Large Language Model Assistant for Emergency Department Discharge Documentation

Can an on-site large language model (LLM) assistant help emergency physicians write discharge notes faster without compromising the quality of the notes?In this comparative effectiveness study including 300 manual notes, 300 LLM drafts, and 300 LLM-assisted notes from 50 cases, the LLM-assisted notes were more complete, correct, concise, and clinically useful than manual notes. The median writing time decreased from 69.5 to 32.0 seconds with LLM assistance.These findings suggest that LLM assistance is a promising solution for generating high-quality discharge notes with lesser burden on emergency physicians.

Corresponding Authors: Seng Chan You, MD, PhD, Department of Biomedical Systems Informatics (chandryou@yuhs.ac), and Ji Hoon Kim, MD, MPH, PhD, Department of Emergency Medicine (JICHOON81@yuhs.ac), Yonsei University College of Medicine, Yonsei-ro 50-1, Seoul 03722, Republic of Korea.

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.