Machine Learning Algorithms for Predicting Urinary Tract Infections: Integration of Demographic Data and Dipstick Reflectance Results
Machine learning models, particularly the CatBoost Classifier, demonstrate high accuracy and offer a promising tool to aid clinicians in UTI diagnosis. Unlike traditional culture methods, these models deliver results within an hour. Further external validation with an independent dataset and prospective studies assessing the impact on antibiotic prescribing practices is recommended.
Authors
- Julien Favresse (ORCID: https://orcid.org/0000-0002-9805-049X)
- Benjamin Lardinois (ORCID: https://orcid.org/0000-0003-2671-1196)
- Julien Cabo (ORCID: https://orcid.org/0000-0001-5630-7114)
- Marc Elsen
- Julie Cadrobbi
- Sander De Bruyne (ORCID: https://orcid.org/0000-0002-9041-4404)
- Kim Laffineur
- Maxime Bosse (ORCID: https://orcid.org/0009-0005-6069-8118)
- Jonathan Douxfils
- Liam Roelandts
Institutions
- University of Namur (BE)
- Ghent University Hospital (BE)
- Ghent University (BE)
- Comagine Health (US)
- Jessa Hospital (BE)
- Clinique Saint-Joseph (BE)
Publication Details
- Journal
- Clinical Chemistry
- Published
- 2025-08-26
- DOI
- https://doi.org/10.1093/clinchem/hvaf088
- Citations
- 3
- Primary Topic
- Bacterial Identification and Susceptibility Testing
- Type
- article
- Field-Weighted Citation Impact
- 3.96