Physician-Reported Safety Outcomes of AI-Generated Hospital Course Summaries
JAMA Network Open · 08.05.2026 · 9 (5) · e2616556
DOI: 10.1001/jamanetworkopen.2026.16556 ↗Kurz gefasst
Fachartikel in der Zeitschrift JAMA Network Open, online erschienen am 08.05.2026. Verfasst von François Grolleau und 22 weiteren Autor:innen. Beteiligte Einrichtung: Division of Computational Medicine, Stanford University, Stanford, California. Hauptthemen laut MEDLINE: Patient Safety, Physicians, Patient Discharge Summaries. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Importance High-quality discharge summaries are essential for safe care transitions but contribute substantially to clinician documentation burden and burnout. While retrospective studies suggest that large language models (LLMs) can generate clinical summaries of comparable quality to those by physicians, prospective data on their safety, utility, and association with clinician well-being in clinical environments are lacking.
Objective
To evaluate the safety, use, and association with clinician burden of MedAgentBrief, an LLM-based agentic workflow for generating hospital course summaries, during prospective clinical deployment. Design, Setting, and Participants This single-arm prospective pilot quality improvement study encompassed hospital discharges at 1 academic inpatient medicine unit from August 1 to October 11, 2025, with baseline comparisons drawn from April 9 to July 31, 2025.
Intervention
A custom agentic LLM workflow using Gemini 2.5 Pro generated draft hospital course summaries nightly using patient history and physical and daily progress notes. Drafts were securely emailed to physicians daily for review and optional use. Main Outcomes and Measures The primary outcome was physician-reported potential for and severity of harm from unedited summaries (Agency for Healthcare Research and Quality Common Format Harm Scale). Secondary outcomes included use rate, error types (omissions, inaccuracies, and hallucinations), time spent in discharge summaries (electronic health record logs), and changes in cognitive burden (NASA Task Load Index; score range, 0-100, with higher scores indicating greater cognitive burden) and burnout (Stanford Professional Fulfillment Index Work Exhaustion Scale; score range, 0-4, with higher scores indicating greater burnout).
Results
Among 384 hospital discharges, the system generated 1274 summaries. Physicians used artificial intelligence (AI) content in 219 cases (57.0%). Feedback on 100 summaries (88 of 219 used summaries [40.2%] and 12 of 165 unused summaries [7.3%]) noted omissions (25 summaries [25.0%]) and inaccuracies (20 summaries [20.0%]) but rare hallucinations (2 summaries [2.0%]). Physicians rated 88 unedited summaries (88.0%) as having no harm potential and 1 (1.0%) as likely to cause moderate harm; no severe harm was reported. Mean physician burnout scores decreased significantly from before to after the intervention (1.75; 95% CI, 1.16-2.34 vs 1.20; 95% CI, 0.71-1.69; P = .03). Time savings were heterogeneous, with 5 of 7 physicians with matched baseline data (71.4%) seeing reductions in median documentation time; changes from baseline to pilot were up to 2.9 minutes, which was a nonsignificant difference (10.7 minutes; 95% CI, 7.4-13.3 minutes vs 7.8 minutes; 95% CI, 5.1-11.7 minutes; P = .13). Conclusions and Relevance In this study, an LLM-based agentic workflow produced hospital course summaries that were frequently used with minimal risk of harm identified. The intervention was associated with a reduction in physician burnout, supporting the viability of AI summarization to mitigate documentation burden.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Division of Computational Medicine, Stanford University, Stanford, California.
- Division of Hospital Medicine, Stanford University, Stanford, California.
- Technology and Digital Solutions, Stanford Health Care, Palo Alto, California.
- Department of Anesthesiology, Perioperative, and Pain Medicine, Stanford University, Stanford, California.
- Department of Biomedical Data Science, Stanford University, Stanford, California.
- Stanford Clinical Excellence Research Center, Stanford University, Stanford, California.
Zitieren
APA
Grolleau, F., Liang, A. S., Keyes, T., Ma, S. P., Lew, T., Huynh, T. R., Steele, N., Chung, P., Qin, P., Chandra, G., Wang, S. F., Mullen, E., Carpenter, L., Hoppenfeld, M., Morrin, M., Kyerematen, B. A., Ambers, N., Kotecha, N., Alsentzer, E., …, & Chen, J. H. (2026). Physician-Reported Safety Outcomes of AI-Generated Hospital Course Summaries. JAMA Network Open, 9(5), e2616556. https://doi.org/10.1001/jamanetworkopen.2026.16556
Vancouver
Grolleau F, Liang AS, Keyes T, Ma SP, Lew T, Huynh TR, et al. Physician-Reported Safety Outcomes of AI-Generated Hospital Course Summaries. JAMA Network Open. 2026;9(5):e2616556. doi:10.1001/jamanetworkopen.2026.16556
BibTeX
@article{Grolleau2026,
author = {Grolleau, François and Liang, April S and Keyes, Timothy and Ma, Stephen P and Lew, Thomas and Huynh, Tridu R and Steele, Natasha and Chung, Philip and Qin, Paige and Chandra, Gowri and Wang, Stephanie F and Mullen, Evan and Carpenter, Lauren and Hoppenfeld, Mita and Morrin, Matthew and Kyerematen, Baffour A and Ambers, Nerissa and Kotecha, Nikesh and Alsentzer, Emily and Hom, Jason and Shah, Nigam H and Schulman, Kevin and Chen, Jonathan H},
title = {Physician-Reported Safety Outcomes of AI-Generated Hospital Course Summaries},
journal = {JAMA Network Open},
year = {2026},
volume = {9},
number = {5},
pages = {e2616556},
doi = {10.1001/jamanetworkopen.2026.16556}
}
EUVIMED