Machine learning-assisted prediction of positive urine cultures using urinalysis and hemogram data: A retrospective cohort study

Machine learning-assisted prediction of positive urine cultures using urinalysis and hemogram data:A retrospective cohort study U rinary tract infections (UTIs) are among the most prev- alent bacterial infections encountered in clinical practice, particularly affecting women.They impose a significant burden on both individual health and healthcare systems worldwide.If left untreated or inadequately managed, UTIs can lead to serious complications, including kidney damage and sepsis, while also contributing to the rise in antimicrobial resistance (AMR) rates [1,2].The diagnosis of UTIs involves a combination of clinical evaluation, laboratory tests, and advanced diagnostic techniques.Patients commonly present with symptoms such as dysuria, increased urinary frequency, urgency, and, in some cases, hematuria.Initial assessment typically includes microscopic urinalysis and dipstick testing, which together constitute standard urinalysis (UA).Although widely used, microscopic urinalysis is time-consuming and prone to human error.When combined Objectives: Urinary tract infections (UTIs) are common and often lead to unnecessary urine culture testing, increasing costs and delaying treatment.This study aims to develop a machine learning (ML) model using urinalysis and hemogram data to predict urine culture positivity and reduce unnecessary testing.Methods: We retrospectively analyzed data from 12,433 patients who underwent urinalysis, urine culture, complete blood count, and CRP testing.After preprocessing and exclusion criteria, data were split into training, test, and validation sets.H 2 O AutoML was employed to develop and evaluate various ML algorithms. Results:The gradient boosting model demonstrated an AUC-ROC of 0.822 with high sensitivity (73.8%) and negative predictive value (90.4%), making it reliable in ruling out negative cases.Urinary leukocytes, nitrite, and bacterial count were identified as top predictors.Conclusion: ML-based models can improve diagnostic accuracy and reduce unnecessary urine cultures.These models have the potential to be integrated into clinical workflows to enhance cost-effectiveness and minimize empirical antibiotic use.