Use of a large language model integrated within the electronic medical record for the evaluation of surgical site infections – Northern California, 2025
Open Access
- 13 April 2026
- journal article
- research article
- Published by Cambridge University Press (CUP) in Infection Control & Hospital Epidemiology
- Vol. 47 (6) , 633-635
Abstract
Our study evaluated a large language model (gpt-4o-mini) for surgical site infection (SSI) adjudication, achieving 100% sensitivity but 69.4% specificity. While reducing the manual screening workload by 66%, the agent generated many false positives, underscoring the need for refined models to improve specificity without compromising accuracy.Keywords
This publication has 6 references indexed in Scilit:
- Unleashing the potential of prompt engineering for large language modelsPatterns, 2025
- Testing and Evaluation of Health Care Applications of Large Language ModelsJAMA, 2025
- Performance of a large language model for identifying central line-associated bloodstream infections (CLABSI) using real clinical notesInfection Control & Hospital Epidemiology, 2024
- Changes in Prevalence of Health Care–Associated Infections in U.S. HospitalsNew England Journal of Medicine, 2018
- Consensus paper on the surveillance of surgical wound infections. The Society for Hospital Epidemiology of America; The Association for Practitioners in Infection Control; The Centers for Disease Control; The Surgical Infection Society.1992
- Consensus Paper on the Surveillance of Surgical Wound InfectionsInfection Control & Hospital Epidemiology, 1992