Podcasts about patients know best

  • 14PODCASTS
  • 17EPISODES
  • 34mAVG DURATION
  • 1MONTHLY NEW EPISODE
  • Apr 22, 2025LATEST

POPULARITY

20172018201920202021202220232024

Related Topics:

university future ceo

Best podcasts about patients know best

Latest podcast episodes about patients know best

UK Health Radio Podcast
117: The Relaxback UK Show with Mike Dilke - Episode 117

UK Health Radio Podcast

Play Episode Listen Later Apr 22, 2025 29:04


Episode 117 - Dr Mohammad Al-Ubaydli started Patients Know Best as a way for patient health information to be available in the right place at the right time. Disclaimer: Please note that all information and content on the UK Health Radio Network, all its radio broadcasts and podcasts are provided by the authors, producers, presenters and companies themselves and is only intended as additional information to your general knowledge. As a service to our listeners/readers our programs/content are for general information and entertainment only.  The UK Health Radio Network does not recommend, endorse, or object to the views, products or topics expressed or discussed by show hosts or their guests, authors and interviewees.  We suggest you always consult with your own professional – personal, medical, financial or legal advisor. So please do not delay or disregard any professional – personal, medical, financial or legal advice received due to something you have heard or read on the UK Health Radio Network.

patients know best
UK Health Radio Podcast
53: HealthTech Hour with Steve Roest - Episode 53

UK Health Radio Podcast

Play Episode Listen Later Apr 15, 2025 55:28


Episode 53 - Mohammad Al-Ubaydli is founder and CEO of Patients Know Best which today has over 4.9 million registered patients and is working with over 100 health providers to release around 26.5 million data points every month. Disclaimer: Please note that all information and content on the UK Health Radio Network, all its radio broadcasts and podcasts are provided by the authors, producers, presenters and companies themselves and is only intended as additional information to your general knowledge. As a service to our listeners/readers our programs/content are for general information and entertainment only.  The UK Health Radio Network does not recommend, endorse, or object to the views, products or topics expressed or discussed by show hosts or their guests, authors and interviewees.  We suggest you always consult with your own professional – personal, medical, financial or legal advisor. So please do not delay or disregard any professional – personal, medical, financial or legal advice received due to something you have heard or read on the UK Health Radio Network.

ceo healthtech roest patients know best
HealthTech Hour
Ep119: Giving patients control of their own patient data creates better health outcomes - Mo, founder of Patients Know Best on his mission to improve global health through patient empowerment

HealthTech Hour

Play Episode Listen Later Apr 11, 2025 58:20


Mo is the inspirational founder and CEO of Patients Know Best which today has over 5 million registered patients and is working with over 100 health providers to release around 26.5 million data points every month.His mission is to give all patients access to their health data because it leads to better health for everyone. This is a fascinating deep-dive into an area that is continually touted as "the future of health" by governments, think tanks and venture capital alike. Mo is a multi-published author and possibly the world's leading expert in patient data.

Digital Health Unplugged
Digital Health Unplugged: Why the NHS is so difficult to sell to

Digital Health Unplugged

Play Episode Listen Later Sep 17, 2024 35:13


Jordan Sollof, reporter at Digital Health News, is joined by Lloyd Price and Mohammad Al-Ubaydli to talk about procurement and why the NHS is so difficult to sell to. From their own experience, Price, a healthtech founder, mergers and acquisitions advisor and non-executive director for various digital health companies, and Al-Ubaydli, founder and chief executive of digital health social enterprise, Patients Know Best, shine a light on the main issues that can make selling to the NHS a challenge. The pair discuss success stories of startups which have successfully sold to the NHS, before assessing whether companies and suppliers need to take more care in ensuring they are pitching the right solution to the right organisation. They give their views on whether the NHS procurement process has become overcomplicated, a point raised in a session at Rewired 2024, and speculate whether the forthcoming Procurement Act (which was originally due to come into force in October 2024, but has been delayed until February 2025) will solve some issues and make it easier for those selling in the health technology sector. Finally, the guests predict what they anticipate will happen in the coming months and years, including whether the NHS will become a simpler system as a whole to sell to or if we will still be having the same conversation about difficulties selling in a few years' time. Guests: Lloyd Price, health tech founder, mergers and acquisitions advisor and non-executive director for various digital health companies Mohammad Al-Ubaydli, founder and chief executive of Patients Know Best  

The Business of Healthcare with Tara Humphrey
#289 Patients Know Best with Mohammad Al-Ubaydli

The Business of Healthcare with Tara Humphrey

Play Episode Listen Later Jan 31, 2024 38:47


Mohammad Al-Ubaydli, CEO and founder of the 'Patients Know Best', a social enterprise and technology platform. It's designed to help health and social care providers bring together patient data, along with the patient's own data, creating one secure Personal Health Record for the patient.  This episode of The Business of Healthcare Podcast is a masterclass in patient empowerment and technological revolution in healthcare. Mohammad highlights how the platform 'Patients Know Best' is not only changing the game for providers but also shapes the mission of giving patients the reins to their health data. Mohammad tells Tara how this shift is transforming care delivery and what's next for the 'Patients Know Best' platform.  Tara and Mohammad cover: Creation of the 'Patients Know Best' app A deep dive into the 'Patients Know Best' platform and what it does Future developments and the use of data Integration with other applications The role of AI in healthcare Visit the Patients Know Best website here & register for free; https://patientsknowbest.com/  Mohammad's LinkedIn profile is here. Work with THC Primary Care I'm Tara Humphrey and I'm the founder of THC Primary Care, a leading healthcare consultancy. I provide project and network management to Primary Care Networks and consulting support to clinical leads. To date, I've worked with 11 Training Hubs and supported over 120 Primary Care Networks and 3 GP Federations.  I understand and appreciate the complexity of healthcare and what it takes to deliver projects across multiple practices. I have over 20 years of project management and business development experience across the private and public sector and have an MBA in Leadership and Management in Healthcare. I'm also published in the London Journal of Primary Care and the author of over 250 blogs. For more weekly insights and advice sign up to my newsletter. Improving the Business of Healthcare – One Episode at a Time Thanks for tuning into this week's episode of the Business of Healthcare Podcast. If you enjoyed this episode, head over to  Apple Podcasts to subscribe, leave your honest review, and share your favourite episodes on social media. Find us on Twitter, Instagram and LinkedIn or visit our website: THC Primary Care. Gob for Good To register your #gobforgood and to join the stem cell registry - please click here to head straight to the website - maybe become a life saver and help make a difference.

Digital Health Section Podcast- Royal Society of Medicine
Personal Health Records- With Mohammad AI-Ubaydli- CEO and Founder of Patients Know Best

Digital Health Section Podcast- Royal Society of Medicine

Play Episode Listen Later Sep 25, 2023 29:12


This episode features a discussion with Mohammad AI-Ubaydli- CEO and Founder of Patients Know Best on personal health records. Key discussion points include - Do patients really know best? - How personal health records are driving clinicians to rethink the way they write their clinical notes - Changes that are needed within clinical training to better prepare the workforce for treating patients using personal health records

Danielle Newnham Podcast
Mohammad Al-Ubaydli: Physician, Founder, One In A Million

Danielle Newnham Podcast

Play Episode Listen Later Jul 6, 2023 48:17


Today's guest is Dr Mohammad Al-Ubaydli – a physician, programmer and founder of Patients Know Best.In this conversation, we talk about Mohammad's upbringing from his family being exiled from Bahrain in the 1970s, to his childhood spent in the Yemen desert, Syria and Beirut during a civil war.On top of that, Mohammad suffers from a one a million genetic immune deficiency called Hyper IgM Syndrome which, had it not been for his mother's astute diligence would have probably cost him his life.A deep love of technology and medicine led Mohammad to study medicine in order to understand the complexity of our bodies but he was destined to start a company in the technology field where he could combine his experience and passion and have real impact.With over 3 million registered users, an integration with the NHS apps and plans for more countries using the Patients Know Best system, Mohammad talks me through how and why we should all have more agency over our healthcare.This is an extremely inspiring and informative episode which I am sure you will enjoy. Mohammad on Twitter / LinkedIn / Patients Know BestDanielle on Twitter @daniellenewnham and  Instagram @daniellenewnham   / Newsletter Books mentioned in this episode:Irrationality: The Enemy WithinSelling The Wheel: Choosing The Best Way To Sell For You, Your Company, Your CustomersChaos: The Amazing Science of the UnpredictableAlso, if you are looking to become a B Corp, Mohammad is happy to answer any questions he can help with over on LinkedIn. 

Physicians Off The Beaten Path
22- Physician-Entrepreneur Series: Mohammad Al-Ubaydli (Patients Know Best)

Physicians Off The Beaten Path

Play Episode Listen Later Apr 20, 2022 41:54


What needs to happen to encourage more entrepreneurship among MDs? What can MDs learn from chaos theory? How can you use your immigrant mentality as a drive to do more, not to take the well-known and secure path? In this episode, we answer all these questions and more with our guest, Mohammad Al-Ubaydli, M.D. Mohammad is founder and CEO of Patients Know Best, a British social enterprise, with an aim of putting patients in control of their own medical records. He trained as a physician at the University of Cambridge; worked as a staff scientist at the National Institutes of Health; and was a management consultant to US hospitals at The Advisory Board Company. Mohammad holds an MD from Cambridge University.

AHSN Network
20: Innovation Exchange - Is technology the key to managing long term conditions?

AHSN Network

Play Episode Listen Later Dec 22, 2020 29:58


Since Covid-19 hit the UK in early 2020, health and care services have digitised at a dramatic pace.  When the crisis is over, a number of questions will need to be answered: for example, was the technology deployed in the most effective way; were downsides addressed; what further changes are needed to achieve full benefits; and how do providers protect the interests of particular groups?    In this podcast, Dr Hasan Chowhan interviews Ben Collins, Project Director at The King’s Fund, to discuss these questions and his research findings published in a recent report: ‘Technology and innovation for long-term health conditions.’   The paper considers four innovation examples from the United Kingdom (UK) and the Nordic countries that use digital technology to support more ambitious transformations of care. One such innovation is Patients Know Best - their CEO Mo Al Ubaydli also joins the podcast to tell us how his company has succeeded, and gives insights into how to move forward and make the changes necessary to improve future care.      Read the King's Fund report here (https://www.kingsfund.org.uk/publications/technology-innovation-long-term-health-conditions)

eGPlearning Podblast
Patients Know Best - an eGPlearning Podblast interview with Mohammad Al-Ulbaydli

eGPlearning Podblast

Play Episode Listen Later May 10, 2019 37:01


Patients Know Best - an eGPlearning Podblast interview with Mohammad Al-Ulbaydli Do you want to know more about sharing information between clinicians and patients?In this episode, we hear from Mohammad Al-Ulbaydli the CEO of Patients Know Best (PKB) - who allow you portable online access to your medical information and more. We cover a variety of aspects including: Why and how he started this company,How this developed into a productThe lessons he learned including working with Great Ormand St hospitalHow PKB works and brings control and safety to patient careHow this works with safeguarding dataHow he came up with the name for PKBHow this can be used by practices and primary care networks from now including the costHow sharing patient data can save money in our health economyHis favourite work based app: Stitcher - listen to eGPlearning on Stitcher here.His favourite non-work app: Scribd - the Netflix of books.How he would spend £100m on health tech with no red tape. Subscribe to or follow the eGPlearning platform for more videos, app reviews and content to support technology-enhanced primary care and learning.

Private Passions
Richard Smith

Private Passions

Play Episode Listen Later Jun 10, 2018 35:03


Dr Richard Smith heads an organisation called Patients Know Best, and having been editor of the British Medical Journal for most of his career, he now enjoys stirring things up in a provocative weekly blog there. Among his targets: the sinister power of drug companies - and the not unrelated tendency of doctors to over-treat illnesses like cancer. When he's not stirring things up at home, Richard Smith is in Bangladesh, working for a charity trying to prevent the terrible human loss caused by infected drinking water. He has also worked as a television doctor and at one point answered readers' letters for Women's Realm. In Private Passions, Richard Smith tells Michael Berkeley about his strong belief that doctors and patients collude to hide the truth about disease and death, and explains why he gives a talk called provocatively: "Death: the Upside". He reveals too how music has sustained him at crisis points in his life. Choices include Bach's cello suites, the Stan Tracey Quartet, Shostakovich, Messiaen, Haydn, Deborah Pritchard, and sacred music by the medieval composer Hermannus Contractus.

15 Minutes With The Doctor: Learn from Healthcare Entrepreneurs and Innovators
17: Creating a Patient-controlled Medical Record with Mohammed from Patients Know Best

15 Minutes With The Doctor: Learn from Healthcare Entrepreneurs and Innovators

Play Episode Listen Later Apr 12, 2018 19:19


In this episode, we welcome Mohammad, founder of Patients Know Best. The platform is a patient-controlled medical record system with numerous features for users, including seeing results, communicating with health professionals, and sharing the medical record with family or friends. Learn about Mohammad’s early journey into creating software, how the company has grown to securing contracts which serve up to 2.3 million patients, and how they have started utilising the benefits of blockchain. What you will learn in this episode: - How the journey to Patients Know Best began? - What is Patients Know Best? - How the process works - Integrating multiple health platforms into a single point of access - How Patients Know Best generates income - Benefits of using Blockchain on PKB platform How the journey to Patients Know Best began? Whilst completing his A-levels, Mohammed read a book called Chaos, which was about nonlinear mathematics. It described chaotic systems like the weather, the earth’s geosphere, the immune system and the economy. It explained how chaos influenced each system. However, there wasn't anything about chaotic systems and how to program the model of the human body in the book. This sparked some interest into software and Mohammed decided to learn about it. “During my medical school summers, I would get a programming job. I wrote software to model the immune system and things like a heart attack. It was really interesting to use programming to help understand healthcare better and to deepen my computer skills.” How the process works When a patient attends the hospital for an appointment, the doctors will inform them that they can have access to their records. They are asked if they want to register and 70-90% of patients do agree. The registration process simply involves an email address and password. From then on, you get access to your data although it depends on which hospitals you’ve visited. “It works on a phone or laptop, as long as you have access to internet connection” The platform offers the ability to share all or certain parts of your information to family members or friends. Some incredible features include adding a Fitbit, connecting a glucose monitor, and you can also message your clinical team. Integrating multiple health platforms into a single point of access “The software is great because patients realise they only have to connect to us and we’ll connect them to everybody else.” In the UK, there are at least 4 main primary care IT systems, 6 main hospital IT system, and now there are over 100 connectable health devices. Once Patients Know Best connects to one of these systems or devices, it starts to work instantly. The PKB platform is upgraded weekly. How Patients Know Best generates income Patients Know Best operates as a software as a service business. There is a subscription fee paid by the health institution - The calculation is based on the number of people cared for by the institution. “As a hospital, once you're a subscriber and looking after patients, you can send unlimited amount of data for your patients with storage.” Benefits of using Blockchain on PKB platform Patients Know Best will be working with Dovetail Labs which won a research grant from SBRI Health Enterprise East, where they have built blockchain software to manage healthcare data – They have used blockchain to move data around from primary and secondary care settings. “Blockchain is a very transparent approach because it keeps a log of every transaction.” Blockchain technology is extremely powerful and it will dominate the healthcare and research industry in coming years according to Mohammad. Learn more about Patients Know Best The best place to learn about PKB is through the website: www.patientsknowbest.com

15 Minutes With The Doctor: Learn from Healthcare Entrepreneurs and Innovators
17: Creating a Patient-controlled Medical Record with Mohammed from Patients Know Best

15 Minutes With The Doctor: Learn from Healthcare Entrepreneurs and Innovators

Play Episode Listen Later Apr 12, 2018 19:19


In this episode, we welcome Mohammad, founder of Patients Know Best. The platform is a patient-controlled medical record system with numerous features for users, including seeing results, communicating with health professionals, and sharing the medical record with family or friends. Learn about Mohammad’s early journey into creating software, how the company has grown to securing contracts which serve up to 2.3 million patients, and how they have started utilising the benefits of blockchain. What you will learn in this episode: - How the journey to Patients Know Best began? - What is Patients Know Best? - How the process works - Integrating multiple health platforms into a single point of access - How Patients Know Best generates income - Benefits of using Blockchain on PKB platform How the journey to Patients Know Best began? Whilst completing his A-levels, Mohammed read a book called Chaos, which was about nonlinear mathematics. It described chaotic systems like the weather, the earth’s geosphere, the immune system and the economy. It explained how chaos influenced each system. However, there wasn't anything about chaotic systems and how to program the model of the human body in the book. This sparked some interest into software and Mohammed decided to learn about it. “During my medical school summers, I would get a programming job. I wrote software to model the immune system and things like a heart attack. It was really interesting to use programming to help understand healthcare better and to deepen my computer skills.” How the process works When a patient attends the hospital for an appointment, the doctors will inform them that they can have access to their records. They are asked if they want to register and 70-90% of patients do agree. The registration process simply involves an email address and password. From then on, you get access to your data although it depends on which hospitals you’ve visited. “It works on a phone or laptop, as long as you have access to internet connection” The platform offers the ability to share all or certain parts of your information to family members or friends. Some incredible features include adding a Fitbit, connecting a glucose monitor, and you can also message your clinical team. Integrating multiple health platforms into a single point of access “The software is great because patients realise they only have to connect to us and we’ll connect them to everybody else.” In the UK, there are at least 4 main primary care IT systems, 6 main hospital IT system, and now there are over 100 connectable health devices. Once Patients Know Best connects to one of these systems or devices, it starts to work instantly. The PKB platform is upgraded weekly. How Patients Know Best generates income Patients Know Best operates as a software as a service business. There is a subscription fee paid by the health institution - The calculation is based on the number of people cared for by the institution. “As a hospital, once you're a subscriber and looking after patients, you can send unlimited amount of data for your patients with storage.” Benefits of using Blockchain on PKB platform Patients Know Best will be working with Dovetail Labs which won a research grant from SBRI Health Enterprise East, where they have built blockchain software to manage healthcare data – They have used blockchain to move data around from primary and secondary care settings. “Blockchain is a very transparent approach because it keeps a log of every transaction.” Blockchain technology is extremely powerful and it will dominate the healthcare and research industry in coming years according to Mohammad. Learn more about Patients Know Best The best place to learn about PKB is through the website: www.patientsknowbest.com

This Much I Know - The Seedcamp Podcast
Seedcamp Sessions: Balderton's Rob Moffat on startup growth engines

This Much I Know - The Seedcamp Podcast

Play Episode Listen Later Mar 7, 2018 16:49


Rob Moffat joined Balderton Capital in 2009 and was promoted to partner in 2015. He is currently a board director or observer with five portfolio companies: Carwow, Wooga, Nutmeg, Prodigy Finance, and Patients Know Best. Prior to joining Balderton, Rob worked for Google in London, as a Manager in the European Strategy and Operations team, and for five years in strategy consulting at Bain. In this Seedcamp Sessions podcast, Rob covers the different growth engines which have proven successful for startups -- from paid marketing for companies like Carwow, who need to be rigorous in how they think about acquisition, through to continuous product innovation for companies like Revolut, and partnerships and business development for startups like Zego. Rob also covers how to navigate VC and strategic partnership relations, and how Balderton is thinking about the evolving Insurtech landscape. Show notes: Carlos Medium: sdca.mp/2entVR3 Seedcamp: www.seedcamp.com Balderton: www.balderton.com Related bio links: Carlos: linkedin.com/in/carloseduardoespinal / twitter.com/cee Rob: linkedin.com/in/robmoff / twitter.com/robmoff

O'Reilly Radar Podcast - O'Reilly Media Podcast
Risto Miikkulainen on evolutionary computation and making robots think for themselves

O'Reilly Radar Podcast - O'Reilly Media Podcast

Play Episode Listen Later Feb 11, 2016 41:41


The O'Reilly Radar Podcast: Evolutionary computation, its applications in deep learning, and how it's inspired by biology.In this week’s episode, David Beyer, principal at Amplify Partners, co-founder of Chart.io, and part of the founding team at Patients Know Best, chats with Risto Miikkulainen, professor of computer science and neuroscience at the University of Texas at Austin. They chat about evolutionary computation, its applications in deep learning, and how it’s inspired by biology. Also note, David Beyer's new free report "The Future of Machine Intelligence" is now available for download.Here are some highlights from their conversation: Finding optimal solutions We talk about evolutionary computation as a way of solving problems, discovering solutions that are optimal or as good as possible. In these complex domains like, maybe, simulated multi-legged robots that are walking in challenging conditions—a slippery slope or a field with obstacles—there are probably many different solutions that will work. If you run the evolution multiple times, you probably will discover some different solutions. There are many paths of constructing that same solution. You have a population and you have some solution components discovered here and there, so there are many different ways for evolution to run and discover roughly the same kind of a walk, where you may be using three legs to move forward and one to push you up the slope if it's a slippery slope. You do (relatively) reliably discover the same solutions, but also, if you run it multiple times, you will discover others. This is also a new direction or recent direction in evolutionary computation—that the standard formulation is that you are running a single run of evolution and you try to, in the end, get the optimum. Everything in the population supports finding that optimum. Biological inspiration Some machine learning is simply statistics. It's not simple, obviously, but it is really based on statistics and it's mathematics-based, but some of the inspiration in evolutionary computation and neural networks and reinforcement learning really comes from biology. It doesn't mean that we are trying to systematically replicate what we see in biology. We take the components we understand, or maybe even misunderstand, but we take the components that make sense and put them together into a computational structure. That's what's happening in evolution, too. Some of the core ideas at the very high level of instruction are the same. In particular, there's selection acting on variation. That's the main principle of evolution in biology, and it's also in computation. If you take a little bit more detailed view, we have a population, and everyone is evaluated, and then we select the best ones, and those are the ones that reproduce the most, and we get a new population that's more likely to be better than the previous population. Modeling biology? Not quite yet. There's also developmental processes that most biological systems adapt and learn during their lifetime as well. In humans, the genes specify, really, a very weak starting point. When a baby is born, there's very little behavior that they can perform, but over time, they interact with the environment and that neural network gets set into a system that actually deals with the world. Yes, there's actually some work in trying to incorporate some of these ideas, but that is very difficult. We are very far from actually saying that we really model biology. OSCAR-6 innovates What got us really hooked in this area was that there are these demonstrations where evolution not only optimizes something that you know pretty well, but also comes up with something that's truly novel, something that you don't anticipate. For us, it was this one application where we were evolving a controller for a robot arm, OSCAR-6. It was six degrees of freedom, but you only needed three to really control it. One of the dimensions is that the robot can turn around its vertical axis, the main axis. The goal is to get the fingers of the robot to a particular location in 3D space that's reachable. It's pretty easy to do. We were working on putting obstacles in the way and accidentally disabled the main motor, the one that turns the robot around its main axis. We didn't know it. We ran evolution anyway, and evolution learned and evolved, found a solution that would get the fingers in the goal, but it took five times longer. We only understood what was going on when we put it on screen and looked at the visualization. What the robot was able to do was that when the target was, say, all the way to the left and it needed to turn around the main axis to get the arm close to it, it couldn't do it because it couldn't turn. Instead, it turned the arm from the elbow or shoulder, the other direction, away from the goal, then swung it back real hard; because of inertia, the whole robot would turn around its main axis, even when there was no motor. This was a big surprise. We caused big problems to the robot. We disabled a big, important component of it, but it still found a solution of dealing with it: utilizing inertia, utilizing the physical simulation to get where it needed to go. This is exactly what you would like in a machine learning system. It innovates. It finds things that you did not think about. If you have a robot stuck in a rock in Mars or it loses a wheel, you'd still like it to complete its mission. Using these techniques, we can figure out ways for it to do so.

O'Reilly Radar Podcast - O'Reilly Media Podcast
Risto Miikkulainen on evolutionary computation and making robots think for themselves

O'Reilly Radar Podcast - O'Reilly Media Podcast

Play Episode Listen Later Feb 11, 2016 41:41


The O'Reilly Radar Podcast: Evolutionary computation, its applications in deep learning, and how it's inspired by biology.In this week’s episode, David Beyer, principal at Amplify Partners, co-founder of Chart.io, and part of the founding team at Patients Know Best, chats with Risto Miikkulainen, professor of computer science and neuroscience at the University of Texas at Austin. They chat about evolutionary computation, its applications in deep learning, and how it’s inspired by biology. Also note, David Beyer's new free report "The Future of Machine Intelligence" is now available for download.Here are some highlights from their conversation: Finding optimal solutions We talk about evolutionary computation as a way of solving problems, discovering solutions that are optimal or as good as possible. In these complex domains like, maybe, simulated multi-legged robots that are walking in challenging conditions—a slippery slope or a field with obstacles—there are probably many different solutions that will work. If you run the evolution multiple times, you probably will discover some different solutions. There are many paths of constructing that same solution. You have a population and you have some solution components discovered here and there, so there are many different ways for evolution to run and discover roughly the same kind of a walk, where you may be using three legs to move forward and one to push you up the slope if it's a slippery slope. You do (relatively) reliably discover the same solutions, but also, if you run it multiple times, you will discover others. This is also a new direction or recent direction in evolutionary computation—that the standard formulation is that you are running a single run of evolution and you try to, in the end, get the optimum. Everything in the population supports finding that optimum. Biological inspiration Some machine learning is simply statistics. It's not simple, obviously, but it is really based on statistics and it's mathematics-based, but some of the inspiration in evolutionary computation and neural networks and reinforcement learning really comes from biology. It doesn't mean that we are trying to systematically replicate what we see in biology. We take the components we understand, or maybe even misunderstand, but we take the components that make sense and put them together into a computational structure. That's what's happening in evolution, too. Some of the core ideas at the very high level of instruction are the same. In particular, there's selection acting on variation. That's the main principle of evolution in biology, and it's also in computation. If you take a little bit more detailed view, we have a population, and everyone is evaluated, and then we select the best ones, and those are the ones that reproduce the most, and we get a new population that's more likely to be better than the previous population. Modeling biology? Not quite yet. There's also developmental processes that most biological systems adapt and learn during their lifetime as well. In humans, the genes specify, really, a very weak starting point. When a baby is born, there's very little behavior that they can perform, but over time, they interact with the environment and that neural network gets set into a system that actually deals with the world. Yes, there's actually some work in trying to incorporate some of these ideas, but that is very difficult. We are very far from actually saying that we really model biology. OSCAR-6 innovates What got us really hooked in this area was that there are these demonstrations where evolution not only optimizes something that you know pretty well, but also comes up with something that's truly novel, something that you don't anticipate. For us, it was this one application where we were evolving a controller for a robot arm, OSCAR-6. It was six degrees of freedom, but you only needed three to really control it. One of the dimensions is that the robot can turn around its vertical axis, the main axis. The goal is to get the fingers of the robot to a particular location in 3D space that's reachable. It's pretty easy to do. We were working on putting obstacles in the way and accidentally disabled the main motor, the one that turns the robot around its main axis. We didn't know it. We ran evolution anyway, and evolution learned and evolved, found a solution that would get the fingers in the goal, but it took five times longer. We only understood what was going on when we put it on screen and looked at the visualization. What the robot was able to do was that when the target was, say, all the way to the left and it needed to turn around the main axis to get the arm close to it, it couldn't do it because it couldn't turn. Instead, it turned the arm from the elbow or shoulder, the other direction, away from the goal, then swung it back real hard; because of inertia, the whole robot would turn around its main axis, even when there was no motor. This was a big surprise. We caused big problems to the robot. We disabled a big, important component of it, but it still found a solution of dealing with it: utilizing inertia, utilizing the physical simulation to get where it needed to go. This is exactly what you would like in a machine learning system. It innovates. It finds things that you did not think about. If you have a robot stuck in a rock in Mars or it loses a wheel, you'd still like it to complete its mission. Using these techniques, we can figure out ways for it to do so.

Healthy Visions
The Patient in Charge?

Healthy Visions

Play Episode Listen Later Mar 31, 2015 13:54


2/5 Most health care is delivered face to face with a highly and expensively qualified practitioner who acts as gatekeeper to any treatment we receive. If we seek advice from our GP, they will generally either prescribe medication, refer us for investigative tests or send us to a specialist consultant who will in turn assess our need for treatment. In the second programme of this Healthy Visions series, Dr Charles Alessi argues that this model of how we access and interact with our health care system will be required to undergo considerable change in the future. Not only do NHS resources need to be saved, but people are becoming increasingly knowledgeable and interested in their health and want to be more involved and in charge of their own care. In the digital age it is now becoming much easier to access and share information about health. Patients Know Best is the world's first patient controlled online medical records system and is based on the premise that patients have the right to, and are best placed to be in control of their own records. By having their own unique profile on a website, patients are able to gain access to their data via a computer or smartphone. Linking together the care teams that treat them, management of any condition is made much easier for all involved. Patients are also becoming more active in their own care as treatment moves away from solely being provided by health care professionals. An illustration of this is the self-care kidney dialysis unit in Harrogate, Yorkshire, the first of its kind in the country, where patients undertake their own dialysis at times that are most convenient for them. This affords them much greater flexibility and can substantially improve their quality of life. Presenter:Dr Charles Alessi Producer:Helena Selby Editor:Andrew Smith.