Development and construction of OAB risk prediction model based on machine learning among US women: The national health and nutrition examination survey,2011-2018

Guoqiang HuangShuangquan Lin^*

• Second Affiliated Hospital of Nanchang University, Nanchang, China

Overactive bladder (OAB) is a prevalent condition, particularly among women, yet traditional prediction methods remain limited. This study leveraged machine learning and data from the National Health and Nutrition Examination Survey (NHANES) to develop a comprehensive risk prediction model for female OAB.This cross-sectional study analyzed data from 7,884 participants across four consecutive cycles (2011-2018) of the NHANES. Lasso regression and univariate and multivariate logistic regression analyses were applied to identify key variables in the training set. Five machine learning (ML) models were developed to predict OAB risk in women. The SHAP (SHapley Additive exPlanations) method interpreted the optimal model, and restricted cubic spline (RCS) curves were used for dose-response analysis.Five variables were identified as significant predictors. Among the five ML models, XGBoost demonstrated the highest predictive performance. The XGBoost model achieved an AUROC of 0.730 (95% CI: 0.716-0.744) in the training set and 0.695 (95% CI: 0.673-0.718) in the test set, indicating good predictive capability. SHAP analysis identified age, body mass index (BMI), and the poverty-to-income ratio (PIR) as the top three contributors to OAB risk. Both RCS and SHAP analyses revealed a positive association of age and BMI with OAB risk and a negative association with PIR.Additionally, RCS showed that the risk of OAB was higher with an earlier age at menarche and a greater number of vaginal deliveries.Integrating ML with SHAP interpretability provides a robust predictive tool for OAB, facilitating early identification and clinical management.