Discover the future of medicine with JAMA+ AI Conversations. This collection of interviews with clinicians, researchers, and AI experts explores how AI is impacting medicine – from clinical practice to training and research. Join us to uncover what lies ahead at the intersection of AI and medicine.
Don't just listen to podcasts. Learn from them with transcripts, summaries, and chapters for every episode. Skim, search, and bookmark insights. Learn more
Every patient has a story, but in modern health care that story is buried across thousands of notes, lab results, and fragmented records. Nigam H. Shah, MBBS, PhD, of Stanford University Department of Medicine joins JAMA Associate Editor Yulin Hswen, ScD, MPH, to explore how researchers are building AI systems that can read and understand a patient's full medical history in seconds. Related Content: Chatting With AI and the Electronic Health Record...
Join JAMA+ AI Associate Editor Yulin Hswen, ScD, MPH, for a conversation about the practical implementation of trustworthy clinical AI. Guests Emily Tat, MD, and Peter Brodeur, MD, discuss ARISE, a research network focused on the real-world effects of AI on clinical care. Related Content: Designing Trustworthy Clinical AI...
As artificial intelligence increasingly shapes population health decisions, evidence and accuracy matter. In this episode of JAMA+ AI Conversations, Associate Editor Yulin Hswen, ScD, MPH, speaks with Sandro Galea, MD, MPH, DrPH, Editor of JAMA Health Forum, about how AI is entering health policy, when it is ready for use, and what rigorous, policy-focused AI research is most needed. Related Content: AI at the Policy Table...
Dr. Viktor Ahlqvist discusses the challenges of determining drug safety in pregnancy, highlighting how traditional observational studies are time-consuming and pregnant individuals are often excluded from trials. The conversation focuses on leveraging AI and computational approaches to automate drug safety surveillance, emphasizing the importance of causal validation to avoid confounding. They also explore the power of sibling comparisons and the long-term vision of personalized medicine in pregnancy, including ongoing research to integrate high-resolution clinical data.
How might AI amplify epidemiological insight into neurodegenerative and systemic disease? JAMA+ AI Associate Editor Yulin Hswen, ScD, MPH, speaks with Fang Fang, MD, PhD, professor at Karolinska Institutet and head of the Integrative Epidemiology group. Drawing on Fang Fang's work in ALS, Parkinson disease, dementia, energy metabolism, immune modulation, and gut microbiome interactions, their conversation probes how AI methods might help map disease trajectories, identify prognostic markers, and...
What are the safety, evidence standards, and transparency needed for AI chatbots used in mental health contexts, particularly for young people. John Torous, MD, MBI, JAMA Psychiatry Author Interviews podcast host, joins JAMA+ AI Associate Editor Yulin Hswen, ScD, to discuss risks, data protections, and the clinical safeguards required to ensure responsible use. Related Content: AI Chatbots and Youth Mental Health...
Dr Robert Wachter, chair of the Department of Medicine at UC San Francisco, speaks with JAMA+ AI Editor in Chief Roy Perlis about his new book, "A Giant Leap." Their discussion addresses multiple potential impacts of AI in medicine in terms of clinical practice but also training the next generation of clinicians. Related Content: Leaping Forward Into…What?—An Interview With Robert M. Wachter...
In this episode, JAMA+ AI Associate Editor Yulin Hswen, ScD, MPH, speaks with David Wu, MD, PhD, and Adam Rodman, MD, MPH, about what safe clinical use of LLMs requires. Drawing on the framework of Do No Harm, they examine failure modes, limits of accuracy-based evaluation, clinician AI interaction, and safeguards needed as medical AI moves into patient care. Related Content: From AI Bench to AI Bedside...
In this episode of JAMA+ AI Conversations, Editor in Chief Roy Perlis and Associate Editor Yulin Hswen debate recent articles highlighted in JAMA+ AI, including work on patient messaging and suicide screening, plus a call for more critical thinking in medicine. Related Content: Stumbling Toward AI in the Clinic...
A large language model (LLM) details the history of 2 early chatbots, ELIZA and PARRY, in conversation with JAMA+ AI Editor in Chief Roy Perlis. This podcast was recorded using OpenAI's ChatGPT in voice mode, via web interface, running on GPT-4o. Related Content: What Can 50-Year-Old Chatbots Teach Us About Clinical Applications of AI?...
Retinal images are becoming powerful windows into human health. Cecilia Lee, MD, MS, joins JAMA and JAMA+ AI Associate Editor Yulin Hswen to explore how AI-enhanced imaging reveals early disease signals, leverages large datasets, and shifts clinical practice in ophthalmology. Related Content: Insights From the Eye With AI...
This episode explores the rapid evolution of AI chatbots, from early models outperforming physicians in diagnostic reasoning to current "multiple reasoning models" that engage in self-dialogue for complex tasks. Guests discuss the paradox where increasingly capable AI might lead to greater overlooked harms due to automation bias and sycophancy. The conversation emphasizes the urgent need for intentional workflow design, robust physician training, and dedicated research to quantify AI's potential downsides, ensuring healthcare values, not just tech, drive its integration.
JAMA+ AI editors review the most cited AI papers of 2025, starting with the rapid but often unevaluated adoption of generative AI in hospitals, which raises concerns about safety and vendor dominance. They also delve into research on large language models for discharge summaries, predictive AI for psychiatric diagnoses, and global efforts in responsible AI governance. Finally, the discussion highlights innovative uses of AI in image-based diagnostics and for streamlining clinical trial recruitment, emphasizing the ongoing challenge of real-world deployment and the critical need for rigorous evaluation.
Dr. Eric Horvitz, Chief Scientific Officer at Microsoft, reflects on his decades-long journey in artificial intelligence, from early neurobiology to today's transformative generative models like GPT-4. He explores both the immense promise of AI to solve humanity's greatest challenges, particularly in medicine, and the profound "rough edges" including the spread of disinformation, threats to biosecurity, and the impact on human cognition and agency. Horvitz emphasizes the critical need for developing robust safeguards, ensuring scientific integrity, and addressing the long-term societal and psychological implications as AI becomes increasingly integrated into our lives.
This episode explores Insitro's innovative approach to drug discovery using AI and machine learning. Ajamete Kaykas details their Clinimel, Celamel, and ChemML platforms, highlighting the critical role of integrating data from the ground up and fostering interdisciplinary teams. The discussion also covers the challenges of balancing public versus proprietary data generation, managing false positives in drug pipelines, and the evolving role of AI as an enabler rather than a replacement for human scientists in the long journey of therapeutic development.
Roy Perlis and Derek Angus delve into the JAMA Summit Report on Artificial Intelligence, questioning how to properly judge AI effectiveness in healthcare. They discuss the paradox of well-evaluated AI being less adopted than rapidly deployed, administrative AI tools like ambient scribes, which often bypass medical device regulations despite having clinical impacts. The conversation also covers the challenges of classifying AI tools, the current misalignment of incentives for rigorous evaluation, and a vision for AI's future in "live edge decision support" that facilitates continuous learning within healthcare.
This special anniversary episode of JAMA+ AI Conversations reflects on the past year's significant developments and future outlook for AI in healthcare. Editors Roy Perlis and Yulin Hswen discuss innovative studies, from AI detecting missed brain lesions and optimizing septic shock treatment to translating patient instructions. They also delve into critical challenges such as physician burnout, maintaining public trust in AI, the rise of direct-to-consumer models, and the urgent need for more robust, real-world empirical research.
How is Google Search evolving with AI and how do we ensure that language models maintain safety? JAMA+ AI Editor in Chief Roy Perlis, MD, talks with Michael Howell, MD, chief health officer at Google, about how he aims to balance innovation and safety in AI-driven medicine, building on his own work in hospital-based quality and safety. Related Content: "15% of Searches Have Never Been Typed Before" Three Epochs of Artificial Intelligence in Health Care...
In this special edition of JAMA+ AI Conversations, editor in chief Roy Perlis is joined by Linda Brubaker, editor in chief of JAMA+ Women's Health and deputy editor at JAMA. They speak with Linda Moy, inaugural vice chair of AI for the NYU Department of Radiology and former editor of Radiology, about the opportunities and risks of applying AI in medical imaging. Will these new tools be a net positive for women's health? Related Content: The Promise and Challenge of AI for Women's Health...
Michelle Mello, JD, PhD, MPhil, professor of law and health policy at Stanford University, joins JAMA+ AI Editor in Chief Roy Perlis, MD, MSc, to discuss her recently published JAMA Perspective that lays out a framework for when and how health care organizations should disclose AI use to patients. Dr Mello shares insights on the importance of patient trust and surveys that suggest many patients currently mistrust the use of AI in their care. Related Content: Ethical Obligations to Inform Patient...
In this episode of JAMA+ AI Conversations, Microsoft CMO David Rhew, MD, discusses his journey from clinical practice to technology leadership, rapid progress in AI, its potential impacts on health care, and the challenges and opportunities that lie ahead for clinicians and researchers. Related Content: Changing Opinions About AI in Health Care...
In this follow-up to a 2017 interview with JAMA Medical News, the University of Southern California's Maja Matarić, PhD, the computer scientist who pioneered the field of socially assistive robotics, discusses how artificial intelligence is advancing the field in areas ranging from autism to physical rehabilitation to anxiety and depression. Related Content: Social Robots That Help Support People's Health Are Getting a Boost From AI Socially Assistive Robots...
3D total-body photography is used to detect lesions and melanoma in patients at high risk of developing skin cancer. The cost-effectiveness of this technology was examined in a recent study published in JAMA Dermatology. Roy Perlis, Editor in Chief of JAMA+ AI, joins economist Daniel Lindsay, PhD, to discuss the clinical and economic outcomes of this recent study. Related Content: Cost-Effectiveness Analysis of 3D Total-Body Photography for People at High Risk of Melanoma Can AI Improve the Cost...
Despite recommendations from health care professionals, most patients with asthma do not track their symptoms, leaving limited data to help them discuss care options with their clinicians. JAMA Associate Editor Yulin Hswen, ScD, MPH, spoke with Robert S. Rudin, PhD, a senior information scientist at RAND, and a professor of policy analysis at the Pardee RAND Graduate School, about a randomized clinical trial published in JAMA Network Open examining the potential benefits of using AI for between-...
The Dana-Farber Cancer Institute (DFCI)'s MatchMiner tool was developed to increase historically low clinical trial enrollment rates in adults with cancer. Roy Perlis, MD, MSc, Editor in Chief of JAMA+ AI, spoke with Kenneth Kehl, MD, MPH, about his recent study published in JAMA Network Open evaluating the AI tool's ability to fulfill its purpose through genome sequencing. Related Content: Clinical Trial Notifications Triggered by Artificial Intelligence–Detected Cancer Progression Consideratio...
Delaying diagnosis of parkinsonism can mean delaying care. In a study recently published in JAMA Neurology, David Vaillancourt, PhD, and colleagues tested the ability of an AI model to differentiate between Parkinson disease and other neurodegenerative disorders when paired with MRI. He joins JAMA and JAMA+ AI Associate Editor Yulin Hswen, ScD, MPH to discuss. Related Content: A Large Proportion of Parkinson Disease Diagnoses Are Wrong—Here's How AI Could Help Automated Imaging Differentiation f...
Employer-sponsored digital health solutions help patients with behavioral health conditions increase workplace productivity. Yulin Hswen, ScD, MPH, Associate Editor of JAMA+ AI, spoke with Molly Candon, PhD, and Adam Chekroud, PhD, about their recent work published in JAMA Network Open evaluating the financial return on investment for companies participating in these AI health care programs. Related Content: Employer-Sponsored Digital Health Platforms for Mental Wellness—A Good Investment Return...
Susan Athey, PhD, of Standford University joins JAMA+ AI Editor in Chief Roy H. Perlis, MD, MSc, to discuss her research on machine learning to target behavioral nudges for college students and their potential implications for health care. Related Content: How an Economist's Application of Machine Learning to Target Nudges Applies to Precision Medicine...
Diabetic retinopathy remains a leading cause of preventable blindness worldwide, and AI may facilitate screening, if such models continue to perform well when they are deployed in the real world. Coauthors Arthur Brant, MD, of Stanford University, and Sunny Virmani, MS, of Google join JAMA+ AI Editor in Chief Roy H. Perlis, MD, MSc, to discuss a new study published in JAMA Network Open. Related Content: Diabetic Retinopathy Is Massively Underscreened—an AI System Could Help Performance of a Deep...
A recent study published in JAMA Health Forum suggests that institutions may be able to deploy custom open-source large language models (LLMs) that run locally without sacrificing data privacy or flexibility. Coauthors Thomas A. Buckley, BS, and Arjun K. Manrai, PhD, from the Department of Biomedical Informatics at Harvard Medical School join JAMA+ AI Editor in Chief Roy H. Perlis, MD, MSc, to discuss. Related Content: Can Open-Source AI Models Diagnose Complex Cases as Well as GPT-4?...
