Explainable machine learning for early detection of Escherichia coli urinary tract infections: integrating SHAP interpretation and bacterial epidemiology
<i>E. coli</i> remains the predominant pathogen among hospitalized UTIs. An explainable RF model using routine laboratory variables provided moderate, reproducible discrimination of <i>E. coli</i> vs non-<i>E. coli</i> UTIs and may support earlier decision-making while awaiting culture results.
Authors
- Yingying Jiang (ORCID: https://orcid.org/0000-0002-3688-1052)
- Pan ChuYing
- Juan Shi (ORCID: https://orcid.org/0000-0001-8554-2383)
- Jinbao Shi
- Junhua Zhang (ORCID: https://orcid.org/0000-0002-8936-3822)
- Yizhou Zheng (ORCID: https://orcid.org/0000-0001-5939-7549)
- Ling-Hui Yao
- Ying Zhu
Institutions
- Fujian University of Traditional Chinese Medicine (CN)
- Anyang Hospital of Traditional Chinese Medicine (CN)
Publication Details
- Journal
- Frontiers in Cellular and Infection Microbiology
- Published
- 2026-02-13
- DOI
- https://doi.org/10.3389/fcimb.2026.1740707
- Primary Topic
- Urinary Tract Infections Management
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Fujian University of Traditional Chinese Medicine