EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Guillermo Rodriguez-Nava iD, Goar Egoryan iD, Katherine E Goodman iD, Daniel J Morgan, Jorge L Salinas iD

Infection Control & Hospital Epidemiology · 2025-03 · 46 (3) · 305-308

DOI: 10.1017/ice.2024.164 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Infection Control & Hospital Epidemiology, online erschienen am 30.10.2024. Verfasst von Guillermo Rodriguez-Nava und 4 weiteren Autor:innen. Beteiligte Einrichtung: Division of Infectious Diseases & Geographic Medicine, Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA. Hauptthemen laut MEDLINE: Catheter-Related Infections, Catheterization, Central Venous, Bacteremia, Electronic Health Records. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 10 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: AHRQ HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Catheter-Related InfectionsCatheterization, Central VenousBacteremiaElectronic Health RecordsCross InfectionHumansLarge Language Models

Autor:innen und Institutionen

  • Division of Infectious Diseases & Geographic Medicine, Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA.
  • Division of Oncology, Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA.
  • 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.
  • VA Maryland Healthcare System, Baltimore, MD, USA.

ORCID-Profile: Guillermo Rodriguez-Nava, Goar Egoryan, Katherine E Goodman, Jorge L Salinas

Förderung

  • AHRQ HHS

Zitieren

APA

Rodriguez-Nava, G., Egoryan, G., Goodman, K. E., Morgan, D. J., & Salinas, J. L. (2025). Performance of a large language model for identifying central line-associated bloodstream infections (CLABSI) using real clinical notes. Infection Control & Hospital Epidemiology, 46(3), 305-308. https://doi.org/10.1017/ice.2024.164

Vancouver

Rodriguez-Nava G, Egoryan G, Goodman KE, Morgan DJ, Salinas JL. Performance of a large language model for identifying central line-associated bloodstream infections (CLABSI) using real clinical notes. Infection Control & Hospital Epidemiology. 2025;46(3):305-308. doi:10.1017/ice.2024.164

BibTeX
@article{RodriguezNava2025,
  author = {Rodriguez-Nava, Guillermo and Egoryan, Goar and Goodman, Katherine E and Morgan, Daniel J and Salinas, Jorge L},
  title = {Performance of a large language model for identifying central line-associated bloodstream infections (CLABSI) using real clinical notes},
  journal = {Infection Control & Hospital Epidemiology},
  year = {2025},
  volume = {46},
  number = {3},
  pages = {305--308},
  doi = {10.1017/ice.2024.164}
}
Kostenlos starten →