Performance of a large language model for identifying central line-associated bloodstream infections (CLABSI) using real clinical notes.

Autor:	Rodriguez-Nava G; Division of Infectious Diseases & Geographic Medicine, Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA., Egoryan G; Division of Oncology, Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA., Goodman KE; Department of Epidemiology and Public Health, University of Maryland School of Medicine, Baltimore, MD, USA.; University of Maryland Institute for Health Computing, Bethesda, MD, USA., Morgan DJ; Department of Epidemiology and Public Health, University of Maryland School of Medicine, Baltimore, MD, USA.; VA Maryland Healthcare System, Baltimore, MD, USA., Salinas JL; Division of Infectious Diseases & Geographic Medicine, Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA.
Jazyk:	angličtina
Zdroj:	Infection control and hospital epidemiology [Infect Control Hosp Epidemiol] 2024 Oct 30, pp. 1-4. Date of Electronic Publication: 2024 Oct 30.
DOI:	10.1017/ice.2024.164
Abstrakt:	We evaluated one of the first secure large language models approved for protected health information, for identifying central line-associated bloodstream infections (CLABSIs) using real clinical notes. Despite no pretraining, the model demonstrated rapid assessment and high sensitivity for CLABSI identification. Performance would improve with access to more patient data.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu