Table 3.

Discrimination indicators of the predictive models in the training and validation sets.

Model	AUC ( 95% CI)	Accuracy	Precision	Sensitivity	Specificity	F1 score	Youden's J	PPV	NPV
Logistic	0.859(0.786~0.924)	0.765	0.750	0.643	0.850	0.692	0.493	0.750	0.773
Decision Tree	0.772(0.677~0.862)	0.716	0.667	0.619	0.783	0.642	0.402	0.667	0.746
Random Forest	0.839(0.764~0.909)	0.765	0.765	0.619	0.867	0.684	0.486	0.765	0.765
XGBoost	0.817(0.740~0.890)	0.706	0.650	0.619	0.767	0.634	0.386	0.650	0.742
LightGBM	0.823(0.738~0.898)	0.755	0.718	0.667	0.817	0.691	0.483	0.718	0.778
SVM	0.865 (0.788~0.927)	0.794	0.784	0.690	0.867	0.734	0.557	0.784	0.800
ANN	0.805(0.714~0.884)	0.745	0.711	0.643	0.817	0.675	0.460	0.711	0.766