The Best of Both Worlds: How Combining a Large Language Model and a Rule-Based Algorithm Makes Catheter-Associated Urinary Tract Infection Surveillance More Efficient
Clinical Infectious Diseases · 23.07.2026 · 83 (1) · e120-e126
DOI: 10.1093/cid/ciag301 ↗Kurz gefasst
Fachartikel in der Zeitschrift Clinical Infectious Diseases, online erschienen am 14.05.2026. Verfasst von Joshua Nordman und 16 weiteren Autor:innen. Beteiligte Einrichtung: Division of Infectious Diseases, Washington University School of Medicine, St.Louis, Missouri, USA. Hauptthemen laut MEDLINE: Urinary Tract Infections, Catheter-Related Infections, Large Language Models, Algorithms. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Washington University/BJC Healthcare Big Ideas Healthcare Innovation Competition, Patient Safety Technology Challenge, Jewish Healthcare Foundation.
Themen: Katheterassoziierte Infektionen, Künstliche Intelligenz in der Pflege
Abstract (Originalsprache)
Background
Catheter-associated urinary tract infection (CAUTI) surveillance is critical for patient safety. Many healthcare systems use electronic algorithms to flag candidate infection events but still require manual chart review to confirm CAUTI cases. We evaluated the use of a large language model (LLM) to enhance CAUTI surveillance.
Methods
We analyzed 919 potential CAUTI cases flagged by the electronic surveillance algorithm at Barnes-Jewish Hospital from 2021 to 2024. These cases were previously classified as 291 CAUTIs and 628 non-CAUTIs by trained infection preventionists (IPs). Several approaches for applying the National Healthcare Safety Network (NHSN) CAUTI definition after extracting clinical data from the electronic medical record (EMR) were compared.
Results
Most patients were female (61.6%) with a median age 68 years (IQR 58, 77). Combining rule-based logic with Clinical Entity Augmented Retrieval (CLEAR) input into an LLM achieved the highest sensitivity (90.0%) and specificity (93.5%). Adjustment of false negatives and false positives after expert adjudication showed sensitivity of 93.6% and specificity of 98.6%. Chart review of false negatives revealed that disagreement with the gold standard mainly occurred due to missing symptom information in clinical documentation provided to the model.
Conclusions
Augmenting the existing algorithmic approach with LLM capabilities significantly enhances CAUTI surveillance and may improve efficiency by reducing the amount of time IPs spend performing manual chart review. Further improvements could be made by optimizing the clinical information presented to the model.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Division of Infectious Diseases, Washington University School of Medicine, St.Louis, Missouri, USA.
- Division of Computational and Data Sciences, Washington University in St.Louis, St. Louis, Missouri, USA.
- Institute for Informatics, Data Science, and Biostatistics, Washington University School of Medicine, St.Louis, Missouri, USA.
- Center for Clinical Excellence, BJC Healthcare, St.Louis, Missouri, USA.
- Department of Computer Science and Engineering, Washington University in St.Louis, St. Louis, Missouri, USA.
- Division of Infectious Diseases, University of Arizona College of Medicine, Phoenix, Arizona, USA.
ORCID-Profile: Joshua Nordman, Claire Najjuuko, Nicholas Jeschke, Maria Cristina Vazquez Guillamet, Carole Leone, Megan Dethloff, Jonas Marschall, Abby Sung
Förderung
- Washington University/BJC Healthcare Big Ideas Healthcare Innovation Competition
- Patient Safety Technology Challenge
- Jewish Healthcare Foundation
Zitieren
APA
Nordman, J., Najjuuko, C., Jeschke, N., Snyders, R. E., Vazquez Guillamet, M. C., Shapiro, J., Leone, C., Dethloff, M., Babcock, H., Reich, P., Whalen, K., Zhang, L., Luong, L., Lu, C., Atkinson, A., Marschall, J., & Sung, A. (2026). The Best of Both Worlds: How Combining a Large Language Model and a Rule-Based Algorithm Makes Catheter-Associated Urinary Tract Infection Surveillance More Efficient. Clinical Infectious Diseases, 83(1), e120-e126. https://doi.org/10.1093/cid/ciag301
Vancouver
Nordman J, Najjuuko C, Jeschke N, Snyders RE, Vazquez Guillamet MC, Shapiro J, et al. The Best of Both Worlds: How Combining a Large Language Model and a Rule-Based Algorithm Makes Catheter-Associated Urinary Tract Infection Surveillance More Efficient. Clinical Infectious Diseases. 2026;83(1):e120-e126. doi:10.1093/cid/ciag301
BibTeX
@article{Nordman2026,
author = {Nordman, Joshua and Najjuuko, Claire and Jeschke, Nicholas and Snyders, Rachael E and Vazquez Guillamet, Maria Cristina and Shapiro, Jordan and Leone, Carole and Dethloff, Megan and Babcock, Hilary and Reich, Patrick and Whalen, Kenneth and Zhang, Lucy and Luong, Lan and Lu, Chenyang and Atkinson, Andrew and Marschall, Jonas and Sung, Abby},
title = {The Best of Both Worlds: How Combining a Large Language Model and a Rule-Based Algorithm Makes Catheter-Associated Urinary Tract Infection Surveillance More Efficient},
journal = {Clinical Infectious Diseases},
year = {2026},
volume = {83},
number = {1},
pages = {e120--e126},
doi = {10.1093/cid/ciag301}
}
EUVIMED