it comes to this particular country. So but let's start with a little bit of background, right. So. You're the CEO of RxRevu. And can you tell us a little bit about sort of the origin story about how you got started here? I mean, I understand your co-founder, Dr. Kevin O'Brien, had an interesting experience trying to get prescriptions filled for his mother, Lucy, but. What's the rest of that story? What did that story reveal to you about what's broken or missing in the way that doctors prescribes medicines or, you know, where the way that maybe payers approve prescription?Kyle Kiser: Yeah, absolutely. So a little background on Kevin's story. Kevin was initially inspired to do this because he wanted to solve a problem for his mom. She had an outsized out-of-pocket spend for meds. Like any good son, he wanted to help solve a problem for his mom. He used his expertise to find sort of ways to save on those medications, and that inspired him to start doing that in his clinic for his patients more comprehensively. So he was, you know, way ahead of his time and putting in all of this extra effort to really help find prescription options for patients that they could afford more easily. And that was the initial inspiration for what we've done today, which is connecting the point of care and clinical decision making with costs and coverage information that's real time and patient specific and location specific and moment in time specific, because all those things matter as inputs into a price.Kyle Kiser: So, you know, really the challenge we've been focused on is, is largely that, you know, the clinical decision making process has been pretty, pretty much disconnected, right, from marketplace information. So, you know, anything that impacts the purchasing of that care. And that was okay in a world where deductibles were low, formularies were relatively inexpensive and simple. But that world has changed dramatically over the last 10 to 20 years, right, as consumer driven healthcare has become the way of the world. And first dollar risk is now at the feet of the patient. It's that patients are now demanding that providers can consider not just what's best from a clinical perspective, but also set expectations around costs, set expectations around any restrictions that exist, and be an advocate for access to care. And the problem we're solving. We're building an access network. And within that access network, we help drive affordability and speed to care for patients. And we're doing that with a number of stakeholders. But at a high level, that's what we're trying to accomplish.Harry Glorikian: Well, you know, it's interesting, right? You know, entrepreneurship 101, solve a real need, right? So that there's a market there because everybody wants it. But so, I mean, look, I think everyone in the United States has probably had experiences similar to Dr. O'Brien's mom. I mean, you get to the pharmacy, you find out that the medication your doctor prescribed isn't covered by your plan, or you find out that the co-pay is outrageously high. But behind their personal experiences, I bet most people don't have a concept of how big and widespread this problem is. You know, you have any maybe some statistics that might illustrate the scale of the problem or how much money is wasted in the medical system because of these disconnects. I mean, I'm wondering how many prescriptions get abandoned or how many patients don't get the meds they need.Kyle Kiser: Yeah, I mean, at a. A macro level, you know, the prescription drug market makes just over makes up, you know, just over a half a trillion. Right. And, you know, estimates are that a third, even as much as half of that is waste and waste in the form of, you know, medications that aren't taken as prescribed or aren't delivering the right outcomes. I don't it's hard to find actually a a stakeholder in the supply chain that's delivered more value than meds themselves. I mean, if you think about, you know, the innovation in that world over the last 30 years, it's second to none. But the, you know, the supply chain within which they exist is complicated and it's hard to navigate. And the consequences of that is waste. And, you know, a ton of administrivia and friction. And frankly, patients bear the brunt of that. Ultimately, it's health plans and PBMs and risk bearing entities making rules on one end. It's providers and care teams making clinical decisions on the other end. And both of those processes are largely disconnected. And the only way that that gets harmonized in any way is a patient advocating for themselves. And we just fundamentally don't believe it should happen that way. What we're building is the connectivity between those stakeholders so that whether it's a provider at the point of care making the decision, whether it's a care team member trying to help you overcome a prior, or whether it's a patient trying to advocate for themselves using their own technology, we want to put real time, patient-specific, moment in time specific information in their hands to drive affordability and speed to care for that patient, no matter where they are in the care continuum.Harry Glorikian: Yeah. I mean, so this lack of prescription cost data, I mean at the point of care feels like a real canonical example of deep systemic problems with the with origins that are buried like deep in at least three of these complex organizations. Providers, payers and EHR makers. I mean, once you guys decided what the problem you wanted to fix was, how the hell did you figure out where to like -- okay, let's start here and let's move forward, right? Because.Kyle Kiser: Yeah.Harry Glorikian: Not trivial.Kyle Kiser: No, it's exactly the right observation because ultimately what we're building is a multi-sided network. And what's difficult about building a multi-sided network is, you know, users on one end, in this case, providers, aren't going to engage if it doesn't have the appropriate information in it. And the data sources, the ability to capture that appropriate information, they don't want to provide that data to you unless you have the appropriate users. So you get stuck in this chicken or the egg problem. And that's job one in growing this business, is to overcome that chicken or the egg problem. And the way we went about that was we worked really closely with health systems, with provider organizations, primarily because that's where the trust exists, is that ultimately patients seek out their provider and their care team to answer these questions. And so we worked closely with them as strategic partners and brought some of them in as investors in the company and aggregated a group of meaningful collaborators on the health system side, which then helped us bring PBMs and payers to the table to say, how do we solve these problems together? And that's that's sort of how we got out of the gate.Harry Glorikian: So I mean, tell me if we could dig a little into I think the product is called SwiftRx, if I remember correctly, but at a high level. You know, if you could describe for listeners, what is it? How does it work? And. Where does it fit in relation to the overall system?Kyle Kiser: Sure. Yes. So SwiftRx Direct is the product you're describing. What it provides is, is that real time, patient specific, location specific, moment in time specific information in the provider's native ordering workflow. So we are a data network that's powering a native feature inside the EMR that provides that insight while providers are selecting medications. So a typical flow would look like, a provider selects a medication. They then place that into a pending status in the software that they use. When that happens, we're able to gain visibility to that choice. We send that transaction out to our network of data sources, payers, PBMs, etc.. And what we get back is the price that is patient specific. We have formulary insights, so prior auth, quantity, limit, step therapy, those sorts of things. Those are also patient specific. And then most importantly, we get back alternatives. And those alternatives come in two forms. They're either a lower cost medication or a lower cost pharmacy where the patient can fulfill that medication. And that's sort of the core information that we then render back into the e-prescribing workflow. And we only interrupt those providers' workflows, or we and our partners only interrupt those providers workflows, when there's relevant information to consider. Because as I'm sure, you know, being deep in this world, provider engagement stuff -- you really have to be thoughtful about when, when is the appropriate time to intervene and when, when do we want to sort of get out of the way and make sure that when we are intervening, it's meaningful and understood to be meaningful?Harry Glorikian: Yeah. So I'm going to I mean, I heard a lot of what you said. I'm I want to maybe summarize all the. A few of these areas that people run into problems. But to try to understand sort of what are the big problems you had to solve to get it to really work? Because I'm just trying to get my head around the magnitude of the data headache here. Right. So if if you'll allow me, I'll just try to break it down into parts and then you can tell me how you're bridging all of these. So for one thing, there's the patient specific data about what kind of insurance each patient has and what level of benefits they have. And none of that is stored in the EHR at the clinic. As far as I know, typically the EHR would only list the patient's group number, subscription number or maybe the RxBin number. And then separate from all that, every insurance has a formula of drugs that will cover and sometimes a, you know, a schedule of different copay amounts for those drugs. And those formularies change every year and even more often. Right. And then there's a patient's actual prescription data which may live in their EMR or may live in a different system at the pharmacy. And then on top of that, there's this obscure black box system of prior authorization criteria that insurers may use to deny a prescription if they don't feel like paying for it. So the fact that the system is so fragmented is a familiar story to anybody who listens to this show. But tell me, you know, how on earth you were able to sort of get all this data under one roof, so to speak? You know, is there a specific architecture of the Swift system that makes you good at collecting all of this changing data and presenting it to the providers in real time?Kyle Kiser: Yeah. The only other element I'd add to your complexity salad is also benefit design, right. Is that yeah, the, the out-of-pocket cost can be and is dramatically different based on where you are in your coverage. If you're a commercial member with a high deductible, you're bearing the, you know, the in-network negotiated rate inside that deductible. And that changes pretty dramatically once you reach a deductible. Or if you're a Medicare member, there's the donut hole. And all of those things are also inputs and complexity to add to this. So to answer your question, it's really working closely with the stakeholders that control those, that are the source of that data. Right. You really can't get to an accurate price without working with those with those data sources specifically. So we work closely with the PBM, with the payer, and we do more or less a mock adjudication. So the same type of adjudication activity that happens on their end when a patient arrives at the point of sale is happening when a provider is making a prescribing decision in this case.Harry Glorikian: I mean, I can tell you, like the last time I had to sit and choose an insurer, and you would think that I'd be better at this than most, I remember having to take two Tylenol, because when I got done, because I thought my head was going to explode. And I could honestly not say to you I made the best choice. It was at the end, it was almost like a Hail Mary, I guess with all the complexity. And the other thing that I keep thinking about is when I used to watch, I think if you have kids, you've watched The Incredibles and there's a point in the show where the manager says they're penetrating inside of our systems to understand how to get how to get the system to pay them or whatever. It feels like it's that level of complexity. And you really need a sophisticated system to sort of bring all that information together to make sense of it all.Kyle Kiser: Yeah, that's true. And it is it is dynamic, it is highly variable and it's very different from administrator to administrator. Right. And a specific example of that, right, is that responses we get back are not across the board consistent, that here's an error and here's what that error means. And that error message is consistent from health plan to health plan. That's just not the way the world works, right. The error messages are specific to those claim systems because ultimately on the other side of the fence, these are mainframe systems in some cases that were designed decades ago that they've then created a layer to expose to the outside world, in this case us. And, you know, it's not simple work for us or for them. So I think the thing also to point out here is that there's a lot of effort from the payer- rrPBM community to make this accessible and to sort of change the way they're doing business and to change the way their technology works to enable some of these things, which is which is progress and should be commended for sure.[musical interlude]Harry Glorikian: Let's pause the conversation for a minute to talk about one small but important thing you can do, to help keep the podcast going. And that's leave a rating and a review for the show on Apple Podcasts.All you have to do is open the Apple Podcasts app on your smartphone, search for The Harry Glorikian Show, and scroll down to the Ratings & Reviews section. Tap the stars to rate the show, and then tap the link that says Write a Review to leave your comments. It'll only take a minute, but you'll be doing a lot to help other listeners discover the show.And one more thing. If you like the interviews we do here on the show I know you'll like my new book, The Future You: How Artificial Intelligence Can Help You Get Healthier, Stress Less, and Live Longer.It's a friendly and accessible tour of all the ways today's information technologies are helping us diagnose diseases faster, treat them more precisely, and create personalized diet and exercise programs to prevent them in the first place.The book is now available in print and ebook formats. Just go to Amazon or Barnes & Noble and search for The Future You by Harry Glorikian.And now, back to the show.[musical interlude]Harry Glorikian: Interesting. So if I'm not mistaken, both Epic and Cerner have made it possible for providers to embed SwiftRx into their EHR. So if I understand it correctly, it even comes as a standard part of Cerner now. So those are two of the biggest EHR providers in the US.Kyle Kiser: And Athena.Harry Glorikian: And Athena, so question: how did you make that happen?Kyle Kiser: Well, you know, we've got a great team and the team executed ultimately. We worked really hard on those relationships. And I think it's both working with the right customers in small ways in the early days that leads to working with these types of partners and bigger ways. And frankly, some of the open programs at some of these places led to this. So early days, we were working in kind of the more open developer type programs with these EMR partners. We were working closely with some of their customers. Banner was one of our first customers. UC Health was one of our first customers, both a Cerner and an Epic user respectively, and, you know, is working in small ways to solve these problems together with those health systems that led us both to interacting with PBMs and ultimately building these enterprise level relationships with the EMR. It's, you know, it's, it's earning the trust, it's delivering for these customers and then earning the right to do this at scale. And we're to a point now where we'll do almost 100 million of these transactions this year. And it's you know, it's grown fast.Harry Glorikian: Yeah, that's a lot of that's a lot of data flowing back and forth. But so let's ask the money question, like, what's the business model? Who ends up paying you? Is it the provider buying SwiftRx as an add on to the existing EHR or how does that work?Kyle Kiser: It's the risk bearing entity ultimately. So think about that as payer and PBM. In most cases, there are cases where we work with health systems and there are some things we do that that are either channel related or related to specific needs that they have when they're that risk bearing entity. But at a high level, we follow the risk and we want to work with the customer that is bearing that risk because ultimately they're the ones that stand to benefit from an optimized prescription choice.Harry Glorikian: Okay. So that everybody gets a clear idea of like, can you give me a before and after picture at a clinic that brings SwiftRx into their EHR?Kyle Kiser: Sure. Yeah. So. You know, this is probably an experience many of many of the listeners have had. Right. Is that. Before such acts you interact with your physician, they diagnose you with whatever condition they've perceived. They select a medication. They route it to the pharmacy. You go to the pharmacy and cross your fingers that all of the requirements have been met. And that is at a price that you can afford if there is a prior or if that's too expensive. When you arrive at that site of fulfillment, you discover that, right, if there's a prior that's not been completed, then you've got to go through that prior authorization process and you're not picking up that prescription today. If it's a price you can't afford, you got to figure out how to pay for it. And there's a variety of ways that that happens. But ultimately, it's up to the patient to figure those things out. In a world where SwiftRx is installed, the difference is, as that prescription decision is happening, we notify the prescriber of the patient's out-of-pocket cost. In some cases, even the plan cost associated with that choice. Any restrictions that exist like prior or quantity limit or step therapy. And we also notify them of any lower cost alternatives. So in many cases, simple changes make big differences in in the out-of-pocket cost. And it might even be something as simple as, time release metformin can be hundreds if not $1,000, and regular old metformin is four bucks and has been four bucks for decades.Kyle Kiser: So it's some of those almost unintentional, I hesitate to call them errors on the provider side. It's just they're making choices based on their own sort of clinical expertise. But they don't they don't know these things, right? They don't know how a time release metformin might be reimbursed for one of the ten or 12 payers that they may see in a given clinic day. So it's just providing that insight upfront so that they can make those decisions and understand the trade offs. Is time release really important or is this patient going to be fine? And is that out-of-pocket costs for a med going to prevent them from being able to actually take that medication? And as a result, they're not going to receive any of the clinical benefit. So ultimately, the $4 option is probably better. So it's really connecting that clinical decision making process with all of the complexity that exists on the payer and PBM end so that we can get the decision right the first time. And when the patient shows up at the pharmacy, they know how much is going to cost, they feel comfortable that they can pay for it and they're either aware of the prior auth and have already completed the requirements or have some, some level of expectations set to how to complete those requirements.Harry Glorikian: So for all the reasons we've been discussing, doctors traditionally have been able to stay somewhat separated or maybe called it shielded from discussions about drug prices. I mean, they just prescribe a drug, leave it to their office staff or the patient or their pharmacy to figure out whether it's covered. But now, for organizations that are using your system that are built into their EHR, a clinical encounter, it can involve essentially going shopping in real time for the best drug at the best price. I mean, in your experience, how do doctors like being pulled into these decisions? I mean, I can see how it be great for patients, but I wonder if doctors are equally excited.Kyle Kiser: You know, one of the things that's been the most surprising to us around this subject, specifically patient out-of-pocket cost, is one of the most requested pieces of information in a primary care clinic, because it's so complex and it creates so many callbacks and it creates so much patient dissatisfaction. Because ultimately the patient's going to, at some level, hold that prescriber accountable for that decision. And if it's really expensive med there's an assumption that the provider knew that already or should have known that, whether that's true or not. And so what that's resulted in is primary care providers want this information, they want it. They want to have this at their fingertips when they're making decisions. It's the world certainly changed in that way. So I think, you know, it's becoming a part of the standard of care being able to consider cost. Because to the point earlier, the only medication that works is the one the patient can afford. And so you really have to consider those things because of the way our sort of health care payment infrastructure exists. Right. There's just, patients are bearing a dramatic portion of that cost these days and got to consider that as a part of the way you deliver care.Harry Glorikian: I mean, I almost feel like your company is is pushing. These providers and payers and to fix the prescription benefit system or making them more efficient or compatible.Kyle Kiser: Yeah. I think there is a, I maybe describe it as rationalizing. R I don't think that a clinical team and a PBM and PNT committee at a health system have dramatically different opinions on what medications should be prescribed, for what conditions. The friction exists in that they're making those decisions in isolation of one another. So I think I see our role as a connector to help, you know, in a value based world, the incentives start to align between risk bearing entity and health system. And many times the health system becomes the risk bearing entity fully. And so our goal is to empower providers to understand those things in real time, to manage the complexity for them, only engage them with the information that makes a difference in the decision they're trying to make and ultimately create a better experience for the patient, a better outcome for the patient, and a less burdensome process for the provider organization.Harry Glorikian: So as we all know, I mean, the American medical system is famous for sending patients surprise bills after clinical encounter or an emergency room visit, right. Where a bandage or an aspirin can carry some crazy prices that I've seen. And I'm trying to project onto where you are as a company and where you want to go. I mean, now that you've tackled the rrtransparency in drug pricing, which I would honestly like to see everywhere, because I think I've heard my wife complain all the time when she encounters some astronomical price. Right. Can you imagine trying to tackle or bring greater transparency to other medical costs, such as maybe a surgical procedure or hospital supplies. I mean, is there anything that you've learned about prescription benefits that's transferable to all these other types of care?Kyle Kiser: Absolutely. Yeah. We're already moving beyond prescriptions today and focused on labs, radiology services, generally. And see the dynamics of the payer-PBM end of the market five or six years ago as it relates to pharmacy real time benefit shaping up much in the same way around medical benefits. That payers are thinking about these problems in the same ways and are showing initiative and prioritizing putting this information at the point of care for for all of the reasons that we just described on the drug side are true in many ways on the medical side. So, yes, absolutely. That's where we're headed. And the regulatory tailwinds are there in a new way. Right. If you think about in the last 12 months, there's been more price transparency legislation than in the last 30 years. And that, combined with the no surprise billing legislation, really creates this this kind of pre EOB requirement for each of the stakeholders and they got to solve that problem. And we see ourselves as really well positioned to be a part of that solution.Harry Glorikian: Yeah. I mean, you know, it there was no way. I mean, the Affordable Care Act got put into place and there were certain things in there that just there was no way that you were going to be able to do that without some level of transparency and understanding what's going on.Kyle Kiser: Yeah. Yeah, that's right. But even further, right, before the end of last year there were price transparency regulations for health systems, for providers, for payers. And then the no surprise billing legislation has in it a component that says, you know, before you deliver care, you got to be able to give an estimation of cost. And so all of those things sort of work together from a regulatory perspective to start to drive the market in that direction. So absolutely, it's coming everywhere. It's going to be, it's going to be a part of the way that every health care decision is made in the future. And it's just a matter of time before that's the case.Harry Glorikian: Yeah. It's interesting because I have lots of conversations with, you know, lots of different people. And they I don't think they understand that. If you don't have that level of transparency, you truly don't have a competitive environment, right? You can't make choices because you don't have the information to be able to make that choice.Kyle Kiser: That's exactly right. Without it, there is no marketplace. Right. That's probably overstated. It's without it, it's a dysfunctional marketplace. And with transparency, we will start to see real competitive dynamics emerge. And I'm hopeful for that. Sunlight's the greatest antiseptic.Harry Glorikian: Oh, I totally agree. I mean, for me, it's always been like a walled garden. Like, you know, either you're here or, you know, you're out of luck, right? Because you don't have any information so you can go across the street. So. So. I guess I should be asking. I've probably reached the limit of my knowledge on the subject matter, but like, is. Is there anything I haven't asked you or anything, you know, that you would want to add to the conversation that would be enlightening to the people that are listening?Kyle Kiser: Yeah, well, the only thing I would sort of make sure we reframe a little bit is that this isn't necessarily about price transparency. Price transparency is a component of providing access to care for patients, and that's ultimately what we continually focus on inside of our company, that price is an input. Affordability is an input. Convenience is an input. The ability to actually receive the prescription is an input. We're ultimately trying to make sure that affordability and speed to care lead to better outcomes. And that's an access story, not just a price transparency story. And so that's the only sort of reframe that I'd offer is that ultimately this has to lead to better health, people getting healthier, getting the care they need, being able to afford the medications that they need. And that's the work. And we're going to stop at nothing to make sure that that happens.Harry Glorikian: Excellent. Well, it was great talking to you, Kyle. I wish you great success because, I mean, whenever I talk to anybody, I'm like, I know I could be benefiting from all of this, so I want everybody to be successful.Kyle Kiser: We appreciate the well-wishes and we'll be working hard to ensure that that's the case.Harry Glorikian: Excellent. Thank you so much.Kyle Kiser: All right. Thanks, Harry.Harry Glorikian: Bye bye.Harry Glorikian: That's it for this week's episode. You can find a full transcript of this episode as well as the full archive of episodes of The Harry Glorikian Show and MoneyBall Medicine at our website. Just go to glorikian.com and click on the tab Podcasts.I'd like to thank our listeners for boosting The Harry Glorikian Show into the top three percent of global podcasts.If you want to be sure to get every new episode of the show automatically, be sure to open Apple Podcasts or your favorite podcast player and hit follow or subscribe. Don't forget to leave us a rating and review on Apple Podcasts. And we always love to hear from listeners on Twitter, where you can find me at hglorikian.Thanks for listening, stay healthy, and be sure to tune in two weeks from now for our next interview.

Harry's guest Eric Daimler, a serial software entrepreneur and a former Presidential Innovation Fellow in the Obama Administration, has an interesting argument about math. If you're a young person today trying to decide which math course you're going to take—or maybe an old person who just wants to brush up—he says you shouldn't bother with trigonometry or calculus. Instead he says you should study category theory. An increasingly important in computer science, category theory is about the relationships between sets or structures. It can be used to prove that different structures are consistent or compatible with one another, and to prove that the relationships in a dataset are still intact even after the data has been transformed in some way. Together with two former MIT mathematicians, Daimler co-founded a company called Conexus that uses category theory to tackle the problem of data interoperability. Longtime listeners know that data interoperability in healthcare, or more often the lack of interoperability, is a repeating theme of the show. In fields from drug development to frontline medical care, we've got petabytes of data to work with, in the form of electronic medical records, genomic and proteomic data, and clinical trial data. That data could be the fuel for machine learning and other kinds of computation that could help us make develop drugs faster and make smarter decisions about care. The problem is, it's all stored in different databases and formats that can't be safely merged without a nightmarish amount of work. So when someone like Daimler says they have a way to use math to bring heterogeneous data together without compromising that data's integrity – well, it's time to pay attention. That's why on today's show, we're all going back to school for an introductory class in category theory.Please rate and review The Harry Glorikian Show on Apple Podcasts! Here's how to do that from an iPhone, iPad, or iPod touch:1. Open the Podcasts app on your iPhone, iPad, or Mac. 2. Navigate to The Harry Glorikian Show podcast. You can find it by searching for it or selecting it from your library. Just note that you'll have to go to the series page which shows all the episodes, not just the page for a single episode.3. Scroll down to find the subhead titled "Ratings & Reviews."4. Under one of the highlighted reviews, select "Write a Review."5. Next, select a star rating at the top — you have the option of choosing between one and five stars. 6. Using the text box at the top, write a title for your review. Then, in the lower text box, write your review. Your review can be up to 300 words long.7. Once you've finished, select "Send" or "Save" in the top-right corner. 8. If you've never left a podcast review before, enter a nickname. Your nickname will be displayed next to any reviews you leave from here on out. 9. After selecting a nickname, tap OK. Your review may not be immediately visible.That's it! Thanks so much.TranscriptHarry Glorikian: Hello. I'm Harry Glorikian, and this is The Harry Glorikian Show, where we explore how technology is changing everything we know about healthcare.My guest today is Eric Daimler, a serial software entrepreneur and a former Presidential Innovation Fellow in the Obama Administration.And he has an interesting argument about math. Daimler says if you're a young person today trying to decide which math course you're going to take, or maybe an old person who just wants to brush up, you shouldn't bother with trigonometry or calculus.Instead he says you should study category theory.That's a field that isn't even part of the curriculum at most high schools. But it's increasingly important in computer science.Category theory is about the relationships between sets or structures. It can be used to prove that different structures are consistent or compatible with one another, and to prove that the relationships in a dataset are still intact even after you've transformed that data in some way.Together with two former MIT mathematicians, Daimler co-founded a company called Conexus that uses category theory to tackle the problem of data interoperability.Now…longtime listeners of the show know that data interoperability in healthcare, or more often the lack of interoperability, is one of my biggest hobby horses. In fields from drug development to frontline medical care, we've got petabytes of data to work with, in the form of electronic medical records, genomic and proteomic data, and clinical trial data.That data could be the fuel for machine learning and other kinds of computation that could help us make develop drugs faster and make smarter decisions about care. The problem is, it's all stored in different databases and formats that can't be safely merged without a nightmarish amount of work.So when someone like Daimler says they have a way to use math to bring heterogeneous data together without compromising that data's integrity – well, I pay attention.So on today's show, we're all going back to school for an introductory class in category theory from Conexus CEO Eric Daimler.Harry Glorikian: Eric, welcome to the show.Eric Daimler: It's great to be here.Harry Glorikian: So I was reading your varied background. I mean, you've worked in so many different kinds of organizations. I'm not sure that there is a compact way or even an accurate way to describe you. So can you describe yourself? You know, what do you do and what are your main interest areas?Eric Daimler: Yeah, I mean, the easiest way to describe me might come from my mother. Well, where, you know, somebody asked her, is that the doctor? And she says, Well, yes, but he's not the type that helps people. So I you know, I've been doing research around artificial intelligence and I from a lot of different perspectives around my research in graph theory and machine learning and computational linguistics. I've been a venture capitalist on Sand Hill Road. I've done entrepreneurship, done entrepreneurship, and I started a couple of businesses which I'm doing now. And most notably I was doing policy in Washington, D.C. is part of the Obama administration for a time. So I am often known for that last part. But my background really is rare, if not unique, for having the exposure to AI from all of those angles, from business, academia and policy.Harry Glorikian: Yeah. I mean, I was looking at the obviously the like you said, the one thing that jumped out to me was the you were a Presidential Innovation Fellow in the Obama administration in 2016. Can you can you give listeners an idea of what is what is the Presidential Innovation Fellowship Program? You know, who are the types of people that are fellows and what kind of things do they do?Eric Daimler: Sure, it was I guess with that sort of question, it's helpful then to give a broader picture, even how it started. There was a a program started during the Nixon administration that's colloquially known as the Science Advisers to the President, you know, a bipartisan group to give science advice to the president that that's called the OSTP, Office of Science and Technology Policy. There are experts within that group that know know everything from space to cancer, to be super specific to, in my domain, computer security. And I was the authority that was the sole authority during my time in artificial intelligence. So there are other people with other expertise there. There are people in different capacities. You know, I had the particular capacity, I had the particular title that I had that was a one year term. The staffing for these things goes up and down, depending on the administration in ways that you might be able to predict and guess. The people with those titles also also find themselves in different parts of the the executive branch. So they will do a variety of things that are not predicted by the the title of the fellow. My particular role that I happened to be doing was in helping to coordinate on behalf of the President, humbly, on behalf of the President, their research agenda across the executive branch. There are some very able people with whom I had the good fortune of working during my time during my time there, some of which are now in the in the Biden administration. And again, it's to be a nonpartisan effort around artificial intelligence. Both sides should really be advocates for having our research agenda in government be most effective. But my role was coordinating such things as, really this is helpful, the definition of robotics, which you might be surprised by as a reflex but but quickly find to be useful when you're thinking that the Defense Department's definition and use, therefore, of robotics is really fundamentally different than that of health and human services use and a definition of robotics and the VA and Department of Energy and State and and so forth.Eric Daimler: So that is we find to be useful, to be coordinated by the Office of the President and experts speaking on behalf. It was started really this additional impulse was started after the effects of, I'll generously call them, of healthcare.gov and the trip-ups there where President Obama, to his great credit, realized that we needed to attract more technologists into government, that we had a lot of lawyers to be sure we had, we had a ton of academics, but we didn't have a lot of business people, practical technologists. So he created a way to get people like me motivated to come into government for short, short periods of time. The the idea was that you could sit around a cabinet, a cabinet meeting, and you could you would never be able to raise your hand saying, oh, I don't know anything about economics or I don't know anything about foreign policy, but you could raise your hand and say, Oh, I don't know anything about technology. That needs to be a thing of the past. President Obama saw that and created a program starting with Todd. Todd Park, the chief technologist, the second chief technology officer of the United States, is fantastic to to start to start some programs to bring in people like me.Harry Glorikian: Oh, yeah. And believe me, in health care, we need we need more technologists, which I always preach. I'm like, don't go to Facebook. Come here. You know, you can get double whammy. You can make money and you can affect people's lives. So I'm always preaching that to everybody. But so if I'm not mistaken, in early 2021, you wrote an open letter to the brand new Biden administration calling for sort of a big federal effort to improve national data infrastructure. Like, can you summarize for everybody the argument in that piece and. Do you see them doing any of the items that you're suggesting?Eric Daimler: Right. The the idea is that despite us making some real good efforts during the Obama administration with solidifying our, I'll say, our view on artificial intelligence across the executive, and this continuing actually into the Trump administration with the establishment of an AI office inside the OSTP. So credit where credit is due. That extended into the the Biden administration, where some very well-meaning people can be focusing on different parts of the the conundrum of AI expressions, having various distortions. You know, the popular one we will read about is this distortion of bias that can express itself in really ugly ways, as you know, as individuals, especially for underrepresented groups. The point of the article was to help others be reminded of of some of the easy, low hanging fruit that we can that we can work on around AI. So, you know, bias comes in a lot of different ways, the same way we all have cognitive distortions, you know, cognitive biases. There are some like 50 of them, right. You know, bias can happen around gender and ethnicity and age, sexual orientation and so forth. You know, it all can also can come from absence of data. There's a type of bias that's present just by being in a developed, rich country in collecting, for example, with Conexus's customers, my company Conexus's customers, where they are trying to report on their good efforts for economic and social good and around clean, renewable energies, they find that there's a bias in being able to collect data in rich countries versus developing countries.Eric Daimler: That's another type of bias. So that was that was the point of me writing that open letter, to prioritize, these letters. It's just to distinguish what the low hanging fruit was versus some of the hard problems. The, some of tthe low hanging fruit, I think is available, I can say, In three easy parts that people can remember. One is circuit breakers. So we we can have circuit breakers in a lot of different parts of these automated systems. You know, automated car rolling down a road is, is the easiest example where, you know, at some point a driver needs to take over control to determine to make a judgment about that shadow being a person or a tumbleweed on the crosswalk, that's a type of circuit breaker. We can have those circuit breakers in a lot of different automated systems. Another one is an audit. And the way I mean is audit is having people like me or just generally people that are experts in the craft being able to distinguish the data or the biases can become possible from the data model algorithms where biases also can become possible. Right. And we get a lot of efficiency from these automated systems, these learning algorithms. I think we can afford a little bit taken off to audit the degree to which these data models are doing what we intend.Eric Daimler: And an example of a data model is that Delta Airlines, you know, they know my age or my height, and I fly to San Francisco, to New York or some such thing. The data model would be their own proprietary algorithm to determine whether or not I am deserving of an upgrade to first class, for example. That's a data model. We can have other data models. A famous one that we all are part of is FICO scores, credit scores, and those don't have to be disclosed. None of us actually know what Experian or any of the credit agencies used to determine our credit scores. But they they use these type of things called zero knowledge proofs, where we just send through enough data, enough times that we can get to a sense of what those data models are. So that's an exposure of a data model. A declarative exposure would be maybe a next best thing, a next step, and that's a type of audit.Eric Daimler: And then the third low hanging fruit, I'd say, around regulation, and I think these are just coming towards eventualities, is demanding lineage or demanding provenance. You know, you'll see a lot of news reports, often on less credible sites, but sometimes on on shockingly credible sites where claims are made that you need to then search yourself and, you know, people in a hurry just won't do it, when these become very large systems and very large systems of information, alert systems of automation, I want to know: How were these conclusions given? So, you know, an example in health care would be if my clinician gave me a diagnosis of, let's say, some sort of cancer. And then to say, you know, here's a drug, by the way, and there's a five chance, 5 percent chance of there being some awful side effects. You know, that's a connection of causation or a connection of of conclusions that I'm really not comfortable with. You know, I want to know, like, every step is like, wait, wait. So, so what type of cancer? So what's the probability of my cancer? You know, where is it? And so what drug, you know, how did you make that decision? You know, I want to know every little step of the way. It's fine that they give me that conclusion, but I want to be able to back that up. You know, a similar example, just in everyday parlance for people would be if I did suddenly to say I want a house, and then houses are presented to me. I don't quite want that. Although that looks like good for a Hollywood narrative. Right? I want to say, oh, wait, what's my income? Or what's my cash? You know, how much? And then what's my credit? Like, how much can I afford? Oh, these are houses you can kind of afford. Like, I want those little steps or at least want to back out how those decisions were made available. That's a lineage. So those three things, circuit breaker, audit, lineage, those are three pieces of low hanging fruit that I think the European Union, the State of New York and other other government entities would be well served to prioritize.Harry Glorikian: I would love all of them, especially, you know, the health care example, although I'm not holding my breath because I might not come back to life by how long I'd have to hold my breath on that one. But we're hoping for the best and we talk about that on the show all the time. But you mentioned Conexus. You're one of three co founders, I believe. If I'm not mistaken, Conexus is the first ever commercial spin out from MIT's math department. The company is in the area of large scale data integration, building on insights that come out of the field of mathematics that's called category algebra, categorical algebra, or something called enterprise category theory. And to be quite honest, I did have to Wikipedia to sort of look that up, was not familiar with it. So can you explain category algebra in terms of a non mathematician and maybe give us an example that someone can wrap their mind around.Eric Daimler: Yeah. Yeah. And it's important to get into because even though what my company does is, Conexus does a software expression of categorical algebra, it's really beginning to permeate our world. You know, the the way I tell my my nieces and nephews is, what do quantum computers, smart contracts and Minecraft all have in common? And the answer is composability. You know, they are actually all composable. And what composable is, is it's kind of related to modularity, but it's modularity without regard to scale. So the the easy analogy is in trains where, yeah, you can swap out a boxcar in a train, but mostly trains can only get to be a couple of miles long. Swap in and out boxcars, but the train is really limited in scale. Whereas the train system, the system of a train can be infinitely large, infinitely complex. At every point in the track you can have another track. That is the difference between modularity and composability. So Minecraft is infinitely self referential where you have a whole 'nother universe that exists in and around Minecraft. In smart contracts is actually not enabled without the ability to prove the efficacy, which is then enabled by categorical algebra or its sister in math, type theory. They're kind of adjacent. And that's similar to quantum computing. So quantum computing is very sexy. It gets in the press quite frequently with forks and all, all that. If it you wouldn't be able to prove the efficacy of a quantum compiler, you wouldn't actually. Humans can't actually say whether it's true or not without type theory or categorical algebra.Eric Daimler: How you think of kind categorical algebra you can think of as a little bit related to graph theory. Graph theory is those things that you see, they look like spider webs. If you see the visualizations of graph theories are graphs. Category theory is a little bit related, you might say, to graph theory, but with more structure or more semantics or richness. So in each point, each node and each edge, in the vernacular, you can you can put an infinite amount of information. That's really what a categorical algebra allows. This, the discovery, this was invented to be translating math between different domains of math. The discovery in 2011 from one of my co-founders, who was faculty at MIT's Math Department, was that we could apply that to databases. And it's in that the whole world opens up. This solves the problem that that bedeviled the good folks trying to work on healthcare.gov. It allows for a good explanation of how we can prevent the next 737 Max disaster, where individual systems certainly can be formally verified. But the whole plane doesn't have a mechanism of being formally verified with classic approaches. And it also has application in drug discovery, where we have a way of bringing together hundreds of thousands of databases in a formal way without risk of data being misinterpreted, which is a big deal when you have a 10-year time horizon for FDA trials and you have multiple teams coming in and out of data sets and and human instinct to hoard data and a concern about it ever becoming corrupted. This math and the software expression built upon it opens up just a fantastically rich new world of opportunity for for drug discovery and for clinicians and for health care delivery. And the list is quite, quite deep.Harry Glorikian: So. What does Conexus provide its clients? Is it a service? Is it a technology? Is it both? Can you give us an example of it?Eric Daimler: Yeah. So Conexus is software. Conexus is enterprise software. It's an enterprise software platform that works generally with very large organizations that have generally very large complex data data infrastructures. You know the example, I can start in health care and then I can I can move to an even bigger one, was with a hospital group that we work with in New York City. I didn't even know health care groups could really have this problem. But it's endemic to really the world's data, where one group within the same hospital had a particular way that they represented diabetes. Now to a layman, layman in a health care sense, I would think, well, there's a definition of diabetes. I can just look it up in the Oxford English Dictionary. But this particular domain found diabetes to just be easily represented as yes, no. Do they have it? Do they not? Another group within the same hospital group thought that they would represent it as diabetes, ow are we treating it? A third group would be representing it as diabetes, how long ago. And then a fourth group had some well-meaning clinicians that would characterize it as, they had it and they have less now or, you know, type one, type two, you know, with a more more nuanced view.Eric Daimler: The traditional way of capturing that data, whether it's for drug discovery or whether it's for delivery, is to normalize it, which would then squash the fidelity of the data collected within those groups. Or they most likely to actually just wouldn't do it. They wouldn't collect the data, they wouldn't bring the data together because it's just too hard, it's too expensive. They would use these processes called ETL, extract, transform, load, that have been around for 30 years but are often slow, expensive, fragile. They could take six months to year, cost $1,000,000, deploy 50 to 100 people generally from Accenture or Deloitte or Tata or Wipro. You know, that's a burden. It's a burden, you know, so the data wasn't available and that would then impair the researchers and their ability to to share data. And it would impair clinicians in their view of patient care. And it also impaired the people in operations where they would work on billing. So we work with one company right now that that works on 1.4 trillion records a year. And they just have trouble with that volume and the number of databases and the heterogeneous data infrastructure, bringing together that data to give them one view that then can facilitate health care delivery. Eric Daimler: The big example is, we work with Uber where they they have a very smart team, as smart as one might think. They also have an effectively infinite balance sheet with which they could fund an ideal IT infrastructure. But despite that, you know, Uber grew up like every other organization optimizing for the delivery of their service or product and, and that doesn't entail optimizing for that infrastructure. So what they found, just like this hospital group with different definitions of diabetes, they found they happen to have grown up around service areas. So in this case cities, more or less. So when then the time came to do analysis -- we're just passing Super Bowl weekend, how will the Super Bowl affect the the supply of drivers or the demand from riders? They had to do it for the city of San Francisco, separate than the city of San Jose or the city of Oakland. They couldn't do the whole San Francisco Bay Area region, let alone the whole of the state or the whole of the country or what have you. And that repeated itself for every business question, every organizational question that they would want to have. This is the same in drug discovery. This is the same in patient care delivery or in billing. These operational questions are hard, shockingly hard.Eric Daimler: We had another one in logistics where we had a logistics company that had 100,000 employees. I didn't even know some of these companies could be so big, and they actually had a client with 100,000 employees. That client had 1000 ships, each one of which had 10,000 containers. And I didn't even know like how big these systems were really. I hadn't thought about it. But I mean, they're enormous. And the question was, hey, where's our personal protective equipment? Where is the PPE? And that's actually a hard question to ask. You know, we are thinking about maybe our FedEx tracking numbers from an Amazon order. But if you're looking at the PPE and where it is on a container or inside of a ship, you know, inside this large company, it's actually a hard question to ask. That's this question that all of these organizations have. Eric Daimler: In our case, Uber, where they they they had a friction in time and in money and in accuracy, asking every one of these business questions. They went then to find, how do I solve this problem? Do I use these old tools of ETL from the '80s? Do I use these more modern tools from the 2000s? They're called RDF or OWL? Or is there something else? They discovered that they needed a more foundational system, this categorical algebra that that's now expressing itself in smart contracts and quantum computers and other places. And they just then they found, oh, who are the leaders in the enterprise software expression of that math? And it's us. We happen to be 40 miles north of them. Which is fortunate. We worked with Uber to to solve that problem in bringing together their heterogeneous data infrastructure to solve their problems. And to have them tell it they save $10 million plus a year in in the efficiency and speed gains from the solution we helped provide for them.[musical interlude]Harry Glorikian: Let's pause the conversation for a minute to talk about one small but important thing you can do, to help keep the podcast going. And that's leave a rating and a review for the show on Apple Podcasts.All you have to do is open the Apple Podcasts app on your smartphone, search for The Harry Glorikian Show, and scroll down to the Ratings & Reviews section. Tap the stars to rate the show, and then tap the link that says Write a Review to leave your comments. It'll only take a minute, but you'll be doing a lot to help other listeners discover the show.And one more thing. If you like the interviews we do here on the show I know you'll like my new book, The Future You: How Artificial Intelligence Can Help You Get Healthier, Stress Less, and Live Longer.It's a friendly and accessible tour of all the ways today's information technologies are helping us diagnose diseases faster, treat them more precisely, and create personalized diet and exercise programs to prevent them in the first place.The book is now available in print and ebook formats. Just go to Amazon or Barnes & Noble and search for The Future You by Harry Glorikian.And now, back to the show.[musical interlude]Harry Glorikian: So your website says that your software can map data sources to each other so that the perfect data model is discovered, not designed. And so what does that mean? I mean, does that imply that there's some machine learning or other form of artificial intelligence involved, sort of saying here are the right pieces to put together as opposed to let me design this just for you. I'm trying to piece it together.Eric Daimler: Yeah. You know, the way we might come at this is just reminding ourselves about the structure of artificial intelligence. You know, in the public discourse, we will often find news, I'm sure you can find it today, on deep learning. You know, whatever's going on in deep learning because it's sexy, it's fun. You know, DeepMind really made a name for themselves and got them acquired at a pretty valuation because of their their Hollywood-esque challenge to Go, and solving of that game. But that particular domain of AI, deep learning, deep neural nets is a itself just a subset of machine learning. I say just not not not to minimize it. It's a fantastically powerful algorithm. But but just to place it, it is a subset of machine learning. And then machine learning itself is a subset of artificial intelligence. That's a probabilistic subset. So we all know probabilities are, those are good and bad. Fine when the context is digital advertising, less fine when it's the safety of a commercial jet. There is another part of artificial intelligence called deterministic artificial intelligence. They often get expressed as expert systems. Those generally got a bad name with the the flops of the early '80s. Right. They flopped because of scale, by the way. And then the flops in the early 2000s and 2010s from IBM's ill fated Watson experiment, the promise did not meet the the reality.Eric Daimler: It's in that deterministic A.I. that that magic is to be found, especially when deployed in conjunction with the probabilistic AI. That's that's where really the future is. There's some people have a religious view of, oh, it's only going to be a probabilistic world but there's many people like myself and not to bring up fancy names, but Andrew Ng, who's a brilliant AI researcher and investor, who also also shares this view, that it's a mix of probabilistic and deterministic AI. What deterministic AI does is, to put it simply, it searches the landscape of all possible connections. Actually it's difference between bottoms up and tops down. So the traditional way of, well, say, integrating things is looking at, for example, that hospital network and saying, oh, wow, we have four definitions of diabetes. Let me go solve this problem and create the one that works for our hospital network. Well, then pretty soon you have five standards, right? That's the traditional way that that goes. That's what a top down looks that looks like.Eric Daimler: It's called a Golden Record often, and it rarely works because pretty soon what happens is the organizations will find again their own need for their own definition of diabetes. In most all cases, that's top down approach rarely works. The bottoms up approach says, Let's discover the connections between these and we'll discover the relationships. We don't discover it organically like we depend on people because it's deterministic. I, we, we discover it through a massive, you know, non intuitive in some cases, it's just kind of infeasible for us to explore a trillion connections. But what the AI does is it explores a factorial number actually is a technical, the technical equation for it, a factorial number of of possible paths that then determine the map of relationships between between entities. So imagine just discovering the US highway system. If you did that as a person, it's going to take a bit. If you had some infinitely fast crawlers that robot's discovering the highway system infinitely fast, remember, then that's a much more effective way of doing it that gives you some degree of power. That's the difference between bottoms up and tops down. That's the difference between deterministic, really, we might say, and probabilistic in some simple way.Harry Glorikian: Yeah, I'm a firm believer of the two coming together and again, I just look at them as like a box. I always tell people like, it's a box of tools. I need to know the problem, and then we can sort of reach in and pick out which set of tools that are going to come together to solve this issue, as opposed to this damn word called AI that everybody thinks is one thing that they're sort of throwing at the wall to solve a problem.Harry Glorikian: But you're trying to solve, I'm going to say, data interoperability. And on this show I've had a lot of people talk about interoperability in health care, which I actually believe is, you could break the system because things aren't working right or I can't see what I need to see across the two hospitals that I need information from. But you published an essay on Medium about Haven, the health care collaboration between Amazon, JPMorgan, Berkshire Hathaway. Their goal was to use big data to guide patients to the best performing clinicians and the most affordable medicines. They originally were going to serve these first three founding companies. I think knowing the people that started it, their vision was bigger than that. There was a huge, you know, to-do when it came out. Fireworks and everything. Launched in 2018. They hired Atul Gawande, famous author, surgeon. But then Gawande left in 2020. And, you know, the company was sort of quietly, you know, pushed off into the sunset. Your essay argued that Haven likely failed due to data interoperability challenges. I mean. How so? What what specific challenges do you imagine Haven ran into?Eric Daimler: You know, it's funny, I say in the article very gently that I imagine this is what happened. And it's because I hedge it that that the Harvard Business Review said, "Oh, well, you're just guessing." Actually, I wasn't guessing. No, I know. I know the people that were doing it. I know the challenges there. But but I'm not going to quote them and get them in trouble. And, you know, they're not authorized to speak on it. So I perhaps was a little too modest in my framing of the conclusion. So this actually is what happened. What happens is in the same way that we had the difficulty with healthcare.gov, in the same way that I described these banks having difficulty. Heterogeneous databases don't like to talk to one another. In a variety of different ways. You know, the diabetes example is true, but it's just one of many, many, many, many, many, many cases of data just being collected differently for their own use. It can be as prosaic as first name, last name or "F.last name." Right? It's just that simple, you know? And how do I bring those together? Well, those are those are called entity resolutions. Those are somewhat straightforward, but not often 100 percent solvable. You know, this is just a pain. It's a pain. And, you know, so what what Haven gets into is they're saying, well, we're massive. We got like Uber, we got an effectively infinite balance sheet. We got some very smart people. We'll solve this problem. And, you know, this is some of the problem with getting ahead of yourself. You know, I won't call it arrogance, but getting ahead of yourself, is that, you think, oh, I'll just be able to solve that problem.Eric Daimler: You know, credit where credit is due to Uber, you know, they looked both deeper saying, oh, this can't be solved at the level of computer science. And they looked outside, which is often a really hard organizational exercise. That just didn't happen at Haven. They thought they thought they could they could solve it themselves and they just didn't. The databases, not only could they have had, did have, their own structure, but they also were stored in different formats or by different vendors. So you have an SAP database, you have an Oracle database. That's another layer of complication. And when I say that these these take $1,000,000 to connect, that's not $1,000,000 one way. It's actually $2 million if you want to connect it both ways. Right. And then when you start adding five, let alone 50, you take 50 factorial. That's a very big number already. You multiply that times a million and 6 to 12 months for each and a hundred or two hundred people each. And you just pretty soon it's an infeasible budget. It doesn't work. You know, the budget for us solving solving Uber's problem in the traditional way was something on the order of $2 trillion. You know, you do that. You know, we had a bank in the U.S. and the budget for their vision was was a couple of billion. Like, it doesn't work. Right. That's that's what happened Haven. They'll get around to it, but but they're slow, like all organizations, big organizations are. They'll get around to solving this at a deeper level. We hope that we will remain leaders in database integration when they finally realize that the solution is at a deeper level than their than the existing tools.Harry Glorikian: So I mean, this is not I mean, there's a lot of people trying to solve this problem. It's one of those areas where if we don't solve it, I don't think we're going to get health care to the next level, to sort of manage the information and manage people and get them what they need more efficiently and drive down costs.Eric Daimler: Yeah.Harry Glorikian: And I do believe that EMRs are. I don't want to call them junk. Maybe I'm going too far, but I really think that they you know, if you had decided that you were going to design something to manage patients, that is not the software you would have written to start. Hands down. Which I worry about because these places won't, they spent so much putting them in that trying to get them to rip them out and put something in that actually works is challenging. You guys were actually doing something in COVID-19, too, if I'm not mistaken. Well, how is that project going? I don't know if it's over, but what are you learning about COVID-19 and the capabilities of your software, let's say?Eric Daimler: Yeah. You know, this is an important point that for anybody that's ever used Excel, we know what it means to get frustrated enough to secretly hard code a cell, you know, not keeping a formula in a cell. Yeah, that's what happened in a lot of these systems. So we will continue with electronic medical records to to bring these together, but they will end up being fragile, besides slow and expensive to construct. They will end up being fragile, because they were at some point hardcoded. And how that gets expressed is that the next time some other database standard appears inside of that organization's ecosystem from an acquisition or a divestiture or a different technical standard, even emerging, and then the whole process starts all over again. You know, we just experience this with a large company that that spent $100 million in about five years. And then they came to us and like, yeah, we know it works now, but we know like a year from now we're going to have to say we're going to go through it again. And, it's not like, oh, we'll just have a marginal difference. No, it's again, that factorial issue, that one database connected to the other 50 that already exist, creates this same problem all over again at a couple of orders of magnitude. So what we discover is these systems, these systems in the organization, they will continue to exist.Eric Daimler: These fragile systems will continue to exist. They'll continue to scale. They'll continue to grow in different parts of the life sciences domain, whether it's for clinicians, whether it's for operations, whether it's for drug discovery. Those will continue to exist. They'll continue to expand, and they will begin to approach the type of compositional systems that I'm describing from quantum computers or Minecraft or smart contracts, where you then need the the discovery and math that Conexus expresses in software for databases. When you need that is when you then need to prove the efficacy or otherwise demonstrate the lack of fragility or the integrity of the semantics. Conexus can with, it's a law of nature and it's in math, with 100 percent accuracy, prove the integrity of a database integration. And that matters in high consequence context when you're doing something as critical as drug side effects for different populations. We don't want your data to be misinterpreted. You can't afford lives to be lost or you can't, in regulation, you can't afford data to be leaking. That's where you'll ultimately need the categorical algebra. You'll need a provable compositional system. You can continue to construct these ones that will begin to approach compositionality, but when you need the math is when you need to prove it for either the high consequence context of lives, of money or related to that, of regulation.Harry Glorikian: Yeah, well, I keep telling my kids, make sure you're proficient in math because you're going to be using it for the rest of your life and finance. I always remind them about finance because I think both go together. But you've got a new book coming out. It's called "The Future is Formal" and not tuxedo like formal, but like you're, using the word formal. And I think you have a very specific meaning in mind. And I do want you to talk about, but I think what you're referring to is how we want automated systems to behave, meaning everything from advertising algorithms to self-driving trucks. And you can tell me if that my assumption is correct or not.Eric Daimler: Though it's a great segue, actually, from the math. You know, what I'm trying to do is bring in people that are not programmers or research technology, information technology researchers day to day into the conversation around automated digital systems. That's my motivation. And my motivation is, powered by the belief that we will bring out the best of the technology with more people engaged. And with more people engaged, we have a chance to embrace it and not resist it. You know, my greatest fear, I will say, selfishly, is that we come up with technology that people just reject, they just veto it because they don't understand it as a citizen. That also presents a danger because I think that companies' commercial expressions naturally will grow towards where their technology is needed. So this is actually to some extent a threat to Western security relative to Chinese competition, that we embrace the technology in the way that we want it to be expressed in our society. So trying to bring people into this conversation, even if they're not programmers, the connection to math is that there are 18 million computer programmers in the world. We don't need 18 million and one, you know. But what we do need is we do need people to be thinking, I say in a formal way, but also just be thinking about the values that are going to be represented in these digital infrastructures.Eric Daimler: You know, somewhere as a society, we will have to have a conversation with ourselves to determine the car driving to the crosswalk, braking or rolling or slowing or stopping completely. And then who's liable if it doesn't? Is it the driver or is it the manufacturer? Is it the the programmer that somehow put a bug in their code? You know, we're entering an age where we're going to start experiencing what some person calls double bugs. There's the bug in maybe one's expression in code. This often could be the semantics. Or in English. Like your English doesn't make sense. Right? Right. Or or was it actually an error in your thinking? You know, did you leave a gap in your thinking? This is often where where some of the bugs in Ethereum and smart contracts have been expressed where, you know, there's an old programming rule where you don't want to say something equals true. You always want to be saying true equals something. If you get if you do the former, not the latter, you can have to actually create bugs that can create security breaches.Eric Daimler: Just a small little error in thinking. That's not an error in semantics. That level of thinking, you don't need to know calculus for, or category theory for that matter. You just need to be thinking in a formal way. You know, often, often lawyers, accountants, engineers, you know, anybody with scientific training can, can more quickly get this idea, where those that are educated in liberal arts can contribute is in reminding themselves of the broader context that wants to be expressed, because often engineers can be overly reductionist. So there's really a there's a push and pull or, you know, an interplay between those two sensibilities that then we want to express in rules. Then that's ultimately what I mean by formal, formal rules. Tell me exactly what you mean. Tell me exactly how that is going to work. You know, physicians would understand this when they think about drug effects and drug side effects. They know exactly what it's going to be supposed to be doing, you know, with some degree of probability. But they can be very clear, very clear about it. It's that clear thinking that all of us will need to exercise as we think about the development and deployment of modern automated digital systems.Harry Glorikian: Yeah, you know, it's funny because that's the other thing I tell people, like when they say, What should my kid take? I'm like, have him take a, you know, basic programming, not because they're going to do it for a living, but they'll understand how this thing is structured and they can get wrap their mind around how it is. And, you know, I see how my nephew thinks who's from the computer science world and how I think, and sometimes, you know, it's funny watching him think. Or one of the CTOs of one of our companies how he looks at the world. And I'm like you. You got to back up a little bit and look at the bigger picture. Right. And so it's the two of us coming together that make more magic than one or the other by themselves.Harry Glorikian: So, you know, I want to jump back sort of to the different roles you've had in your career. Like like you said, you've been a technology investor, a serial startup founder, a university professor, an academic administrator, an entrepreneur, a management instructor, Presidential Innovation Fellow. I don't think I've missed anything, but I may have. You're also a speaker, a commentator, an author. Which one of those is most rewarding?Eric Daimler: Oh, that's an interesting question. Which one of those is most rewarding? I'm not sure. I find it to be rewarding with my friends and family. So it's rewarding to be with people. I find that to be rewarding in those particular expressions. My motivation is to be, you know, just bringing people in to have a conversation about what we want our world to look like, to the degree to which the technologies that I work with every day are closer to the dystopia of Hollywood narratives or closer to our hopes around the utopia that's possible, that where this is in that spectrum is up to us in our conversation around what these things want to look like. We have some glimpses of both extremes, but I'd like people, and I find it to be rewarding, to just be helping facilitate the helping catalyze that conversation. So the catalyst of that conversation and whatever form it takes is where I enjoy being.Harry Glorikian: Yeah, because I was thinking about like, you know, what can, what can you do as an individual that shapes the future. Does any of these roles stand out as more impactful than others, let's say?Eric Daimler: I think the future is in this notion of composability. I feel strongly about that and I want to enroll people into this paradigm as a framework from which to see many of the activities going around us. Why have NFTs come on the public, in the public media, so quickly? Why does crypto, cryptocurrency capture our imagination? Those And TikTok and the metaverse. And those are all expressions of this quick reconfiguration of patterns in different contexts that themselves are going to become easier and easier to express. The future is going to be owned by people that that take the special knowledge that they've acquired and then put it into short business expressions. I'm going to call them rules that then can be recontextualized and redeployed. This is my version of, or my abstraction of what people call the the future being just all TikTok. It's not literally that we're all going to be doing short dance videos. It's that TikTok is is an expression of people creating short bits of content and then having those be reconfigured and redistributed. That can be in medicine or clinical practice or in drugs, but it can be in any range of expertise, expertise or knowledge. And what's changed? What's changed and what is changing is the different technologies that are being brought to bear to capture that knowledge so that it can be scalable, so it can be compositional. Yeah, that's what's changing. That's what's going to be changing over the next 10 to 20 years. The more you study that, I think the better off we will be. And I'd say, you know, for my way of thinking about math, you might say the more math, the better. But if I were to choose for my children, I would say I would replace trig and geometry and even calculus, some people would be happy to know, with categorical algebra, category theory and with probability and statistics. So I would replace calculus, which I think is really the math of the 20th century, with something more appropriate to our digital age, which is categorical algebra.Harry Glorikian: I will tell my son because I'm sure he'll be very excited to to if I told him that not calculus, but he's not going to be happy when I say go to this other area, because I think he'd like to get out of it altogether.Eric Daimler: It's easier than calculus. Yeah.Harry Glorikian: So, you know, it was great having you on the show. I feel like we could talk for another hour on all these different aspects. You know, I'm hoping that your company is truly successful and that you help us solve this interoperability problem, which is, I've been I've been talking about it forever. It seems like I feel like, you know, the last 15 or 20 years. And I still worry if we're any closer to solving that problem, but I'm hopeful, and I wish you great success on the launch of your new book. It sounds exciting. I'm going to have to get myself a copy.Eric Daimler: Thank you very much. It's been fun. It's good to be with you.Harry Glorikian: Thank you.Harry Glorikian: That's it for this week's episode. You can find a full transcript of this episode as well as the full archive of episodes of The Harry Glorikian Show and MoneyBall Medicine at our website. Just go to glorikian.com and click on the tab Podcasts.I'd like to thank our listeners for boosting The Harry Glorikian Show into the top three percent of global podcasts.If you want to be sure to get every new episode of the show automatically, be sure to open Apple Podcasts or your favorite podcast player and hit follow or subscribe. Don't forget to leave us a rating and review on Apple Podcasts. And we always love to hear from listeners on Twitter, where you can find me at hglorikian.Thanks for listening, stay healthy, and be sure to tune in two weeks from now for our next interview.