Evaluating Hospital Course Summarization by an Electronic Health Record–Based Large Language Model

When asked to revise hospital courses (HCs) toward a quality standard, are there differences in how many edits physicians make to large language model (LLM)–generated HCs compared with physician-generated HCs?This quality improvement study of 100 general medicine admissions found that physicians edited a statistically significantly smaller percentage of LLM-generated HCs than physician-generated HCs (mean 31.5% vs 44.8%, respectively).These findings suggest LLM HCs were of higher quality than physician HCs and would be feasible to implement into practice.

Corresponding Author: William R. Small, MD, MBA, NYU Grossman School of Medicine, 550 First Ave, New York, NY 10016 (will.small@nyulangone.org).

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.