Model May Help Identify Women at Risk for Overactive Bladder

THURSDAY, Aug. 20, 2026 (HealthDay News) — A machine learning model can predict overactive bladder (OAB) risk in women, using common reproductive and sociodemographic data, according to a study published online Aug. 12 in JMIR Medical Informatics.

Guoqiang Huang, M.D., and Shuangquan Lin, Ph.D., M.D., both from the Second Affiliated Hospital of Nanchang University in China, developed and validated a machine learning-based model to predict OAB risk in women, incorporating reproductive and sociodemographic factors. The model was developed based on data from 7,884 participants across four consecutive cycles (2011 to 2018) of the National Health and Nutrition Examination Survey.

The researchers identified five variables as significant predictors. Of the 11 machine learning models, the random forest (RF) showed the highest predictive performance, achieving an area under the receiver operating characteristic curve of 0.8536 in the training set and 0.6999 in the test set, indicating moderate predictive capability. The top three contributors to OAB risk in a Shapley Additive Explanations (SHAP) analysis were age, body mass index (BMI), and number of vaginal deliveries. There was a positive association for age and BMI with OAB risk and a negative association for the ratio of family income to poverty threshold with OAB risk in both restricted cubic spline (RCS) and SHAP analyses. RCS also demonstrated higher OAB risk with an earlier age at menarche and a greater number of vaginal deliveries.

“The RF model demonstrated good predictive accuracy and practical clinical applicability, serving as a noninvasive, cost-effective tool for early screening and risk stratification in community health and primary outpatient settings,” the authors write.

Abstract/Full Text