Figure 1. Human Factors–Related Risk and Recommendation Map for AIeMDs.
Figure 2. Mapping of AIeMD Human Factors Guidance to Standard Regulatory Usability Deliverables.
Policy Corner by Z. Ding et al.: Evaluation of Human Factors–Related Risks in AI-Enabled Medical Devices — A Practical Guide nejm.ai/4uXQTTj
#AI #MedSky #MLSky
Figure 1. Overview of the Study Design.
Figure 2. Overall Study Workflow across Datasets.
Figure 3. Model Diagram.
Original Article by Z. Ding et al.:Generating Cardiac Magnetic Resonance Images from Electrocardiograms — A Multicenter Study nejm.ai/4166ulW
#AI #MedSky #MLSky
Free Virtual Event | April 22, 2026 Value Alignment & Incentive Divergence in Clinical AI Session 2: Navigating Different Regulatory Regimes and Value Systems Across Countries Isaac Kohane, MD, PhD Moderator Rebecca W. Brendel, MD, JD Jonathan Ketcham Nikhil R. Sahni, MBA, MPA Chethan Sarabu, MD Susan M. Wolf, JD
Don't miss our expert panel discussion on navigating different regulatory regimes and value systems across countries during our next free web event. Learn more and register: nejm.ai/4rVJEIH
AI Grand Rounds Episode 41 Doctronic’s Autonomous AI with Dr. Byron Crowe Photo of Dr. Crowe
In the latest episode of AI Grand Rounds, Dr. Byron Crowe, chief medical officer of Doctronic, describes how administrative complexity can interfere with timely, effective treatment, and how #AI may help address those challenges. Listen to the full episode: nejm.ai/ep41
“Ensuring access to AI across rural and urban health systems is not merely about technology deployment, but whether health systems can distribute the benefits of innovation.” Perspective “The Inverse Care Law in the Age of AI — Geographic Disparities in Health Care Technology Access” by Yeon-Mi Hwang, Ph.D., Brian T. Rice, M.D., and Tina Hernandez-Boussard, Ph.D.
Perspective by Yeon-Mi Hwang, PhD, Brian T. Rice, MD, and Tina Hernandez-Boussard, PhD: The Inverse Care Law in the Age of AI — Geographic Disparities in Health Care Technology Access nejm.ai/4v0RvHx
#AI #MedSky #MLSky
Editorial Health systems need to weigh the risk of allowing these tools to be used in a compliant way against the status quo of unmonitored use without protections for patient data. “Health Systems Govern Only the Tip of the AI Iceberg” by E. Ötleş et al.
Editorial by E. Ötleş et al.: Health Systems Govern Only the Tip of the AI Iceberg nejm.ai/4sQFxz6
#AI #MedSky #MLSky
Figure 1. Human Factors–Related Risk and Recommendation Map for AIeMDs.
A new Policy Corner proposes a structured human factors framework for AI-enabled medical devices, distinguishing technical model performance from the safety and effectiveness of human interaction with #AI outputs in real-world clinical workflows. Learn more: nejm.ai/4uXQTTj
#MedSky #MLSky
Figure 1. Overview of the Study Design.
Across large, multicohort datasets, CardioNets achieved superior performance to ECG-only baselines and diagnostic accuracy comparable to CMR-based models, supporting its potential to expand access to advanced cardiovascular assessment. Full study results: nejm.ai/4166ulW
#AI #MedSky #MLSky
Free Virtual Event Value Alignment & Incentive Divergence in Clinical AI Session 1: Prior to Regulation: How May Health Care Clarify the Values Their AI Systems Are Aligned to? (Executive Sponsor Q & A) Isaac Kohane, MD, PhD Moderator Meera Kataria Atkins, MD, MBA, FACOG Ashok Chennuru Andrew M. Ibrahim, MD, MSc, FACS David C. Rhew, MD
Hear from our executive sponsors at our next free virtual event. You'll hear from experts from Lyric, Elevance Health, Viz.ai, and Microsoft.
View the full speaker lineup and save your seat: nejm.ai/4rVJEIH
Figure 1. Health Care Needs and Resources by Rural–Urban Classification Using the 2013 National Center for Health Statistics Urban–Rural Classification Scheme for Counties.
A new Perspective examines the misalignment between health needs, health care resources, and #AI implementation capacity, demonstrating that Hart’s inverse care law persists in the AI era. Read the full Perspective: nejm.ai/4v0RvHx
#MedSky #MLSky
Figure 1. The AI Governance Iceberg Demonstrating Visible and Hidden AI Use in Health Care.
Health systems’ lack of engagement with consumer #AI tools worsens their risk by eliminating institutional visibility and protections. Ötleş et al. describe the scope of this problem and why health systems need to reform their approach to AI governance. nejm.ai/4sQFxz6
#MedSky #MLSky
Figure 3. Clinical Impact Study.
Original Article by H.-Y. Zhou et al.: MedVersa: A Generalist Foundation Model for Diverse Medical Imaging Tasks nejm.ai/4bVAiYz
#AI #MedSky #MLSky
Value Alignment & Incentive Divergence in Clinical AI April 22, 2026 Free Virtual Event NEJM AI
Different AI models consistently prioritize clinical decisions in unique ways — and those differences impact patients, clinicians, and organizations alike. Don’t miss our next free event:
📅 April 22
🕛 12 PM–1:45 PM ET
📍 Virtual
Learn more and save your spot: nejm.ai/4rVJEIH
No one opts out of health care. That’s the moral and operational reality. On NEJM AI Grand Rounds, Dr. Kyunghyun Cho argues #AI should help systems care better under constraints. If a tool can’t reduce friction at the bedside, what is it really for? Full episode: nejm.ai/ep40
#MedSky #MLSky
Figure 1. Strengthening the Reporting of Observational Studies in Epidemiology Inclusion Flowchart.
Figure 2. Transitions in Care Intentions from Preassessment to Postassessment Time Points.
Figure 3. Transitions between Preassessment Intentions and Actual Behavior.
Original Article by F. Cotte et al.: From Advice to Action — Real-World Behavior of Patients Using an Integrated Diagnostic Decision Support System for Navigating the Health Care System nejm.ai/4rENohz
#AI #MedSky #MLSky
From Advice to Action — Real-World Behavior of Patients Using an Integrated Diagnostic Decision Support System for Navigating the Health Care System nejm.ai/4rENohz
𝗣𝗼𝗹𝗶𝗰𝘆 𝗖𝗼𝗿𝗻𝗲𝗿
Evaluation of Human Factors–Related Risks in AI-Enabled Medical Devices — A Practical Guide nejm.ai/4uXQTTj
𝗢𝗿𝗶𝗴𝗶𝗻𝗮𝗹 𝗔𝗿𝘁𝗶𝗰𝗹𝗲𝘀
Generating Cardiac Magnetic Resonance Images from Electrocardiograms — A Multicenter Study nejm.ai/4166ulW
MedVersa: A Generalist Foundation Model for Diverse Medical Imaging Tasks nejm.ai/4bVAiYz
Cover of the April 2026 issue of NEJM AI with "NEW ISSUE NOW AVAILABLE" above it.
Volume 3, No. 4 of NEJM AI is now available! Here is a preview of the latest content:
𝗘𝗱𝗶𝘁𝗼𝗿𝗶𝗮𝗹
Health Systems Govern Only the Tip of the AI Iceberg nejm.ai/4sQFxz6
𝗣𝗲𝗿𝘀𝗽𝗲𝗰𝘁𝗶𝘃𝗲
The Inverse Care Law in the Age of AI — Geographic Disparities in Health Care Technology Access nejm.ai/4v0RvHx
Sometimes expertise becomes a trap. On NEJM AI Grand Rounds, Dr. Kyunghyun Cho reflects on how we can reconsider our perspective to unlock progress. Hear more from Dr. Cho in the full episode: nejm.ai/ep40
#AI #MedSky #MLSky
Value Alignment & Incentive Divergence in Clinical AI April 22, 2026 Free Virtual Event Register Now NEJM AI
A critical issue is coming into focus as AI becomes further embedded in clinical decision-making: different AI models consistently prioritize clinical decisions in unique ways—and those differences impact patients, clinicians, and organizations alike.
Register for our next event → nejm.ai/4rVJEIH
Figure 1. Study Overview.
The authors of a new article show that MedVersa, a model trained on millions of medical images, matches or outperforms task-specific systems while producing clinically equivalent radiology reports and reducing reporting time and discrepancies. Learn more: nejm.ai/4bVAiYz
#AI #MedSky #MLSky
When a research path becomes “predictable,” is it still research or product development? On NEJM AI Grand Rounds, Dr. Kyunghyun Cho draws a hard line between discovery and scaling. In health care, where should each live, and who should own the risk? Learn more: nejm.ai/ep40
#AI #MedSky #MLSky
Figure 1. Strengthening the Reporting of Observational Studies in Epidemiology Inclusion Flowchart.
An AI-powered digital front door tool used in Portugal was associated with reduced patient uncertainty, meaningful shifts in care-seeking behavior, and a substantial improvement in the appropriateness of health care utilization. Full study results: nejm.ai/4rENohz
#AI #MedSky #MLSky
A career in #AI doesn’t always start with a plan. Sometimes it starts with a recession, a random lab assignment, and a decision to keep going. On NEJM AI Grand Rounds, Dr. Kyunghyun Cho reminds us that serendipity favors the curious. Listen to the full episode: nejm.ai/ep40
#MedSky #MLSky
Letter by Sean Mann, MSc, and Carl T. Berdahl, MD, MSc: Spillover Effects in Randomized Evaluations of Translational AI nejm.ai/4seuNK1
Perspective by Richard K. Leuchter, MD, William B. Turner, BA, and David Ouyang, MD: Evaluating Translational AI: A Two-Way Moving Target Problem nejm.ai/3LFovDj
Page 1 of "Response to Spillover Effects in Randomized Evaluations of Translational AI” Read the full letter at ai.nejm.org.
Richard K. Leuchter, MD, William B. Turner, BA, and David Ouyang, MD, respond to a letter about their Perspective “Evaluating Translational AI: A Two-Way Moving Target Problem.” Read the full response: nejm.ai/4cQzu8d
#AI #MedSky #MLSky
AI Grand Rounds Episode 40 AI’s Next Frontier with Dr. Kyunghyun Cho Photo of Dr. Cho
In the latest episode of AI Grand Rounds, Dr. Kyunghyun Cho discusses his wide-ranging career spanning fundamental #AI research, co-founding Prescient Design (acquired by Genentech), and driving applications of AI in health care. Full episode: nejm.ai/ep40
#MedSky #MLSky
Letter by Gerald Wiest, MD, FAAN, and Oliver H. Turnbull, PhD: Response: Metaphors and Errors in Describing Large Language Models nejm.ai/4rBUqUZ
Perspective by Gerald Wiest, MD, FAAN, and Oliver H. Turnbull, PhD: Faulty Artificial Intelligence, or the Sleep of Reason nejm.ai/4nV6JKh
Page 1 of the letter "From Psychological Metaphors to Mechanistic Framing in Describing Errors in Large Language Models" Read the full letter at ai.nejm.org.
In a letter, Daniel I. Ro, MD, comments on the Perspective “Faulty Artificial Intelligence, or the Sleep of Reason.” Read the full letter: nejm.ai/4rBU9Br
#AI #MedSky #MLSky
Figure 1. Correctly Identified Safe and Unsafe NGT by AI in our Study (True-Positive and True-Negative Cases).
Figure 2. Examples of False-Negative Cases.
Figure 3. Examples of False-Positive Cases — CXRs Showing “Safe” NGTs Identified Incorrectly as “Suboptimal” (Unsafe) by the AI Tool.
Original Article by A.-M. Bartsch et al.: External Validation of a Commercially Available AI Tool for Nasogastric Tube Position Decision Support in the NHS: A Prospective Silent Trial nejm.ai/46nhZbS
#AI #MedSky #GastroSky
