Table 2.

Overview of machine learning models’ performance.

Model	Training AUCa	Testing AUC	Accuracy	Sensitivity	Specificity	PPVb	NPVc	F1-score
LGBMd	0.98	0.80	0.88	0.33	0.96	0.51	0.91	0.40
GBe	0.98	0.78	0.88	0.35	0.95	0.49	0.91	0.41
XGBf	0.98	0.80	0.88	0.39	0.94	0.49	0.92	0.44
RFg	0.99	0.77	0.87	0.24	0.95	0.42	0.90	0.30
AdaBoost	0.97	0.78	0.87	0.25	0.96	0.46	0.90	0.32
ANNh	0.99	0.72	0.84	0.22	0.93	0.30	0.90	0.25

^aAUC: area under the curve.

^bPPV: positive predictive value.

^cNPV: negative predictive value.

^dLGMB: light gradient boosting machine.

^eGB: gradient boosting.

^fXGB: extreme gradient boosting.

^gRF: random forest.

^hANN: artificial neural network.