Physician-Reported Safety Outcomes of AI-Generated Hospital Course Summaries

Is a large language model (LLM)–based agentic workflow for generating hospital course summaries safe and useful during prospective clinical deployment, and is it associated with reduced physician burnout?In this quality improvement study of 384 hospital discharges, physicians incorporated artificial intelligence agent–generated summaries into most final discharge notes, and among summaries with feedback, most were rated as having no harm potential, with 1 rated as likely to cause moderate harm. Burnout scores decreased significantly, crossing below the established burnout threshold.These findings suggest that agentic LLM workflows with reasoning models may be integrated into active clinical care with minimal safety risk and may be associated with reduced physician burnout, even when objective time savings are modest.

Corresponding Author: François Grolleau, MD, PhD, Division of Computational Medicine, Stanford University, 450 Jane Stanford Way, Stanford, CA 94305 (grolleau@stanford.edu).

Link to the article in your story

We encourage you to link out to this article in your story using the link below. It includes an access token that will give free access to the article for your readers up to one year after publication. (The link will be live after the article publishes and embargo is lifted.)

Please see the article for additional information, including full author list, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.

Need more information? Contact us.