Main Library
Researchers at University of California San Diego School of Medicine found that large language models (LLMs) can accurately process hospital quality measures, achieving 90% agreement with manual reporting.
By addressing the complex demands of quality measurement, the researchers believe the findings pave the way for more efficient and reliable approaches to healthcare quality reporting.
The results of the pilot study were published in the Oct. 21, 2024 online edition of the New England Journal of Medicine (NEJM) AI.
Researchers of the study, in partnership with the Joan and Irwin Jacobs Center for Health Innovation at UC San Diego Health (JCHI), found that LLMs can perform accurate abstractions for complex quality measures, particularly in the context of the Centers for Medicare & Medicaid Services (CMS) SEP-1 measure for severe sepsis and septic shock.