Predicting Urine Culture Outcomes in Adult Patients Using Machine Learning with the Aim of Reducing Unnecessary Urine Cultures
We presented an XGBoost model to predict urine culture outcomes, which retained its performance during external validation. Contrary to most other models, adult patients of all ordering departments were included, which impedes future implementation. An additional external validation and prospective evaluation will be necessary before implementation with the aim of reducing unnecessary urine cultures.
Authors
- Martijn C. Schut (ORCID: https://orcid.org/0000-0003-4591-9646)
- Anneroos W. Boerman
- Victoria A. Janes (ORCID: https://orcid.org/0000-0001-6574-1449)
- Prabath W.B. Nanayakkara (ORCID: https://orcid.org/0000-0002-1555-3682)
- Róbert de Jonge (ORCID: https://orcid.org/0000-0002-3454-0094)
- Hans H M Schotman
- Allerdien Visser (ORCID: https://orcid.org/0000-0001-8642-7520)
- Manon M van Ingen
Institutions
- Amsterdam Neuroscience (NL)
- GGD Amsterdam (NL)
- Public Health Service of Amsterdam (NL)
- Amsterdam University Medical Centers (NL)
- University of Amsterdam (NL)
- Amsterdam UMC Location Vrije Universiteit Amsterdam (NL)
Publication Details
- Journal
- The Journal of Applied Laboratory Medicine
- Published
- 2025-10-23
- DOI
- https://doi.org/10.1093/jalm/jfaf131
- Primary Topic
- Urinary Tract Infections Management
- Type
- article
- Field-Weighted Citation Impact
- 0.00