Fig. 1. Model performance for four different algorithms (including Extreme gradient boosting (XGB), Decision tree (DT), Logistic regression (LR), and Support vector machine (SVM)), with default parameter settings (a) and with tuned parameter settings (b).

Default_LR, Default_SVM, Default_DT, and Default_XGB represent ML algorithms using default parameter settings. Tuning_LR, Tuning_SVM, Tuning_DT, and Tuning_XGB represent ML algorithms using tuned parameter settings. AUC_train, AUC_validation, and AUC_test, represent AUC score on train, validation, and test dataset. Recall_train, Recall_validation, and Recall_test, represent recall score on train, validation, and test dataset. Precision_train, Precision_validation, and Precision_test, represent precision score on train, validation, and test dataset. Accuracy_train, Accuracy_validation, and Accuracy_test, represent accuracy score on train, validation, and test dataset.