Medical Record Abstraction for Quality Improvement in Sepsis Care Using Artificial Intelligence

Can automated assessment of a complex care quality measure with more timely feedback improve measure performance?In this cluster randomized trial of 66 physicians treating 301 patients, the use of a large language model to automatically assess a complex measure for severe sepsis and septic shock and deliver targeted feedback improved quality metric performance. No change in 30-day mortality was observed among patients with sepsis cared for by physicians in the control and intervention groups.These findings suggest that artificial intelligence may enable quality clinical integration to address limitations in current quality measurement.

Corresponding Authors: Aaron Boussina, PhD, Division of Biomedical Informatics, University of California, San Diego, 9500 Gilman Dr, La Jolla, CA 92093 (aboussina@health.ucsd.edu), and Gabriel Wardi, MD, Department of Emergency Medicine, University of California, San Diego, 200 W Arbor Dr, San Diego, CA 92103 (gwardi@health.ucsd.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.