Performance of an artificial intelligence model for evaluation of unnecessary central lines, Northern California 2025
Jenna M Wick1, Apoorva Bhaskara1, Wajeeha Tariq1
1https://ror.org/03mtd9a03Stanford University School of Medicine, USA.
Infection Control and Hospital Epidemiology
|April 27, 2026
Abstract:
We used a large language model integrated in the electronic health record to evaluate unnecessary central lines. It had a 16% sensitivity and 99% specificity for detecting unnecessary lines. Although it missed many unnecessary lines, the high specificity suggests potential as a tool where human review is not feasible.
More Related Videos
09:57A Protocol to Set Up Needle-Free Connector with Positive Displacement on Central Venous Catheter in Intensive Care Unit
Published on: July 13, 2019
12.9K
05:04Author Spotlight: Evaluating Clinicians' Adoption of Ultrasound-Guided Vascular Cannulation Through Simulation Training
Published on: August 9, 2024
1.9K
