Table 2.

Overview of machine learning models’ performance.

Model	Training AUCa	Testing AUC	Accuracy	Sensitivity	Specificity	PPVb	NPVc	F1-score	Brier Score	BSSd
LRe	0.86	0.85	0.80	0.80	0.80	0.74	0.85	0.77	0.15	Ref
LDAf	0.86	0.86	0.80	0.80	0.80	0.73	0.85	0.76	0.15	0.17%
RFCg	0.94	0.89	0.81	0.84	0.79	0.73	0.88	0.78	0.13	15.79%
GBCh	0.99	0.88	0.83	0.86	0.81	0.75	0.89	0.80	0.13	12.54%
ABCi	0.90	0.85	0.79	0.77	0.80	0.72	0.83	0.74	0.22	–47.29%
XGBoostj	0.97	0.88	0.80	0.81	0.80	0.73	0.86	0.77	0.13	14.33%
LGBMk	0.99	0.90	0.83	0.85	0.82	0.76	0.89	0.80	0.13	10.38%

^aAUC: area under the curve.

^bPPV: positive predictive value.

^cNPV: negative predictive value.

^dBSS: Brier skill score.

^eLR: logistic regression.

^fLDA: linear discriminant analysis.

^gRFC: random forest classifier.

^hGBC: gradient boosting classifier.

ⁱABC: AdaBoost classifier.

^jXGBoost: extreme gradient boosting.

^kLGBM: light gradient boosting machine.