NEJM AI Grand Rounds

Mark Cuban, business magnate and investor, shares his journey from self-taught programmer to successful entrepreneur. He discusses the founding story of his pharmacy benefits company and the potential of AI in healthcare. Cuban also talks about lowering drug prices, AI language models, trust in healthcare, and the future of the US healthcare system.

Dr. Atul Butte, a pioneering informatician, discusses his career, from pediatric endocrinology to trailblazing work with biomedical data. Topics include his entrepreneurial journey, the importance of utilizing electronic health record data, building neural networks in AI, the connection between pediatric endocrinology and informatics, the role of a chief data scientist in understanding human disease, the power of public speaking, the impact of the Bay Dol Act on academic researchers, managing data and infrastructure, and driving AI in medicine.

In this thought-provoking episode, Dr. Ziad Obermeyer delves into the complex issues of bias, safety, and generalizability of medical AI. Dr. Obermeyer emphasizes the importance of machine learning researchers’ task formulation, an often-overlooked yet significant determinant of bias in AI algorithms. Highlighting the dual impact of machine learning, he compares two of his works that demonstrate how AI can either exacerbate or help mitigate health care disparities. Lastly, he discusses the significant challenges encountered in the development of AI models due to siloed and inaccessible data, sharing his own experiences and solutions in tackling this issue. Dr. Obermeyer is the Blue Cross of California Distinguished Professor at the Berkeley School of Public Health, Co-Founder of Nightingale Open Science, and Co-Founder of Dandelion Health. Transcript    

Dr. Marzyeh Ghassemi has been at the forefront of medical machine learning for several years. In this episode, she describes her group’s work and her perspectives on developing and applying machine learning to understand and improve health in ways that are robust, private, and fair. Dr. Ghassemi is an Assistant Professor at MIT in Electrical Engineering and Computer Science and the Institute for Medical Engineering & Science. Transcript

Large language models (LLMs) like ChatGPT have proven highly capable of a broad array of natural language tasks including summarizing text, generating prose, and answering questions. This episode’s two guests, Dr. Alan Karthikesalingam and Vivek Natarajan of Google, describe their team’s recent efforts to adapt and evaluate LLMs for clinical applications. Alan and Vivek took very different paths to becoming leading medical AI researchers and in this episode they also share their educational journeys and perspectives on where the field is headed. Alan is a Senior Staff Clinician Scientist and Research Lead at Google Health and Vivek is a Research Scientist at Google Health AI. Transcript

Dr. Michael Abramoff is a renowned ophthalmologist and medical AI pioneer. In this episode, we explore his groundbreaking work that led to the first FDA-authorized device that does not require a physician, IDx-DR, which detects more than mild diabetic retinopathy from digital images of the eye. Dr. Abramoff also reflects on the challenges of commercialization, AI reimbursement, and the ethical imperatives for AI in health care centered around patient benefit. Dr. Abramoff is the Robert C. Watzke Professor of Ophthalmology and Visual Sciences at the University of Iowa and Founder & Executive Chairman of Digital Diagnostics, an autonomous AI diagnostics company that developed IDx-DR. Transcript

Dr. Peter Lee has shaped computer science from academia, government, and industry. He has chaired a major computer science department, built a new technology office at DARPA, and now serves as Corporate Vice President at Microsoft, where he leads Microsoft Research and its nine worldwide laboratories. In this episode, Peter reveals Microsoft’s interest in health care and the origins of the OpenAI and Microsoft partnership, and he speculates on how large language models like ChatGPT will transform medicine. Transcript

Dr. Lily Peng has driven major medical AI efforts along the long and arduous path from ideation to deployment. From publishing a landmark study in 2016 presenting an AI model to detect diabetic retinopathy in retinal fundus photographs to evaluating deep learning systems in India and Thailand, she has a unique and wide-ranging perspective on both model development and real-world validation. She continues to lead medical AI efforts as a physician-scientist and the Director of Product Management at Verily. Transcript

Dr. Pranav Rajpurkar has been at the forefront of medical AI for his entire career. As a graduate student in computer science at Stanford, he created some of the first AI models for radiology and created a suite of datasets and benchmarks that have been widely used by researchers across the world. Now, as a faculty member at Harvard, his group has continued to push the frontier of medical AI across many different specialties including radiology, pathology, and cardiology. Transcript

Dr. Euan Ashley is a pioneer. In 2010, he led the team that conducted the first clinical interpretation of a human genome, and he holds the record for the world’s fastest genomic diagnosis. He even has a Guinness World Record to prove it. In this wide-ranging discussion, Dr. Ashley shares the stories behind these feats, his experiences applying artificial intelligence to genomics and to cardiology, and his views on whether and how AI will change medicine. Transcript