The study compared six machine learning models to predict myofascial pelvic pain syndrome (MPPS) in Chinese women at a single center in a retrospective design. The analysis included 1,136 women with MPPS and 1,448 healthy women who underwent pelvic floor screening during the same period. The six algorithms tested were logistic regression, support vector machine (SVM), random forest (RF), XGBoost, LightGBM, and AdaBoost, trained using 5-fold cross-validation and grid search. The performance of the models was evaluated by confusion matrix, accuracy, fit, F1 score, overall accuracy and ROC curves. The accuracy of the models was 0.77 for logistic regression, 0.80 for SVM, 0.91 for RF, 0.89 for XGBoost, 0.88 for LightGBM, and 0.81 for AdaBoost. The average areas under the ROC curves (AUC) were 0.670 for logistic regression, 0.672 for SVM, 0.956 for RF, 0.951 for XGBoost, 0.952 for LightGBM, and 0.836 for AdaBoost. The best result was achieved by the random forest (RF) model, with RF, XGBoost and LightGBM having AUC > 0.95.