Health and Explainable AI Podcast

Karen Colbert, an AI strategist, data scientist, and Lead Math Faculty at Keweenaw Bay Ojibwa Community College, speaks with Pitt HexAI Producer, Brent Phillips about tribal colleges and their mission and vision to revitalize language and culture through education, the indigenization of math and teaching math, computing and data science in the AI age, collaboration tools, data sharing and privacy, explainability and storytelling, project ideation, AI applications, data annotation, and life lessons for students.Karen Colbert is an AI strategist, data scientist, keynote speaker, and a nationally recognized advocate for STEM education. She currently serves as the General Education Department Chair and Lead Math Faculty at Keweenaw Bay Ojibwa Community College, a Tribal College, where she advances data and computational literacy for Indigenous students. Notably, Karen became the first Data Carpentries Instructor and Trainer among all Tribal Colleges, pioneering efforts to bridge the digital divide in higher education. Her passion lies in ensuring that non-traditional, re-entry, and adult learners are not left behind in the AI revolution. Karen is passionate about sharing her insights on “digital sovereignty in the age of AI.” Specifically, she has a deep interest in exploring how AI is reshaping education, research, and opportunity, challenging educators to lead with cultural integrity as technology evolves. She also has an upcoming book 'The Algorithm wasn't Built for Us: Reclaiming the Future of AI, Education, and Culture' available July 4 on Amazon. Visit her website: https://www.karencolbert.com/

Anatea Einhorn, Research Assistant with the University of Pittsburgh's Health and Explainable AI Research Laboratory, speaks with Pitt HexAI podcast host Jordan Gass-Pooré about her work and studies linking artificial intelligence and machine learning, statistics and public health, and about explainable AI, the future of work, and the importance of exchange programs and working abroad. Jordan and Anatea dig into data and data analysis, differences between personal health and public health, and into explainability from a public health perspective.

Janneta Tabakov, Enterprise Growth Lead with Perplexity who focuses on AI in biotech and biopharma speaks with Pitt HexAI Podcast host Jordan Gass-Pooré about her work at Perplexity, a popular and fast-growing new AI-powered answer engine that's redefining search and information discovery in the AI era. Janneta and Jordan discuss how Perplexity (https://www.perplexity.ai/) makes information discovery clear, trustworthy, and accessible, especially in fields like health, medicine, and science and they touch on Janneta's prior work at Arima Genomics, the field of 3D genomics, Hi-C technology and the visualization and mapping of DNA structures.The episode is geared towards introducing students and healthcare professionals to new AI-powered search tools and information discovery processes. The episode highlights how tools like Perplexity are advancing explainable AI in information discovery by making the search and synthesis process transparent, interactive, and easy to understand, helping users not only find answers, but also understand the reasoning and evidence behind them.Janneta and Jordan also discuss the accelerating pace of AI innovation and the dynamic momentum that startups like Perplexity are driving in the industry, setting new benchmarks in healthcare and research.

Yanshan Wang (PhD, FAMIA), Vice Chair for Research and Assistant Professor of Health Informatics at the University of Pittsburgh, speaks with Pitt HexAI podcast host Jordan Gass-Pooré.Yanshan is also the interim Director of Generative AI with the University of Pittsburgh's Computational Pathology and AI Center of Excellence and he leads the Clinical Natural Language Processing and Artificial Intelligence Innovation Laboratory (PittNAIL). Jordan and Yanshan discuss his journey into biomedical and health informatics, his role as Vice Chair of Research, his views on explainable AI, private sector engagement around AI transparency, and on emerging generative AI models and computational resources at Pitt. Yanshan closes the interview with advice for students on setting up research projects.

Pitt HexAI podcast host Jordan Gass-Poore' speaks with three talented young student researchers from Ukraine who participated in the RAI for Ukraine program, a fully remote academic research program launched by NYU in partnership with the Ukrainian Catholic University (UCU) in Lviv, Ukraine. The program conducts cutting-edge collaborative research on a range of responsible AI topics in collaboration with mentors from other U.S. and European universities.Participating students: Yaroslav Klym, Vladyslav Protsenko, and Danylo Reznyk discuss the RAI for Ukraine program, their journeys into the initiative, their experiences working with the AMIIE Lab at Pace University and the HexAI Lab at the University of Pittsburgh, as well as provide insights into their research and forthcoming papers.The RAI for Ukraine program and participating initiatives like Pitt's HexAI lab help provide high-quality research opportunities to students in Ukraine, helping to strengthen research capacity in responsible and explainable AI.

Dr. Xenophon Papademetris, Professor of Biomedical Informatics & Data Science, and Radiology & Biomedical Imaging at Yale School of Medicine speaks with Pitt HexAI guest host Jamie Gramz, Senior Director of Digital Strategy and Business Development with Siemens Healthineers. Jamie and Dr. Papademetris discuss Xenophon's experience in medical image analysis, machine learning, and software development and his involvement in the development of medical image analysis software as well as his involvement in Yale's Certificate Program in Medical Software and Medical AI. Jamie and Dr. Papademetris also discuss Xenophon's textbook “Introduction to Medical Software: Foundations for Digital Health, Devices and Diagnostics” and his Coursera online class “Introduction to Medical Software”, the importance of medical software and AI education as well as the importance of interdisciplinary collaboration in AI for healthcare, and they discuss explainability in AI and clinical communications.

Pitt HexAI podcast host Jordan Gass-Poore´ speaks with Beth Bauer about data and digital knowledge in the AI age, exploring foundational, strategic, and people-focused perspectives. Beth, CEO of PosiROI, Co-Founder and CEO of Communities Connected, VP of The DataJam, and Global Board Co-Chair of Program & Projects for the Healthcare Businesswomen Association's Women in Healthcare Giveback affinity group, is a trailblazer in aligning technology, data, and analytics with people and shared goals. Known for her inspirational public speaking, extensive mentoring, and educational initiatives, Beth has shaped strategies and innovations that empower people through data for over 35 years. In this episode, she and Jordan discuss her insights on data, artificial intelligence, and explainable AI, as well as her work inspiring young people, promoting data fluency, and fostering people-centric, data-informed cultures that drive holistic, intentional outcomes. 

Ashwin Kumar, a PhD candidate at Washington University in St Louis, working on fair resource allocation and explainable AI, speaks with Brent Phillips, Pitt HexAI podcast producer, about the intricacies of fairness in AI systems and about balancing fairness and efficiency in complex systems like ride-sharing and healthcare resource distribution. The discussion dives into AI transparency, human-machine interaction, multi-agent reinforcement learning, and the evolving challenges in ensuring equitable outcomes in AI decision-making. The conversation connects AI's technical workings with real-world ethical concerns.

John Carbone, Adjunct Professor of Applied AI and Applied Data Science at Baylor University speaks with Zoe Menezes, a student at the University of Pittsburgh, and Brent Phillips, Pitt HexAI podcast producer about the future of education in the AI age and how universities are adapting to the emergence of applications like ChatGPT. John elaborates on how universities like Baylor are embracing change, trying new things and and working towards keeping up with advances in technology. John also elaborates on a number of his AI connected academic papers and, on digital security in the AI age and offers advice for students and fellow faculty members on education and acquiring new skills.

Jordan Gass-Poore', Pitt HexAI host, delves into the cutting-edge world of bioinformatics and cancer research with Dr. Aristotelis Tsirigos, a Professor of Medicine and Pathology and the Co-Director of Precision Medicine at NYU Grossman School of Medicine. Dr. Tsirigos shares his journey from computer science and electrical engineering to becoming a leading figure in pathology and bioinformatics. In this episode, they explore the latest advancements in self-supervised deep learning and its transformative impact on cancer diagnosis and management. Dr. Tsirigos discusses his former work at IBM and his current research at NYU Langone Health's Perlmutter Cancer Center, including the innovative study "Mapping the landscape of histomorphological cancer phenotypes using self-supervised learning on unannotated pathology slides." This study, conducted in collaboration with the University of Glasgow, leverages AI to identify distinct cancer phenotypes, offering new insights into cancer subtypes and potential therapeutic strategies. Tune in to learn about the intersection of AI, molecular information, and healthcare, and how these advancements are paving the way for more precise and personalized cancer treatments

Fei Wang, Professor of Population Health Sciences and Emergency Medicine at the Weill Cornell Medical College and Founding Director of the WCM Institute of AI for Digital Health (AIDH) speaks with Pitt HexAI guest host Brent Phillips about Dr. Wang's work at Cornell and about Cornell's new Institute of AI for Digital Health. Dr. Wang and Brent also discuss new and existing data sources for health AI research, the evolution and power of complex machine learning models and their impact on informatics and computational health fields, education in the AI age and about explainable AI and advice for private sector companies interested in collaborating with academic institutions. 

Adolph J. Yates Jr., MD, Chief of Orthopedics at the University of Pittsburgh Medical Center Shadyside, speaks with Pitt HexAI guest host Jamie Gramz, Senior Director of Digital Strategy and Business Development with Siemens Healthineers, about Dr. Yate's work specializing in hip and knee replacement as well as knee arthroscopy and his work as a professor and vice chairman for quality management within the UPMC's Department of Orthopedic Surgery. Jamie and Dr. Yates discuss in detail artificial intelligence and the future of orthopedics, how AI and machine learning are being used to support hip and knee replacements, the availability and adoption of machine learning models, collaboration between universities and hospitals around applications of AI and about Dr. Yates views on explainable AI.

Elizabeth Skidmore, a Professor of Occupational Therapy at the University of Pittsburgh and Associate Dean for Research at Pitt's School of Health and Rehabilitation Sciences, speaks with Pitt HexAI podcast host Jordan Gass-Pooré about Beth's work as an occupational therapist and rehabilitation scientist with expertise in neurological rehabilitation. Beth and Jordan discuss rehabilitation sciences, intervention program design, program implementation, fidelity, applications of artificial intelligence and the training of occupational therapists in the AI age.

Dr. Sarah Wheeler, Associate Professor of Pathology at the University of Pittsburgh, speaks with Pitt HexAI guest host Jamie Gramz, Senior Director of Digital Strategy and Business Development with Siemens Healthineers. Sarah and Jamie discuss Sarah's work and expertise in clinical pathology and laboratory medicine and about the use of artificial intelligence for clinical diagnosis, robotics and automation, explainable and trustworthy AI, lab developed testing and the future of laboratory medicine.

Dr. Dana Tudorascu, Associate Professor of Psychiatry and Biostatistics at the University of Pittsburgh speaks with Pitt HexAI guest host Jamie Gramz, Senior Director of Digital Strategy and Business Development with Siemens Healthineers. Jamie and Dr. Tudorascu discuss how neuroimaging statistics and artificial intelligence are being used in the fight against neurodegenerative diseases like Alzheimers. Dr. Tudorascu is recognized for her expertise in neuroimaging data analysis and imaging techniques and is currently conducting research in key areas including improving brain tissue classification, imaging data harmonization and reproducibility of neuroimaging studies on neurodegenerative diseases. Jamie and Dr. Tudorascu touch on the importance of collaborating across disciplines like psychiatry, neurology and radiology, training others in biostatistical methods and study design and the roles they play in clinical research, multi-modal imaging studies, data harmonization across modalities, applications of artificial intelligence and machine learning in research, and on explainable AI and trustworthy AI in healthcare.

Dr. Hooman Rashidi founding director of Cleveland Clinic's Pathology and Laboratory Medicine Institute's Center for Artificial Intelligence and Data Science and vice chair of technology innovation and computational pathology speaks with Pitt HexAI guest host Jamie Gramz, Senior Director of Digital Strategy and Business Development with Siemens Healthineers. Jamie and Dr. Rashidi, who will soon be joining the University of Pittsburgh as Associate Dean for Artificial Intelligence in Medicine and as a professor of pathology and executive vice chair for computational pathology, and founding executive director of the Computational Pathology and AI Center of Excellence (CPACE), discuss Dr. Rashidi's career and interests in medicine, healthcare and artificial intelligence, the role pathology plays in medicine, digital pathology and AI integration, synthetic data, explainable AI, large language models and how research centers are approaching experimenting with generative AI, and about AI education and curriculum development.

Morgan Cheatham, a medical student and Vice President at Bessemer Venture Partners, speaks with Pitt HexAI host Jordan Gass-Pooré about his background, interests in healthcare and life sciences, and his venture capital work investing at the intersection of computation and bimedicine. Jordan and Morgan discuss in detail AI in healthcare and medicine from a venture capital perspective, the types of next-generation biotech companies and cutting-edge technologies that Bessemer is following, imaging, diagnostics and the science and data behind computational healthcare, and how university labs can collaborate with companies and venture capital firms.

William Hersh, MD, a Professor in the Department of Medical Informatics & Clinical Epidemiology in the School of Medicine at Oregon Health & Science University in Portland, Oregon, speaks with Pitt HexAI podcast host Jordan Gass-Poore' about his background and work, the field of biomedical informatics, his books and writing on health informatics, explainable AI and on being an educator in the AI age.

Shashank Manjunath, a PhD student and researcher with the Dr. Aarti Sathyanarayana's Sath Lab at Northeastern University, speaks with Pitt HexAI guest host Zoe Menezes about biomedical signal processing, applied machine learning, data sources, noise reduction, explainable AI and on Shashank's workflow, favorite resources and views on emerging generative AI powered tools geared for researchers.

Vivek Nallur, a Lecturer and Assistant Professor of Computer Science at University College Dublin speaks with Pitt HexAI podcast producer Brent Phillips about Vivek's work around AI Ethics. Vivek is particularly interested in ethics, AI governance and explainable AI and in questions around AI ethics relevant to autonomous machines. The interview focuses to a large degree on the subject of family caregiving and "Ethical Challenges for Elder-care Robots". Vivek provides a fresh perspective on AI ethics and raises important concerns relevant to applications of AI powered autonomous machines.

Natalia Díaz Rodríguez, an Assistant Professor focusing on trustworthy AI and responsible AI systems at the University of Granada, Spain and a researcher at DaSCI (Andalusian Data Science and Computational Intelligence Institute), speaks with Pitt HexAI's podcast host Jordan Gass-Poore' about her work and thoughts on explainable AI. Natalia graduated from University of Granada (Spain) in 2010 and got her double PhD from Abo Akademi (Finland) and University of Granada in 2015 on symbolic Artificial Intelligence. She was Asst. Prof. of Artificial Intelligence at the Autonomous Systems and Robotics Lab at ENSTA Paris, Institute Polytechnique de Paris, and INRIA Flowers team on developmental robotics. Her background is on knowledge representation, reasoning and machine learning. Her current interests include deep, reinforcement and unsupervised learning, open-ended learning, continual/lifelong learning, (state) representation learning, neural-symbolic computation, computer vision, autonomous systems, explainable AI, and AI for social good. She has worked on R&D at CERN (Switzerland), Philips Research (Netherlands), University of California Santa Cruz, and in industry in Silicon Valley. 

Annika Schoene, a Research Scientist with Northeastern University specializing in natural language processing for mental health, speaks with Mythili Tirumalasetty with the University of Pittsburgh's Health and Explainable AI Research Laboratory about her work, graph neural networks, applications of deep learning relevant to mental health, classification of risk and pain, responsible AI, explainable AI and other subjects.

William Hsu is a Professor of Radiological Sciences, Bioinformatics, and Bioengineering at the University of California, Los Angeles. He is a biomedical informatician focused on maximizing the utility of multimodal data to detect and treat cancers earlier. His lab harnesses artificial intelligence/machine learning techniques to integrate and transform multimodal data into actionable knowledge. He serves as principal investigator on grants from the National Institutes of Health, National Science Foundation, Agency for Healthcare Research and Quality, and the V Foundation. He is a deputy editor of Radiology: Artificial Intelligence. Pitt HexAI's podcast Jordan Gass-Poore' speaks with William about his career and interests, his work at UCLA, emerging applications of AI in radiology, advances in the field, explainable AI and interpretability, bioengineering and other subjects. For students interested in learning about imaging informatics training at UCLA, they can head over to https://mii.ucla.edu/training/ and https://mii.ucla.edu/applying-to-mii/.

Jason Fries is a research scientist with the Shah Lab at Stanford University. In this episode Jason speaks with Pitt HexAI's podcast host Jordan Gass-Poore' about his early interests in computational pathology and his current work at Stanford and interests in foundational models and data-centric AI. Jordan and Jason also discuss lab research papers, explainable AI, the DC-Check initiative and the lab's unique vantage point being based in the heart of Silicon Valley.

Sriraam Natarajan is a Professor of Computer Science and Director of the Center for Machine Learning at The University of Texas at Dallas. In this episode Dr. Natarajan speaks with Pitt HexAI's podcast host Jordan Gass-Poore' about his background and interests in artificial intelligence and machine learning with a focus on healthcare and biomedical applications. Sriraam and Jordan discuss work being carried out at the University of Texas, advice Dr. Natarajan commonly offers students, his being chosen to chair the Association for the Advancement of Artificial Intelligence's upcoming AAAI-24 conference and his views on explainable AI.

Peter Shen is Vice President of Digital and Automation at Siemens Healthineers and an industry expert on medical imaging and artificial intelligence. In this episode Peter speaks with Jamie Gramz about vivo and in vitro diagnostic testing, the evolution of medical imaging and how X-ray, computed tomography and magnetic resonance imaging technologies work; real-world use cases of how AI is being used in healthcare today; the impact data quality has on enabling trustworthy AI, generalization and avoiding bias; the importance of integrating AI within workflows; the need for explainable AI and transparency through performance metrics; and the importance of close collaboration between industry, academia and providers to enable the evolution from acceptance to early adoption to routine use within the delivery of patient care.

Claudia von Vacano, the Executive Director of the D-Lab and the Digital Humanities at the University of California, Berkeley, speaks with Mythili Tirumalasetty about Berkeley's new, forward looking College of Computing, Data Science and Society and about the D-Lab, it's mission and its training initiatives supporting research in data intensive social sciences. Mythili and Claudia touch on Berkeley's unique culture and how the D-Lab is keeping pace with explosive growth around generative AI and helping ensure researchers can overcome technical barriers to accelerate and improve their research projects leveraging artificial intelligence and machine learning including in the fields of health informatics and explainable AI.

Leah Reid, MD, a board-certified internal medicine physician with clinical informatics experience, who is an online Master of Science in Health Informatics (MSHI) graduate student at the University of Pittsburgh, speaks with Pitt HexAI Lab's Mythili Tirumalasetty about studying health informatics and her interests in applying AI in hospital settings. The interview brings the two students together to talk about their backgrounds and interests in health informatics and applications of artificial intelligence.

Gaurav Kaushik on launching ScienceIO and making healthcare data useful and accessible in the AI age. Jen Bees, Pitt HexAI's Audio Engineer guest hosts a special interview giving students an opportunity to get to know ScienceIO, a cutting-edge health informatics startup. Gaurav Kaushik, President and Co-founder of ScienceIO, discusses his journey from academia to the private sector, offers advice to students on launching their own startups and shares valuable insight on generative AI, data sharing, medical ontologies, explainable AI and other subjects of interest to students pursuing careers linking artificial intelligence and healthcare. The Pitt HexAI podcast series is produced by the University of Pittsburgh's Health and Explainable AI Research Laboratory headed by Ahmad P. Tafti. The series is hosted by Mia Kossiavelou and co-produced by Brent Phillips and Mythili Tirumalasetty with engineering by Jen Bees and music by Music Vine/Sky Gienger.

Dr. Isaac Kohane on the impact of generative AI on health and biomedical informatics. Isaac Kohane, MD, PhD - Professor of Biomedical Informatics and Chair of the Department of Biomedical Informatics, Harvard Medical School discusses the impact of generative AI on the advancing fields of health and biomedical informatics, his book: “The AI Revolution in Medicine: GPT-4 and Beyond” and his new role as Editor-in-Chief of NEJM AI. Dr. Kohane touches on explainable AI, the importance of data sharing and the future of education in the ChatGPT age. Closing the interview, Dr. Kohane graciously offers valuable advice and encouragement to students pursuing fields linking artificial intelligence, health and medicine. The Pitt HexAI podcast series is produced by the University of Pittsburgh's Health and Explainable AI Research Laboratory headed by Ahmad P. Tafti. The series is hosted by Mia Kossiavelou and co-produced by Brent Phillips and Mythili Tirumalasetty with engineering by Jen Bees and music by Music Vine/Sky Gienger.

Davina Zamanzadeh, a PhD student studying computer science at UCLA speaks with Pitt HexAI Lab's Mythili Tirumalasetty about clinical applications of machine learning and Davina's work around imputation and deep learning. The interview brings the two students together to talk about their backgrounds, research and interests in health informatics, applications of artificial intelligence and the fields of health and medicine.

Adam Yala, Assistant Professor of Computational Precision Health with UC Berkeley-UCSF's new joint program in Computational Precision Health talks about precision medicine applied to cancer screening and treatment, explainable AI, access to datasets and the future of health informatics. “Precision medicine leverages advanced computing tools to collect, connect and apply vast amounts of scientific research data and information about our health, from the basic molecular understanding of disease to clinical, environmental, psychosocial and mobile lifestyle data, to understand why individuals respond differently to treatments and help guide more precise and predictive medicine and health worldwide.”(https://precisionmedicine.ucsf.edu/about) The Pitt HexAI podcast series is produced by the University of Pittsburgh's Health and Explainable AI Research Laboratory, hosted by Mia Kossiavelou and co-produced by Brent Phillips and Mythili Tirumalasetty with engineering by Jen Bees and music by Music Vine/Sky Gienger.