Volume 2, No. 7 of NEJM AI is now available! Here are the latest articles:. Editorial: The Generalist–Specialist Paradox of Medical AI 🔖 Save for later and share with a friend

Can an AI doctor learn from its mistakes? In training AMIE, @apalepu13 & team used a “critic agent” that reviewed each conversation & coached the chatbot to try again. On @NEJM_AI Grand Rounds, hear how AI practiced to get better at empathy. Listen now:

Case Study by J. Clusmann et al.: Incidental Prompt Injections on Vision–Language Models in Real-Life Histopathology . #AIinMedicine

Case Study by W.S. Azar et al.: LLM-Mediated Data Extraction from Patient Records after Radical Prostatectomy . #HealthIT #MedicalAI

Review Article: Development and Commercialization Pathways of AI Medical Devices in the United States: Implications for Safety and Regulatory Oversight

Policy Corner: Lessons from the Failure of Canada’s Artificial Intelligence and Data Act Datasets, Benchmarks, and Protocols: PadChest-GR: A Bilingual Chest X-Ray Dataset for Grounded Radiology Report Generation

Original Article: An Electrocardiogram Foundation Model Built on over 10 Million Recordings Original Article: Expert-Level Detection of Epilepsy Markers in EEG on Short and Long Timescales

Perspective: Improving Mental Health Care Access with Technology: Addressing the Screening-to-Referral Bottleneck Original Article: AI-Enabled Parkinson’s Disease Screening Using Smile Videos

Perspective: The Landscape of Medical AI in China Perspective: Can a Chatbot Be a Medical Surrogate? The Use of Large Language Models in Medical Ethics Decision-Making

RT @EricTopol: A foundation model of 10 million ECGs shows how much is encoded in these recordings that cardiologists would not be able to….

Policy Corner by Bettina McMahon, MBA, and Daniel McInerney, MTax: Right Care, Right Place, First Time: How AI Is Improving National Virtual Front Doors . #AIinMedicine

Original Article by M.H. Bernstein et al.: Randomized Study of the Impact of AI on Perceived Legal Liability for Radiologists . #Radiology #AinMedicine

Editorial by Spyridon P. Basourakos, MD, and Jonathan E. Shoag, MD: AI Streamlines Prostate Pathology Data Extraction . #AIinMedicine #CancerResearch

Datasets, Benchmarks, and Protocols by A.S. Chiou et al.: Multimodal Image Dataset for AI-Based Skin Cancer (MIDAS) Benchmarking . #AIinMedicine #DermTwitter

RT @NEJM: Many AI innovations could benefit patients and clinicians, write the authors of a new Perspective. Yet medicine should heed lesso….

RT @NEJM: I. Glenn Cohen, JD (@CohenProf), discusses the professional implications of the use of artificial-intelligence–based monitoring s….

Perspective by M.J.A. Reid: Essential Strategies for Leveraging AI in the Global HIV Response . #AIinMedicine #GlobalHealth

Perspective by S. Tripathi (@Satvikt_ai) et al.: Development, Evaluation, and Assessment of Large Language Models (DEAL) Checklist: A Technical Report . #ArtificialIntelligence

Handwritten labels and watermarks on histopathological images can unintentionally act as prompt injections, misleading vision–language models and resulting in inaccurate outputs that highlight a critical vulnerability in medical AI systems. Learn more:

RT @zakkohane: Interesting snapshot of growth in clinical AI publications in China @NEJM_AI (TLDR rapid growth but lagging in the highest….