Editorial by Samuel G. Finlayson, MD, PhD, and Heidi L. Rehm, PhD: When Genomic Reanalysis Leaves the Laboratory — Clinical Genetics in the Age of Consumer AI https://nejm.ai/4vVYCAY #ArtificialIntelligence #AIinMedicine

Sometimes the problem isn't the model. It's the environment around it. In the latest episode of the NEJM AI Grand Rounds podcast, Dr. Karan Singal explains why workflow design matters. Listen now: https://nejm.ai/ep43 #ArtificialIntelligence #AIinMedicine

ReXGroundingCT is the first publicly available manually annotated dataset to link free-text radiology findings with 3D segmentations in chest CT scans, enabling research in grounded radiology report generation. Learn more: https://nejm.ai/4giw8N6

A new Case Study evaluates an LLM–assisted genomic reanalysis workflow that integrates clinician notes, Human Phenotype Ontology terms, and filtered variant data to generate diagnostic hypotheses for expert review. Learn more: https://nejm.ai/4eMh8pu

What if better models reduce — not increase — the value of traditional oversight? In the latest episode of the NEJM AI Grand Rounds podcast, Dr. Karan Singal discusses findings that challenge assumptions. Listen to the full episode: https://nejm.ai/ep43 #ArtificialIntelligence #AIinMedicine

A new editorial discusses whether clinical genetics is prepared for a world in which patients and families can generate rare disease analyses on their own. Full editorial: https://nejm.ai/4vVYCAY

Human + AI isn't a fixed equation. In the latest episode of the NEJM AI Grand Rounds podcast, Dr. Karan Singal describes findings showing that oversight may depend on model capability. Learn more: https://nejm.ai/ep43 #ArtificialIntelligence #AIinMedicine

What pulls someone into AI? For Dr. Karan Singal, it wasn’t code first — it was curiosity. Hear more from Dr. Singal in the latest episode of the NEJM AI Grand Rounds podcast: https://nejm.ai/ep43 #ArtificialIntelligence #AIinMedicine

Perspective by Adrian Gropper, MD: The Medical AI Assistant as Publication, Not Device — Why Peer-Reviewed, Open-Source AI Belongs in the Standard of Care https://nejm.ai/4e7q6MA #ArtificialIntelligence #AIinMedicine

Editorial by Isaac S. Kohane, MD, PhD: Guideline Machines https://nejm.ai/49QwJBF #ArtificialIntelligence #AIinMedicine

A new Perspective proposes that open-weight, peer-reviewed retrieval-augmented medical artificial intelligence assistants, used with physician review, may be better understood as published clinical methodologies rather than regulated devices. Learn more: https://nejm.ai/4e7q6MA

A new editorial by Isaac S. Kohane, MD, PhD, discusses the role of AI in clinical guidelines. Full editorial: https://nejm.ai/49QwJBF #ArtificialIntelligence #AIinMedicine

Medical expertise has always been scarce. Can AI help change that? Dr. Karan Singal, research lead at OpenAI, believes it can and explains how in the latest episode of the NEJM AI Grand Rounds podcast. Listen now: https://nejm.ai/ep43

Review Article by @mattbmcdermott.bsky.social et al.: MEDS — An Emerging Data Standard and Ecosystem for Health AI Research https://nejm.ai/3Q9iGjW #ArtificialIntelligence #AIinMedicine

In a randomized trial involving patients undergoing complex high-risk PCI, the risk of target-vessel failure (a composite outcome) was not lower with intravascular ultrasound guidance than with angiography guidance. Full IVUS-CHIP trial results and Research Summary: https://nej.md/4uRFSCW

What good is the “right answer” if no one can access it? In the latest episode of the NEJM AI Grand Rounds podcast, Dr. Travis Zack of OpenEvidence discusses AI in low-resource settings. Hear more from Dr. Zack in the full episode: https://nejm.ai/ep42

Among patients with unprotected left main coronary artery disease, intravascular ultrasonography–guided PCI did not result in a lower risk of ischemic events or death than angiography-guided PCI. Full OPTIMAL trial results and Research Summary: https://nej.md/4rUEuwu

Policy Corner by Jonathan D. Ketcham, PhD: Artificial Intelligence as a Return on Investment Multiplier in Health Care https://nejm.ai/4uNRshk #ArtificialIntelligence #AIinMedicine

Policy Corner by Sara Gerke, Dipl.-Jur. Univ., MA, and David A. Simon, PhD, JD, LLM: Privacy Considerations of Artificial Intelligence Scribes https://nejm.ai/3Pkqwaa #ArtificialIntelligence #AIinMedicine

Twelve papers. One recommendation. Humans still outperform models. Dr. Travis Zack of OpenEvidence explains on NEJM AI Grand Rounds. Listen to the full episode: https://nejm.ai/ep42

Editorial by Jeffrey M. Drazen, MD, and Charlotte J. Haug, MD, PhD: Medicine as an Information Industry in the Age of Language Models https://nejm.ai/4ddmTMh #ArtificialIntelligence #AIinMedicine

The model has the paper, but not the answer. Dr. Travis Zack of OpenEvidence explains on NEJM AI Grand Rounds how hallucinations still happen. Listen to the full episode: https://nejm.ai/ep42

A new Review Article examines MEDS, an open-source data framework designed to improve reproducibility and interoperability for AI models applied to EHR data. It highlights early gains in performance and code efficiency. Learn more: https://nejm.ai/3Q9iGjW #ArtificialIntelligence #AIinMedicine

A new Policy Corner argues that predictive AI can multiply the clinical and economic value of therapies by improving treatment allocation through risk-based and response-based targeting. Learn more: https://nejm.ai/4uNRshk

Most decisions aren’t uncertain — they’re almost certain. In the latest episode of the NEJM AI Grand Rounds podcast, Dr. Travis Zack of OpenEvidence explains why AI is a double-check tool. Learn more: https://nejm.ai/ep42

A new Policy Corner examines emerging privacy risks related to AI scribes, outlining data flows and key privacy considerations, and offers best practice recommendations for health systems implementing or considering their use. Learn more: https://nejm.ai/3Pkqwaa

A new editorial traces the evolution of medical knowledge delivery from print and search-based systems to AI-synthesis powered by LLMs. It argues that efficiency gains introduce new risks to reliability and evidence. Full editorial: https://nejm.ai/4ddmTMh

“The answer is not the important part.” In the latest episode of the NEJM AI Grand Rounds podcast, Dr. Travis Zack of OpenEvidence challenges how we measure both clinicians and AI. Hear more from Dr. Zack in the full episode: https://nejm.ai/ep42

Ambient AI documentation tools carry legal risks around consent, data transmission, and state recording laws. A new Perspective outlines strategies to mitigate liability and support transparent implementation. https://nej.md/43esKuR #ArtificialIntelligence #AIinMedicine

Review Article by R. Goel et al.: Large Language Models in Informed Consent — Opportunities, Evidence, and Challenges https://nej.md/4nDEIrs #ArtificialIntelligence #AIinMedicine

Policy Corner by David Blumenthal, MD, MPP, and Vivian S. Lee, MD, PhD, MBA: A Typology of Generative Health Care Artificial Intelligence — Definitions and Policy Implications https://nej.md/3R6WwiC #ArtificialIntelligence #AIinMedicine

Perspective by T.N. Anderson et al.: Ambient AI in Clinical Practice — The Legal Landscape of Recording Consent Requirements https://nej.md/43esKuR #ArtificialIntelligence #AIinMedicine

A new Review Article examines how LLMs could reshape informed consent in clinical research by making it clearer, more accessible, and more responsive to participants' needs. It also highlights safeguards required for responsible use. Learn more: https://nej.md/4nDEIrs

How should AI support decision-making? Dr. Travis Zack, CMO of OpenEvidence, addresses that question in the latest episode of AI Grand Rounds. He also takes us behind the scenes of the start and growth of the company. Listen to the full episode available now: https://nejm.ai/ep42 #AIinMedicine

A new Policy Corner article clarifies key concepts and differences across various applications of AI in health care to help clinicians, patients, managers, and policy-makers better understand, apply, manage, and govern these technologies in practice. Learn more: https://nej.md/3R6WwiC #AIinMedicine

The authors of a new Perspective argue that clinicians are rightly expected to disclose their gaps in knowledge or their inability to forecast an outcome. Yet emerging AI tools often cannot, or will not, do the same. Read the Perspective: https://nej.md/4fgdg0D

Original Article by I.A. Qazi et al.: Automation Bias in Large Language Model–Assisted Diagnostic Reasoning among Physicians Trained in AI Literacy — A Randomized Clinical Trial https://nej.md/4tUxtgX

Perspective by S. Kpodzro et al.: A Collaborative Best Practice Guide for Promoting AI Vendor Transparency in Health Care — The HAIP AI Vendor Disclosure Framework https://nej.md/3OWAb6B

Editorial by Laura Zwaan, PhD, Adam Rodman, MD, and Taro Shimizu, MD, PhD: Trust, Scrutiny, or Collaboration? A Performance-Based Framework for Human–AI Interaction in Medicine https://nej.md/48Eckzk @adamrodmanmd.bsky.social

Original Article by Y. Ji et al.: A Generative Foundation Model for Chest Radiography https://nej.md/4nuGhYR #ArtificialIntelligence #AIinMedicine

Penicillin changed medicine — AI could too. In the latest episode of the NEJM AI Grand Rounds podcast, Dr. Byron Crowe warns that moving too slowly is a risk. Listen to the full episode to learn why: nejm.ai/ep41 #ArtificialIntelligence #AIinMedicine

Perspective by Sam Joseph Amirfar, MD, MS: I Hope You Are Doing Well — Will AI Widen or Close Health Care’s Disparity Gap? https://nej.md/42cvbhd #ArtificialIntelligence #AIinMedicine

Automation bias from LLMs presents a potential patient safety risk. A new trial quantified that risk, revealing a 14-percentage-point decrease in diagnostic accuracy among physicians trained in #AI literacy. Learn more: https://nej.md/4tUxtgX

Health care delivery organizations are facing a surge of #AI vendor offerings but often lack the information needed to evaluate these systems responsibly. A new, structured approach clarifies what information vendors should provide. Learn more: https://nej.md/3OWAb6B

A new editorial discusses the automation bias that was found in the study by Qazi et al., “Automation Bias in Large Language Model–Assisted Diagnostic Reasoning among AI-Trained Physicians.” Full editorial: https://nej.md/48Eckzk @adamrodmanmd.bsky.social

A new study introduces ChexGen, a generative vision-language foundation model for chest radiography, and demonstrates its applications in training data augmentation, data-efficient learning, and bias detection and mitigation. Learn more: https://nej.md/4nuGhYR #AIinMedicine

In a new Perspective, Sam Joseph Amirfar, MD, MS, argues that deliberate policies, equitable access, and clinician-led governance are essential to ensure AI strengthens care without deepening existing disparities. Read the full Perspective: https://nej.md/42cvbhd #AIinMedicine

What if refills weren’t just clicks but conversations? In the latest episode of the NEJM AI Grand Rounds podcast, Dr. Byron Crowe discusses AI-driven patient interaction. Hear more from Dr. Crowe: nejm.ai/ep41 #ArtificialIntelligence #AIinMedicine

From telemedicine to AI: In the latest episode of the NEJM AI Grand Rounds podcast, Dr. Byron Crowe explains why recognizing the shift matters more than predicting it. Listen to the full episode: nejm.ai/ep41 #ArtificialIntelligence #AIinMedicine

Datasets, Benchmarks, and Protocols by J.W. Hughes et al.: EchoNext-Mini: A Dataset and Baseline AI Model for Detecting Structural Heart Disease from Electrocardiograms nejm.ai/4sI5Iab #AIinMedicine