Comparing Generative Artificial Intelligence vs Experts for Detection of Catheter-Associated Urinary Tract Infection
A retrospective cohort study compared generative artificial intelligence (GenAI) versus infection control expert for catheter-associated urinary tract infection (CAUTI) detection. Sensitivity was 95.2% (20/21), and specificity was 76.2% (16/21), improving to 90% with expert review of GenAI output. GenAI is a promising tool to assist in CAUTI surveillance.
Authors
- Shatha Alshanqeeti (ORCID: https://orcid.org/0000-0003-4691-5743)
- Jonathan Baghdadi (ORCID: https://orcid.org/0000-0002-2442-0654)
- Kelly McDermott (ORCID: https://orcid.org/0000-0002-2410-538X)
- Katherine E Goodman (ORCID: https://orcid.org/0000-0003-2851-775X)
- Westyn Branch‐Elliman (ORCID: https://orcid.org/0000-0002-9658-5124)
- Anthony D. Harris (ORCID: https://orcid.org/0000-0003-2193-1560)
- Daniel J. Morgan (ORCID: https://orcid.org/0000-0002-2933-6208)
- Karen C. Coffey
- A. E. Guzman
Institutions
- University of Maryland, Baltimore (US)
- West Los Angeles College (US)
- University of California, Los Angeles (US)
- King Saud University (SA)
- VA West Los Angeles Medical Center (US)
- Institute of Human Virology (NG)
- VA Greater Los Angeles Healthcare System (US)
- VA Maryland Health Care System (US)
- University of Maryland, College Park (US)
Publication Details
- Journal
- Clinical Infectious Diseases
- Published
- 2025-09-04
- DOI
- https://doi.org/10.1093/cid/ciaf486
- Citations
- 4
- Primary Topic
- Urinary Tract Infections Management
- Type
- article
- Field-Weighted Citation Impact
- 5.42