JAMA+ AI Conversations

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

Why can signals that appear consistent across many studies still reflect shared bias; how do sibling comparisons help recalibrate cumulative evidence; and what AI-enabled approaches can add to large-scale evidence integration? Viktor H. Ahlqvist, PhD, from the Karolinska Institute joins JAMA and JAMA+ AI Associate Editor Yulin Hswen, ScD, MPH, to discuss why automated drug safety surveillance during pregnancy is urgently needed and how AI and computation can strengthen or undermine causal inference. Related Content: AI Drug Safety in Pregnancy

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 ultimately support precision prevention and translational research, while preserving scientific rigor and interpretability. Related Content: AI and the Epidemiology of Complex Disease

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  

AI chatbots have advanced rapidly, incorporating new reasoning architectures that reshape decision-making and medical education. Jonathan Chen, MD, PhD, and Ethan Goh, MD, MS, of Stanford University join JAMA and JAMA+ AI Associate Editor Yulin Hswen, ScD, MPH, to discuss the latest generation of AI models, the importance of evaluating benefits and harms, and sycophancy in AI systems. Related Content: Multiple Reasoning Models and the Future of AI Chatbots AI Chatbots in Clinical Practice Large Language Model Influence on Diagnostic Reasoning

JAMA+ AI Editor in Chief Roy Perlis and Associate Editor Yulin Hswen discuss some of the most cited AI papers in 2025 across the JAMA Network. A little bit of gen AI, some prediction models, and deep learning from videos as well as an increasing awareness of the challenges of real-world deployment. Related Content: AI and Health—The Year in Review

How can AI systems reason safely in the open world of medicine? JAMA+ AI Associate Editor Yulin Hswen, ScD, MPH, talks with Eric Horvitz, MD, PhD, Chief Scientific Officer at Microsoft, about the future of AI in 5 years to 100 years, from neurons to the nebulous, and how we can guide AI to be copilots while maintaining integrity and safety in the clinical arena. Related Content: AI—Days of Future Past

Will AI usher in a new era of rapid drug discovery? In this episode of JAMA+ AI Conversations, Editor in Chief Roy Perlis interviews Ajamete Kaykas, Chief eXploration Officer at Insitro, a biotech company looking to apply AI to develop new therapeutics. Related Content: AI in the Lab—Will It Really Change Drug Discovery?

Derek Angus, MD, MPH, joins JAMA+ AI Editor in Chief Roy Perlis, MD, MSc, to discuss a special communication from JAMA Summit: Artificial Intelligence. Related Content: What the Experts Think About Where AI Is Headed AI, Health, and Health Care Today and Tomorrow

How will 2026 shape the world of AI in health? Editor in Chief Roy Perlis and Associate Editor Yulin Hswen discuss in this special episode marking one year since the launch of JAMA+ AI. Hosted by Roy H. Perlis, MD, MSc and Yulin Hswen, ScD, MPH. Related Content: What Will Next Year Bring for AI in Health? Detection of Epileptogenic Focal Cortical Dysplasia Using Graph Neural Networks Evaluating a Large Language Model in Translating Patient Instructions to Spanish Using a Standardized Framework Public Perception of Physicians Who Use Artificial Intelligence Assessment of Machine Learning to Estimate the Individual Treatment Effect of Corticosteroids in Septic Shock Artificial Intelligence Across the JAMA Network Early Warning Scores With and Without Artificial Intelligence Artificial Intelligence and Radiologist Burnout Complete AI-Enabled Echocardiography Interpretation With Multitask Deep Learning How AI Could Reshape Health Care—Rise in Direct-to-Consumer Models Artificial Intelligence–Enabled Wearable Devices and Nocturnal Scratching in Mild Atopic Dermatitis

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 Patients About Use of AI Tools AI Disclosure and Patient Consent in Health Care

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-Effectiveness of 3D Total-Body Photography?

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-visit asthma symptom monitoring. Related Content: Between-Visit Asthma Symptom Monitoring With a Scalable Digital Intervention Discussing Digital Interventions in Asthma Symptom Monitoring

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 Considerations in Translating AI to Improve Care How AI Could Increase Clinical Trial Enrollment in Adults With Cancer

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 for Parkinsonism

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 on Investment of Enhanced Behavioral Health Services Return on Investment in Digital Mental Health Solutions

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 Learning Diabetic Retinopathy Algorithm in India

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?

Correction: This podcast has been updated to add additional context on the frequency of false positives. Open neural tube defects affect approximately 1 in 1400 births. Daniel Herman, MD, PhD, of the University of Pennsylvania Perelman School of Medicine joins JAMA+ AI Editor in Chief Roy H. Perlis, MD, MSc, to discuss a quality improvement study examining the need to continue to incorporate race in tests that screen for these defects. Related Content: Study Findings Question Value of Including Race in Prenatal Screening for Birth Defects Reassessing the Inclusion of Race in Prenatal Screening for Open Neural Tube Defects

Artificial intelligence (AI) in health care is advancing, despite concerns about how its use may impact health disparities. Dimitri Christakis, MD, MPH, chief health officer at Special Olympics, joins JAMA Associate Editor Yulin Hswen, ScD, MPH, to discuss AI's potential role in improving health care delivery for people with intellectual and developmental disabilities. Related Content: How AI Could Improve Health Care for People With Intellectual and Developmental Disabilities How Artificial Intelligence Can Promote Inclusive Health

A recent study showed AI-assisted screening using a large language model tool reduced time to determine trial eligibility compared with manual methods. Author Alexander J. Blood, MD, MSc, cardiologist at Brigham and Women's Hospital, and Associate Director of the Accelerator for Clinical Transformation Research Group at Harvard Medical School joins JAMA Associate Editor Yulin Hswen, ScD, MPH, to discuss this topic and more. Related Content: Study Finds AI Can Quickly Prescreen Patients for Clinical Trials, Speeding Enrollment Manual vs AI-Assisted Prescreening for Trial Eligibility Using Large Language Models—A Randomized Clinical Trial

In a recent study published in JAMA Psychiatry, researchers reported that a machine learning model was able to stratify risk for subsequent diagnosis of schizophrenia or bipolar disorder among individuals already receiving psychiatric treatment. Coauthor Søren Dinesen Østergaard, PhD, of Aarhus University in Denmark joins JAMA+ AI Editor in Chief Roy H. Perlis, MD, MSc, to discuss. Related Content: Machine Learning Model Shows Promise in Early Detection of Serious Mental Illness Predicting Diagnostic Progression to Schizophrenia or Bipolar Disorder via Machine Learning

AI can play a role in addressing language barriers in health care. In a recent Editorial in JAMA Network Open, Pilar Ortega, MD, MGM, of the University of Illinois College of Medicine, and coauthors emphasized the urgent need for integrating language equity into digital health solutions. Dr Ortega joins JAMA and JAMA+ AI Associate Editor Yulin Hswen, ScD, MPH, to discuss. Related Content: Researcher Proposes New Framework for Language Equity in Health Technology Language Equity in Health Technology for Patients With Non–English Language Preference Challenges to Video Visits for Patients With Non–English Language Preference

Lung ultrasound aids in the diagnosis of patients with dyspnea but requires technical proficiency for image acquisition. Cristiana Baloescu, MD, MPH, of Yale School of Medicine, joins JAMA Associate Editor Yulin Hswen, ScD, MPH, to discuss a new study published in JAMA Cardiology evaluating the ability of AI to guide acquisition of diagnostic-quality lung ultrasound images by trained health care professionals. Related Content: AI-Guided Lung Ultrasounds Could Help Nonexpert Clinicians Acquire "Expert-Level" Images Artificial Intelligence–Guided Lung Ultrasound by Nonexperts

A recent study in JAMA Network Open evaluates the use of machine learning algorithms to assess the management of urinary tract infection (UTI). Author Sanjat Kanjilal, MD, MPH, professor in the Department of Population Medicine at Harvard Medical School and Harvard Pilgrim Healthcare Institute, joins JAMA Associate Editor Yulin Hswen, ScD, MPH, to discuss this topic and more. Related Content: Researchers Use Machine Learning to Put Older Clinical Guidelines to the Test Use of Machine Learning to Assess the Management of Uncomplicated Urinary Tract Infection

Digital health technologies, including patient portals, are widely used by older adults, as described in a recent study published in JAMA Network Open. Author Cornelius James, MD, of the University of Michigan joins JAMA+ AI Editor in Chief Roy H. Perlis, MD, MSc, to discuss the study and how it fits with his own experience in the clinic. Related Content: Study Finds Most Older Adults Use Digital Health Technologies, Plus Some Surprises Use of Digital Health Technologies by Older US Adults

How do patients feel about the quality of AI-generated responses to their messages to clinicians? Author Eleni Linos, MD, DrPH, of Stanford joins JAMA+ AI Editor in Chief Roy H. Perlis, MD, MSc, to discuss her recent study in JAMA Network Open that characterized satisfaction with these messages. Related Content: Study Finds People Prefer AI Over Clinician Responses to Questions in the Electronic Medical Record Perspectives on Artificial Intelligence–Generated Responses to Patient Messages

The burden of responding to clinician inbox messages may be a contributor to burnout. Eden English, MD, of UCHealth joins JAMA+ AI Editor in Chief Roy H. Perlis, MD, MSc, to discuss her recent study published in JAMA Network Open, which examined the use of large language models to reply to patient messages. Related Content: Researchers Tested an AI Tool That Drafts Responses to Patient Messages—Here's What They Found Utility of Artificial Intelligence–Generative Draft Replies to Patient Messages Are Artificial Intelligence–Generated Replies the Answer to the Electronic Health Record Inbox Problem?

With accelerating global adoption of AI, countries are developing ethical AI frameworks to prevent harm to the most vulnerable populations. Maria Villalobos-Quesada, PhD, from the National eHealth Living Lab (NeLL) in the Netherlands and the Observatory of Bioethics and Law of the University of Barcelona, discusses this and more with JAMA+ AI Associate Editor Yulin Hswen, ScD, MPH.  *Author image and affiliations updated February 4, 2025. Related Content: Study Finds Limited Evidence to Support More Than 40 Predictive Machine Learning Algorithms Used in Primary Care Availability of Evidence for Predictive Machine Learning Algorithms in Primary Care The Need for Continuous Evaluation of Artificial Intelligence Prediction Algorithms

American Indian and Alaska Native communities have higher rates of suicide than any other racial or ethnic group in the US. A recent study published in JAMA Network Open describes an AI-based suicide screening tool investigated in an American Indian community. Author Emily Haroz, PhD, of Johns Hopkins Bloomberg School of Public Health, joins JAMA and JAMA+ AI Associate Editor Yulin Hswen, ScD, MPH. Related Content: How AI Could Help Clinicians Identify American Indian Patients at Risk for Suicide Performance of Machine Learning Suicide Risk Models in an American Indian Population

How can hospitals use early warning score tools to risk stratify patients without adding to alarm fatigue? Dana Edelson, MD, MS, of the University of Chicago joins JAMA+ AI Editor in Chief Roy H. Perlis, MD, MSc, to discuss a recent study published in JAMA Network Open that she coauthored, comparing 6 early warning scores designed to recognize clinical deterioration in hospitalized patients. Related Content: Researchers Compared Hospital Early Warning Scores for Clinical Deterioration—Here's What They Learned Early Warning Scores With and Without Artificial Intelligence

Chatbots may have a role in enhancing clinical care, but the best way to apply them remains a work in progress. Jonathen Chen, MD, PhD, and Ethan Goh, MD, MS, of Stanford, join JAMA and JAMA+ AI Associate Editor Yulin Hswen, ScD, MPH, to discuss their randomized clinical trial published in JAMA Network Open investigating the use of chatbots in clinical practice. Related Content: An AI Chatbot Outperformed Physicians and Physicians Plus AI in a Trial—What Does That Mean? Large Language Model Influence on Diagnostic Reasoning

In a recent Viewpoint published in JAMA, Michael Pencina, PhD, of Duke University, argued for a federated registration system for AI tools deployed in health systems. He joins JAMA+ AI Editor in Chief Roy H. Perlis, MD, MSc, to discuss his article, the Coalition for Health AI (CHAI), and more. Related Content: Health Systems Are Struggling to Keep Up With AI—A National Registration System Could Help A Federated Registration System for Artificial Intelligence in Health

In resource-limited settings, an integrated AI tool allows novice users to improve gestational age estimates. Jeffrey Stringer, MD, University of North Carolina, joins JAMA+ AI Editor in Chief Roy H. Perlis, MD, MSc, to discuss "Diagnostic Accuracy of an Integrated AI Tool to Estimate Gestational Age From Blind Ultrasound Sweeps." Related Content: The Low-Cost, Battery-Powered AI-Enabled Ultrasound Device That Could Improve Global Obstetric Care Diagnostic Accuracy of an Integrated AI Tool to Estimate Gestational Age From Blind Ultrasound Sweeps

Effective communication is essential in medicine, yet language barriers can result in suboptimal care. AI holds promise for bridging these gaps, enhancing outcomes, and reducing disparities. Casey Lion, MD, MPH, from the University of Washington School of Medicine, joins JAMA and JAMA+ AI Associate Editor Yulin Hswen, ScD, MPH, to discuss AI as an interpreter in the clinic. Related Content: Researcher Explores Using AI to Overcome Language Barriers With Patients Artificial Intelligence for Language Translation

A recent Special Communication published in JAMA points out that the FDA has already approved nearly 1000 devices using AI. Author Robert M. Califf, MD, commissioner of the US Food and Drug Administration, joins JAMA+ AI Editor in Chief Roy H. Perlis, MD, MSc, to discuss AI regulation. Related Content: FDA Commissioner Robert Califf on Setting Guardrails for AI in Health Care JAMA AI Interview With Robert M. Califf, MD FDA Perspective on the Regulation of Artificial Intelligence in Health Care and Biomedicine

A recent JAMA Cardiology essay argues that medicine is not just a technical endeavor, it's also a moral endeavor, and a robot does not have moral agency. Coauthor Sarah C. Hull, MD, MBE, of Yale School of Medicine, joins JAMA and JAMA+ AI Associate Editor Yulin Hswen, ScD, MPH, to discuss the use of AI in managing decision-making in cardiac care. Related Content: AI Can't Worry About Patients, and a Clinical Ethicist Says That Matters Echoes of Concern—AI and Moral Agency in Medicine

Widespread adoption of AI raises questions about accountability, transparency, and reproducibility. Marcia McNutt, PhD, president of the National Academy of Sciences, joins JAMA Editor in Chief Kirsten Bibbins-Domingo, PhD, MD, MAS, to discuss advancing scientific knowledge in the age of AI. Related Content: National Academies President on How to Use Generative AI Responsibly in Scientific Research

Getting genuinely useful new technologies, from wearables to clinical decision support, into the clinic has proven to be surprisingly challenging. Tanzeem K. Choudhury, PhD, of Cornell Tech joins JAMA+ AI Editor in Chief Roy H. Perlis, MD, MSc, to discuss how to take research into the real world in a way that is scalable and affordable. Related Content: How Health and Technology Sectors Can Collaborate on Better AI-Assisted Wearables

What hard lessons did the US Department of Veterans Affairs (VA) learn in 3 decades of EHR development, and what can it teach us about building better AI in medicine? Stephen Fihn, MD, MPH, of the University of Washington, and formerly a leader in the VA's EHR efforts, joins JAMA+ AI Editor in Chief Roy H. Perlis, MD, MSc, to discuss his experience at the VA building decision support tools and other technology. Related Content: The VA Was an Early Adopter of Artificial Intelligence to Improve Care—Here's What They Learned Hello, World—Introducing JAMA+ AI