fig2

Figure 2. Performance evaluation of seven ML models. (A) ROC curves of seven ML models in the testing set; (B) ROC curves of seven ML models in the training set; (C) Calibration curves of the seven models in the testing set, with the Brier score indicated for each model; (D) DCA of the seven models in the testing set, demonstrating the net clinical benefit across different threshold probabilities. ML: Machine learning; ROC: receiver operating characteristic; AUC: area under the curve; CI: confidence interval; DCA: decision curve analysis; SVM: support vector machine; ANN: artificial neural network; LightGBM: Light Gradient Boosting Machine; XGBoost: Extreme Gradient Boosting.