Machine learning models for identifying urinary incontinence in women with a history of hysterectomy using basic demographic and clinical characteristics: A cross-sectional study

Abstract

Background

Urinary incontinence (UI) in women with a history of hysterectomy represents a significant global health concern. It is crucial to clarify the association between hysterectomy for benign indications and UI to avoid unnecessary surgery.

Objective

This study aimed to develop a machine learning (ML) model to identify factors associated with UI in women with a history of hysterectomy.

Methods

We analyzed 2021 patients from the National Health and Nutrition Examination Survey (NHANES) database who underwent hysterectomy for benign indications as our derivation cohort. Thirteen demographic and clinical features were evaluated: age, educational, anthropometric measurements (height, weight, waist), medical history diabetes mellitus (DM), and reproductive history. Six ML algorithms were employed: logistic regression (LR), naïve Bayes (NB), multilayer perceptron (MLP), extreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM). External validation was performed on a cohort consisting of 556 patients from the Second Qilu Hospital of Shandong University. To improve interpretability, the predictive process was graphically illustrated employing a nomogram and SHapley Additive exPlanations (SHAP). Finally, the model was deployed as an online clinical decision support platform for applications.

Results

 A comparison of receiver operating characteristic (ROC) curves using LR as the reference model revealed no statistically significant differences across the six ML algorithms. In the internal validation cohorts, the models achieved area-under-the-curve (AUC) values of 0.753–0.763 and accuracies between 0.627 and 0.664. This predictive performance was sustained in the external-validation cohort, with AUC values ranging from 0.702 to 0.718 and accuracies ranging from 0.661 to 0.697.

Conclusion

 Our findings demonstrated that ML models could effectively identify UI in women with a history of hysterectomy. This approach, facilitated by the nomogram and online tool, enhanced the feasibility and accessibility of identifying women at risk.