article · BJUI Compass
Urine culture results typically take between 24 and 72 hours to become available, creating uncertainty during initial clinical assessments. Machine-learning models were developed and internally validated to estimate the probability of urine-culture positivity using routinely collected data from 2,530 paired urinalysis and culture records collected across three university hospitals. Thirteen supervised algorithms were evaluated using a stratified sample split. Several gradient-boosting methods achieved comparable discriminatory ability, with CatBoost yielding an area under the curve of 0.858. At the reported operating threshold, the model achieved a specificity of 0.930, a sensitivity of 0.587, a positive predictive value of 0.766, and a negative predictive value of 0.851. Because culture positivity does not equate to symptomatic urinary tract infection, external validation grouped by patient and centre is required before these models can be used in clinical practice.
Delays of up to three days for urine culture results make the early assessment of suspected urinary infections challenging. Estimating culture probabilities from standard urinalysis could help healthcare providers assess diagnostic risk earlier. However, positive laboratory cultures do not always represent active disease, making rigorous testing against patient outcomes essential before tools of this type can safely influence clinical decision-making.
The models could potentially be incorporated into diagnostic decision-support software for hospital clinicians reviewing routine urinalysis results. The technology currently sits at an early, internal validation stage based on retrospective laboratory records. Commercial application remains distant, as deployment will require patient-grouped external validation, clinical safety trials, and direct evidence that the tool can support antibiotic stewardship without compromising patient care.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Objectives This study aim to develop, compare and internally validate machine‐learning models for predicting urine‐culture positivity in patients who had both urinalysis and culture ordered and to explore descriptive probability strata. Post hoc secondary analyses examined age subgroups, the incremental contribution of text‐derived features, simpler comparators and calibration. Patients and Methods Urine culture results are typically unavailable for 24–72 h, creating uncertainty during initial assessment, and machine‐learning models may help estimate the probability of culture positivity from routinely collected data. This retrospective study included 2530 urine‐sample records originating from three university hospitals. Eligibility was based on paired urinalysis and urine culture records rather than symptom‐based diagnostic criteria for urinary tract infection (UTI). Thirteen supervised algorithms were evaluated using a stratified 75:25 sample‐record split. This constituted internal validation; records were not grouped by patient or centre because stable cross‐centre patient, centre and collection‐date identifiers were unavailable. Results Several gradient‐boosting algorithms showed similar discrimination. CatBoost had the numerically highest test‐set AUC of 0.858 (95% CI 0.829–0.892), but its AUC did not differ significantly from gradient boosting or XGBoost. At the reported operating threshold, sensitivity was 0.587 (95% CI 0.513–0.662), specificity 0.930 (0.903–0.951), PPV 0.766 (0.693–0.833) and NPV 0.851 (0.821–0.882). Exploratory probability strata separated records with different observed rates of culture positivity, but their clinical utility and safety were not evaluated. Conclusion Machine‐learning models discriminated between culture‐positive and culture‐negative sample records in a sample‐level internal validation. Culture positivity is not synonymous with symptomatic or clinically significant UTI. The findings support further evaluation as diagnostic risk‐estimation tools after urinalysis results are available. They do not establish clinical UTI or the safety or effectiveness of starting, withholding or delaying antibiotics. Patient‐grouped external validation with clinical outcomes is required before clinical use.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1002/bco2.70280
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
