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 https://jamanetwork.com/journals/jama/fullarticle/10.1001/jama.2025.22603?utm_campaign=podcasts&utm_medium=social&utm_source=youtube&utm_content=public Podcast was originally published on February 26, 2026. https://edhub.ama-assn.org/jn-learning/audio-player/10.1001/jama.2025.21541?utm_campaign=podcasts&utm_medium=social&utm_source=youtube&utm_content=public --------------------------------------------------------------------------------- Follow JAMA+ AI Conversations on: Youtube: https://www.youtube.com/playlist?list=PL4VOPuLXRs1cPr-5oaaoFK4LCp8VCSrMQ Apple Podcasts: https://podcasts.apple.com/us/podcast/jama-ai-conversations/id1772163310 Spotify: https://open.spotify.com/show/4pTdqjmuLI6bo3PKISajb7 Pocket Casts: https://pca.st/qq5h08zu Your podcast app of choice: https://pod.link/1772163310 Website: https://jamanetwork.com/channels/ai/pages/podcast --------------------------------------------------------------------------------- For more from JAMA • https://www.jama.com • https://www.facebook.com/JAMAJournal • https://www.twitter.com/JAMA_Current • https://www.linkedin.com/company/jamanetwork Follow the JAMA Network • https://www.jamanetwork.com • http://www.jamanetworkaudio.com • https://www.facebook.com/JAMANetwork • https://www.twitter.com/JAMANetwork • https://www.instagram.com/JAMANetwork • https://www.pinterest.com/JAMANetwork

- Stanford Medicine Grand Rounds 2025-12-10

With Jonathan Chen, MD, PhD In this session, learners will explore the transformative impact of AI technologies on healthcare and medical education, including the rapid advancements in AI's diagnostic capabilities and its implications for traditional medical knowledge testing. Dr. Jonathan Chen will challenge participants to consider the evolving role of human doctors in light of AI's growing proficiency, particularly in areas such as empathy and communication, while also addressing the ethical and practical challenges posed by these technologies. The session will encourage critical reflection on what it means to be a doctor in an era increasingly influenced by AI.

AI in Medicine: Pitfalls and Potential Frontiers in Medicine 2024 Pandora’s box has opened in the form of publicly available generative AI systems—where human versus generated content can no longer be distinguished reliably. How is this new capability reshaping medicine? With a global scarcity of medical providers pitted against the unlimited demand of people in need, AI’s potential to democratize health care knowledge and access is desperately needed. But is it safe? Dr. Chen, part of a new breed of physician-scientist dually trained in medicine and computer science, will illuminate the unique opportunities and pitfalls of AI in medicine and help distinguish reality from fantasy. Jonathan Chen, MD, PhD Assistant Professor of Medicine, Biomedical Informatics Research and Hospital Medicine Faculty, Clinical Excellence Research Center Part of Frontiers in Medicine, Stanford Medicine's premier annual event that showcases pioneering breakthroughs in the most promising fields in biosciences and medicine presented by world-class Stanford faculty. Please visit frontiersinmedicine.stanford.edu to learn more.

Keynote presentations at the AI in Healthcare and Physician Executive Forums at HIMSS 2024.

Bio: Jonathan H Chen MD, PhD is a physician-scientist with professional software development experience and graduate training in computer science. He continues to practice Internal Medicine for the concrete rewards of caring for real people and to inspire his research group to empower individuals with the collective experience of the many, combining human and artificial intelligence approaches to medicine that will deliver better care than either can do alone. He has published influential work in venues including the New England Journal of Medicine, JAMA, JAMA Internal Medicine, and the Journal of the American Medical Informatics Association, with research awards and recognition from the NIH Big Data 2 Knowledge initiative, National Library of Medicine, American Medical Informatics Association, Yearbook of Medical Informatics, and American College of Physicians, among others. Dr. Chen has won multiple best student presentation awards during his training, continues to give invited presentations at national conferences in front of hundreds of scientists, trainees, and physicians, and currently hosts the Stanford Biomedical Informatics Research weekly colloquia series. Outside his day job, Dr. Chen won 1st Place in the 2022 International Brotherhood of Magician's Ring 216 Close-Up Magic Competition. Abstract: People fear public speaking more than death, even when communication and presentation skills are crucial for making an impact with your work. Perhaps because it is the norm, we somehow accept and tolerate incomprehensible presentations, confusing boring with scientific rigor. This session will inspire, inform, and influence you to improve your presentation skills. We'll learn core principles and techniques to engage your audience and showcase your work. By putting in the effort, you can achieve the recognition, collaborations, and job opportunities you deserve when you get your audiences as excited about your work as you are. Don't let fear hold you back - join this session to invest in your own presentation skills.

Background: High-quality, precise medical practice is challenging in the face of uncertainty when the majority of clinical decisions lack adequate evidence to support or refute their practice (e.g., only 11% of clinical practice guideline recommendations are based on high-quality evidence). Pervasive practice variability then compromises both the quality and cost-efficiency of healthcare (e.g., patients receive only 55% of evidence-based recommended medical care). Clinical decision support like order sets help distribute expertise, but are constrained by resource intensive manual development. Objective: To overcome scalability limitations by automatically generating decision support content from existing practice patterns, analogous to Amazon.com’s product recommender. To perform the first structured validation of such a system against external standards-of-care and outcome predictions. Methods: We extracted deidentified electronic health record data from all hospitalizations at Stanford Hospital in 2011 (+5.4M structured data items from +19K patients) to build a system with association statistics for 811 clinical orders (e.g., labs, imaging, medications) and clinical outcomes. We manually reviewed the National Guideline Clearinghouse for diagnoses of chest pain, gastrointestinal hemorrhage, and pneumonia. We compared system generated clinical orders against guideline referenced orders by receiver operating characteristic (ROC) analysis. Human authored order sets provided real-world benchmarks. We compared predicted vs. actual outcomes by ROC analysis for separate validation patients. Results: System generated orders were overall consistent with guidelines (ROC AUC c-statistics 0.89, 0.95, 0.83) and improve upon statistical prevalence (0.76, 0.74, 0.73) and pre-existing order sets (0.81, 0.77, 0.73) (P Conclusions: Automatically generated order suggestions can reproduce and even optimize manual constructs like order sets while remaining largely concordant with guidelines and avoiding inappropriate recommendations. This has even more important implications for prevalent cases where well-defined guidelines and order sets do not exist. The same methodology is predictive of clinical outcomes comparable to state-of-the-art prognosis models (e.g., APACHE II), pointing to opportunities to link suggestions against favorable outcomes.

Dr. Jonathan Chen moderates a discussion on recent breakthrough concepts in medicine with panelists Michelle Litchman and Chen-Hua Yeow. Medicine X is a catalyst for new ideas about the future of medicine and health care. The initiative explores how emerging technologies will advance the practice of medicine, improve health, and empower patients to be active participants in their own care. The “X” is meant to encourage thinking beyond numbers and trends—it represents the infinite possibilities for current and future information technologies to improve health. Under the direction of Dr. Larry Chu, Associate Professor of Anesthesia, Medicine X is a project of the Stanford AIM Lab.

Stanford Medicine Grand Rounds April 25, 2018 https://lane.stanford.edu/biomed-resources/medgrandrounds.html

Medicine is ripe for applying AI, given the enormous volumes of real world data and ballooning healthcare costs. Professor Chen demystifies buzzwords, draws analogies to well-established tools and shares why mastering Go and operating self-driving cars differs from solving the unique medical challenges. Jonathan H. Chen, assistant professor of medicine at the Stanford University Medical Center As a physician data scientist, Professor Chen practices internal medicine for the concrete rewards of caring for real people and to inspire research focused on discovering and distributing clinical data knowledge. At Stanford, his group seeks to empower individuals with the collective experience of the many, combining human and artificial intelligence approaches that will deliver better care than either can do alone. Professor Chen is a founding partner of the startup Reaction Explorer, which draws on technology to teach complex problem-solving in organic chemistry. This talk was recorded at Stanford Reunion Homecoming 2018.

Jonathan Chen, Assistant Professor of Biomedical Informatics, Stanford University

Read more: https://stanford.io/38vi26f An expert in bioinformatics says that empowering clinicians with artificial intelligence that combs medical data will deliver better health care than either could do alone. We’re all familiar with those algorithms on our favorite e-commerce and streaming services that recommend purchases, books or movies based on what “others like you” have enjoyed. In the industry, they are known as “recommender engines.” Medical doctor Jonathan Chen is an assistant professor of medicine at Stanford and an expert in bioinformatics who wondered if the medical profession might benefit from similar artificial intelligence. He now creates recommender engines for doctors that comb real-world clinical data to help them make key decisions based on steps other doctors have taken with similar patients, empowering individuals with the collective experience of the many. Chen tells Stanford Engineering’s The Future of Everything podcast that such programs will soon be commonplace in exam rooms, helping doctors become better at what they already do and making medical practice a more consistent, universal experience for everyone. Subscribe here: https://the-future-of-everything-stanford-engineering.simplecast.com/

Session 5 focuses on issues of equity, bias, and strategies to achieve fairness in clinical AI applications 00:00 - Session Overview Kristen Yeom - Associate Professor of Radiology and, by courtesy, of Neurosurgery; Stanford 00:41 - AI, Medicine, & Bias: Diversifying Your Dataset is Not Enough Rachel Thomas - Director, Center for Applied Data Ethics, USF; Co-Founder of fast.ai 18:06 - Upgrading the Product Development Process to Foster ML Fairness and Ethical AI Donald Martin - Senior Technical Program Manager, Google 26:08 - Data autopsy for FAIR Medical AI Judy Gichoya - Assistant Professor of Radiology, Emory University School of Medicine 39:36 - The Price of Fairness in Clinical Risk Prediction Nigam Shah - Associate Professor of Medicine, and of Biomedical Data Science, Stanford 50:55 - Wisdom of the Crowd or Tyranny of the Mob? Will AI/ML Amplify Our Capabilities or Exacerbate Our Problems? Jonathan Chen - Assistant Professor of Medicine, Stanford 57:17 - Panel Discussion and Audience Q&A // Livestreamed on August 5, 2020 from the Stanford Center for Artificial Intelligence in Medicine and Imaging. Website: https://aimi.stanford.edu Twitter: https://twitter.com/StanfordAIMI #AIMI20

There is a paradox of artificial intelligence for decades that answering highly complex analytical tasks is almost easy to make a computer do. It is understanding common sense that is hard for computers to understand, which is why we need to have the intuition and perspective of the end-user practitioner. Dr. Chen is here to discuss the notion of whether and how computers can make physicians smarter. Jonathan Chen is a physician-scientist with professional software development experience and graduate training in computer science. He continues to practice Internal Medicine for the concrete rewards of caring for real people and to inspire his research focused on mining clinical data sources to inform medical decision making. He completed medical training in Internal Medicine and a VA Research Fellowship in Medical Informatics. He has published influential work in the New England Journal of Medicine, JAMA Internal Medicine, Bioinformatics, Journal of Chemical Information and Modeling, and the Journal of the American Medical Informatics Association, with research awards and recognition from the NIH Big Data 2 Knowledge initiative, National Library of Medicine, American Medical Informatics Association, Yearbook of Medical Informatics, and the American College of Physicians, among others. Jonathan Chen is a physician-scientist with professional software development experience and graduate training in computer science. He continues to practice Internal Medicine for the concrete rewards of caring for real people and to inspire his research focused on mining clinical data sources to inform medical decision making. He completed medical training in Internal Medicine and a VA Research Fellowship in Medical Informatics. He has published influential work in the New England Journal of Medicine, JAMA Internal Medicine, Bioinformatics, Journal of Chemical Information and Modeling, and the Journal of the American Medical Informatics Association, with research awards and recognition from the NIH Big Data 2 Knowledge initiative, National Library of Medicine, American Medical Informatics Association, Yearbook of Medical Informatics, and American College of Physicians, among others. This talk was given at a TEDx event using the TED conference format but independently organized by a local community. Learn more at https://www.ted.com/tedx

Guest seminar at Stanford Biomedical Informatics 205 in Fall 2020. Thanks to Daniel Rubin and Rocky Aikens for hosting. Overview of several of the broad research directions our group is working on to combine human and artificial intelligence approaches to deliver better healthcare than either could alone.

Opening Speech Prof Kelvin Tsoi, Associate Professor, JC School of Public Health and Primary Care, The Chinese University of Hong Kong, Hong Kong, China Keynote Presentation: The Digital Innovations from the COVID Pandemic That Will Make the Biggest Impact on Health by 2030 Dr Ashley McKimm, Editor-in-Chief, BMJ Innovations, United Kingdom Invited Presentation: Mobile Digital Health for COVID-19: Ready, Set, ... Go? Prof Björn Schuller, Professor of Artificial Intelligence, Imperial College London, United Kingdom Australia’s Telehealth Response to COVID-19 Prof Anthony Smith, Director, Centre for Online Health, The University of Queensland, Australia; Editor-in-Chief, Journal of Telemedicine and Telecare Discovering and Distributing the Latent Knowledge Embedded in Clinical Data: Enabling Digital Consultations Prof Jonathan Chen, Assistant Professor, Center for Biomedical Informatics Research, Stanford University, United States Harnessing Digital Medicine to Optimise Drug Development and N-of-1 Healthcare Prof Dean Ho, Provost’s Chair Professor of Biomedical Engineering and Pharmacology, National University of Singapore, Singapore Facilitators: Dr Michelle Morris, University Academic Fellow, Leeds Institute for Data Analytics, University of Leeds, United Kingdom Dr Esther Talboom-Kamp, Chief Innovation Officer, Unilabs

Keynote presentation for over a hundred clinicians at the Stanford University Medical Partners annual retreat, October 2023. Mix of technology and medicine concepts with demonstrations of magic and mentalism that further blur the lines between sophisticated methods vs. convincing illusions

During this Grand Rounds, experts discuss "Fountain of Creativity or Pandora's Box? Large Language Models in Healthcare: From Concept to Application." Presenter: Ron Li, MD, Clinical Assistant Professor of Hospital Medicine, Jonathan Chen, MD, PhD, Assistant Professor of Medicine - Biomedical Informatics. Learn more: https://medicine.stanford.edu/

AI generated script, voice, and talking portrait to introduce a talk on AI in healthcare Script: https://chat.openai.com/ Voice: https://elevenlabs.io/ Talking Portrait: https://www.d-id.com/

Artificial intelligence is making waves in nearly every industry, but questions still abound. Maya Adam, MD, and guests Jonathan Chen, MD, PhD, assistant professor of medicine and biomedical data sciences, and Michael Pfeffer, MD, chief information officer of Stanford Health Care and the Stanford School of Medicine, talk about how AI is being brought into the folds of medicine. From questions like, “How is AI impacting the doctor-patient relationship?” to “Can I trust medical information that comes from AI,” Chen and Pfeffer discuss their experiences with AI and other boons of the technology when it comes to diagnostics and access to health care. Learn more about this episode: https://stan.md/3YNi6bN Read the article that inspired this episode: https://stan.md/3QNzbyG . . . #AIMedicine #AIHealthcare #DoctorPatientRelationship #MedicalAI #AIinDiagnostics #DigitalHealth #HealthInnovation #AIEthics #MedicalInformation #AIandTrust #FutureOfHealthcare #AIBenefits #HealthTech #StanfordMedicine #StanfordHealthCare Stanford Medicine advances human health through world-class biomedical research, education and patient care. Bringing together the resources of Stanford University School of Medicine, Stanford Health Care and Lucile Packard Children's Hospital, Stanford Medicine is committed to training future leaders in biomedicine and translating the latest discoveries into new ways to prevent, diagnose and treat disease. The Stanford Medicine YouTube channel is a curated collection of contributions from our School of Medicine departments, divisions, students, and the community. Our diverse content includes coverage of events, presentations, lectures, and associated stories about the people of Stanford Medicine.

🇺🇸Holiday Sale: https://ept.ms/41dPADi 🔵 Watch the full episode:https://ept.ms/BalancingScienceAndArt_YT In this insightful interview, Dr. Jonathan Chen, a medical doctor and professor at Stanford University, reflects on his remarkable journey, beginning college at age 13 through an early entrance program at Cal State Los Angeles before transferring to UCLA. He shares his thoughts on artificial intelligence in medicine, addressing its potential and limitations and shedding light on misconceptions about it. He explores its role in improving doctor-patient interactions while cautioning against overhyped expectations. Beyond medicine, Chen delves into the mind-body connection, the pitfalls of over-testing, and the importance of balance. He also shares how his passion for music and magic enrich his personal and professional life, highlighting creativity’s vital role in innovation. “Amongst Nobel Prize-winning scientists, they’re two times more likely to play music... and 20 times more likely to perform, like magic or acting,” Chen noted, emphasizing the transformative power of disciplined creativity. Join us for this captivating conversation that blends science, art, and human connection. 💛 Support us: https://donorbox.org/epochtv 🔴 Sign up for our NEWSLETTER and stay in touch: https://ept.ms/EpochTVNewsletter 🇺🇸Stay updated with breaking news, special reports, and LIVE COVERAGE on NTD: https://ept.ms/NTDlive_ 🔴SUBSCRIBE to The Epoch Times YouTube channel TODAY: https://www.youtube.com/channel/UCeLc4heXqG9dtL7jiPHMBfQ?Sub_confirmation=1 Balancing Science and Art: Dr. Chen’s Unique Approach to Innovation | Trailer | Bay Area Innovators #bayareainnovators #scienceandarts #artificialintelligence ------------------ Views expressed in this video are opinions of the host and guests, and do not necessarily reflect the views of The Epoch Times. © All Rights Reserved.

During this Grand Rounds, experts discuss "Artificial Intelligence in Medicine: Real Magic or Technological Illusions?" Presenter: Jonathan Chen, MD, PhD Assistant Professor of Medicine, (Biomedical) and of Biomedical Data Science Learn more: https://medicine.stanford.edu/

Artificial Intelligence in Medicine - Real Magic or Technological Illusions? with Jonathan H. Chen MD, PhD, Assistant Professor of Medicine (Biomedical Informatics) and of Biomedical Data Science at Stanford University. It will be moderated by Jeff Hancock. Stanford affiliates are invited to join us at 12:40 PM for lunch, prior to the seminar. The Spring Seminar Series continues through the end of May; see our Spring Seminar Series page for speakers and topics. About the Seminar: Pandora’s box has opened in the form of publicly available generative AI systems for every imaginable (and many unintended) purposes. With a global scarcity of medical expertise against the unlimited demand of people in need, AI's potential to democratize healthcare knowledge, access, and to recover efficiencies is desperately needed. The implications are vast as we converge upon a point in history where human vs. computer generated content can no longer be reliably distinguished. This session will review the attention and intention required for AI applications in the high-stakes world of healthcare as we distinguish real magic from convincing illusions. About the Speaker: Jonathan H. Chen MD, PhD leads a research group to empower individuals with the collective experience of the many, combining human and artificial intelligence approaches to deliver better care than either alone. Dr. Chen continues to practice medicine for the concrete rewards of caring for real people and to inspire this research focused on discovering and distributing the latent knowledge embedded in clinical data. Before his medical training, Chen co-founded a company to translate his Computer Science graduate work into an expert system for organic chemistry, with applications from drug discovery to an education tool for students around the world. His expertise is regularly featured in popular press outlets with over 100 publications in leading clinical and informatics venues and awards from the NIH, National Library of Medicine, American Medical Informatics Association, International Brotherhood of Magicians and more. In the face of ever escalating complexity in medicine, informatics solutions are the only credible approach to systematically address challenges in healthcare. Tapping into real-world clinical data like electronic medical records with machine learning and data analytics will reveal the community's latent knowledge in a reproducible form. By delivering this back to clinicians, patients, and healthcare systems as clinical decision support, he aims to uniquely close the loop on a continuously learning health system.

This year's RAISE Health Symposium aims to build on discussions that took place at our inaugural event in May 2024 by focusing more deeply on practical challenges and actionable solutions to ensure the safe and responsible use of AI in biomedicine.

AI in Medical Education Symposium, a part of Stanford Medicine's Health AI Week. June 4th, 2025.