Table 2.

The performance of predictive models on seven ML algorithms.

Models	Training cohort					Validation cohort
	AUC	Accuracy	Recall	Precision	F1-score	AUC	Accuracy	Recall	Precision	F1-score
XGBoost	1.00	0.99	1.00	0.97	0.99	0.69	0.66	0.46	0.47	0.47
GBM	0.76	0.62	0.78	0.41	0.54	0.71	0.62	0.72	0.44	0.55
RF	0.93	0.76	0.97	0.55	0.70	0.74	0.63	0.72	0.46	0.56
KNN	0.77	0.63	0.81	0.42	0.56	0.72	0.63	0.74	0.46	0.56
SVM	0.64	0.49	0.73	0.33	0.45	0.66	0.53	0.78	0.39	0.52
DT	0.70	0.72	0.50	0.52	0.51	0.65	0.66	0.42	0.48	0.45
LR	0.69	0.58	0.76	0.38	0.51	0.69	0.56	0.74	0.41	0.53

XGBoost, Extreme Gradient Boosting; GBM, Gradient Boosting Machine; RF, Random Forest; KNN, k-Nearest Neighbors; SVM, Support Vector Machines; DT, Decision Tree; LR, Logistic Regression.