Explainable machine learning for early detection of Escherichia coli urinary tract infections: integrating SHAP interpretation and bacterial epidemiology
Abstract
Background Escherichia coli is the predominant uropathogen in urinary tract infections (UTIs), but culture-based identification is time-consuming. This study aimed to develop an explainable, culture-independent model to distinguish E. coli from other uropathogens using routinely collected clinical data. Methods We retrospectively analyzed 308 hospitalized patients with culture-confirmed UTIs at Fuding Hospital, Fujian University of Traditional Chinese Medicine (January–December 2023), classified as E. coli (n = 158) or non–E. coli (n = 150). Species identification was performed using an automated microbiology system. Nineteen predictors (sex, urinary leukocyte grade, and 17 routine laboratory variables) were used. Associations with E. coli UTI were examined using univariate and multivariable logistic regression. A Random Forest (RF) classifier was developed with SHapley Additive exPlanations (SHAP) for interpretability. Data were split using a stratified 70/30 train–test split; 5-fold stratified cross-validation within the training set was used for hyperparameter tuning, and final performance (discrimination and calibration) was reported on the held-out test set. RF was additionally benchmarked against regularized logistic regression, calibrated linear SVM, and gradient boosting using the same protocol. Results E. coli accounted for 51.3% of isolates, followed by Enterococcus spp. (18.5%) and Klebsiella spp. (7.8%). Compared with non–E. coli cases, E. coli infections were…
Read the paper
Related studies
- Length of stay and mortality associated with healthcare-associated urinary tract infections: a multi-state model
- Development and Validation of a Calculator for Estimating the Probability of Urinary Tract Infection in Young Febrile Children
- Effect of Missing Data Imputation on Deep Learning Prediction Performance for Vesicoureteral Reflux and Recurrent Urinary Tract Infection Clinical Study
- Probiotics [LGG-BB12 or RC14-GR1] versus placebo as prophylaxis for urinary tract infection in persons with spinal cord injury [ProSCIUTTU]: a randomised controlled trial
- Randomized Clinical Trial Using Sterile Single Use and Reused Polyvinylchloride Catheters for Intermittent Catheterization with a Clean Technique in Spina Bifida Cases: Short-Term Urinary Tract Infection Outcomes
- Urinary tract infection after stroke: A narrative review
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.