About The Study: In this cohort study of 1,600 emergency medicine patient medical records, large language model (LLM)-generated emergency medicine-to-inpatient handoff notes were determined superior compared with physician-written summaries via conventional automated evaluation methods, but marginally inferior in usefulness and safety via a novel evaluation framework. This study suggests the importance of a physician-in-loop implementation design for this model and demonstrates an effective strategy to measure pre-implementation patient safety of LLM models.
Corresponding Author: To contact the corresponding author, Vince Hartman, MS, email vince@abstractivehealth.com.
To access the embargoed study: Visit our For The Media website at this link https://media.jamanetwork.com/
(doi:10.1001/jamanetworkopen.2024.48723)
Editor’s Note: Please see the article for additional information, including other authors, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.
Embed this link to provide your readers free access to the full-text article This link will be live at the embargo time http://jamanetwork.com/journals/jamanetworkopen/fullarticle/10.1001/jamanetworkopen.2024.48723?utm_source=For_The_Media&utm_medium=referral&utm_campaign=ftm_links&utm_term=120324
Journal
JAMA Network Open