Fig. 5

The discrimination and calibration performance of the XGBoost model. Plot (A) showed the ROC curves of the XGBoost model in the training set and validation set, respectively (AUC = 0.7854 versus 0.7941). Calibration curves of the XGBoost model in the training set (B) and validation set (C). AUC, area under the curve; ROC, receiver operating characteristic. XGBoost, extreme gradient boosting