Advancing ESWL Outcome Predictions in X-Ray and CT Through Sophisticated Feature Selection

Ureteral stones, a prevalent type of urinary stone, form within the ureter, causing severe pain and hematuria. Extracorporeal shock wave lithotripsy (ESWL) and transurethral lithotripsy (TUL) are the primary treatments. Although ESWL is less invasive and requires shorter hospital stays, its lower success rate compared to TUL, often necessitates additional treatments, increasing both the physical and financial burdens on patients. This study aims to enhance the accuracy of predicting ESWL outcomes by using advanced machine learning methods to analyze both CT and X-ray images together with clinical findings. Particularly, X-ray images, which have been less frequently in past studies, are anticipated to provide detailed analytical features. Addressing the limitations of current predictive methods, which often suffer from excessive irrelevant features and low interpretability, this study introduces three sophisticated feature selection approaches: P-value, AUC, and SHAP value. These approaches aim to enhance both model interpretability and predictive performance. Several machine learning algorithms were evaluated, including decision tree, K-nearest neighbors, random forest, logistic regression, SVM, adaboost, and Gaussian NB. Results from 139 subjects with ESWL show that logistic regression and SVM perform optimally, with SHAP-based feature selection significantly boosting outcomes, demonstrated by the increase in the AUC from 0.791 to 0.845 for logistic regression, and from 0.750 to 0.764 for SVM. Furthermore, the study decreases the number of features used in the model from 55 to 19, simplifying the prediction process. However, features extracted from X-ray images showed limited effectiveness.