Table 4.

Performance of Different Classifiers.

	Accuracy	Sensitivity	Specificity	Precision	F1-Score	AUC (Test)
neg-Han (2020)
Logistic-all	0.643	0.500	0.750	0.600	0.545	0.578
Logistic-step	0.786	0.625	1.000	1.000	0.769	0.833
RF	0.929	1.000	0.800	0.900	0.947	0.900
SVM	0.786	0.800	0.750	0.889	0.842	0.744
XGBoost	0.714	0.889	0.400	0.727	0.800	0.644
pos-Han (2020)
Logistic-all	0.714	0.750	0.800	0.600	0.667	0.700
Logistic-step	0.929	1.000	0.900	0.800	0.889	0.900
RF	0.929	1.000	0.800	0.900	0.947	0.900
SVM	0.857	0.818	1.000	1.000	0.900	0.800
XGBoost	0.929	1.000	0.800	0.900	0.947	0.900
AH-Wang (2019)
Logistic-all	0.733	0.667	0.833	0.857	0.750	0.652
Logistic-step	0.600	0.556	0.667	0.714	0.625	0.643
RF	0.867	0.875	0.857	0.857	0.857	0.866
SVM	0.800	0.857	0.750	0.750	0.800	0.804
XGBoost	0.733	0.625	0.857	0.833	0.714	0.741
Vit-Wang (2019)
Logistic-all	0.556	0.600	0.500	0.600	0.600	0.525
Logistic-step	0.722	0.778	0.667	0.700	0.737	0.725
RF	0.833	0.750	0.900	0.857	0.800	0.825
SVM	0.778	0.750	0.800	0.750	0.750	0.775
XGBoost	0.778	0.750	0.800	0.750	0.750	0.775
Yun (2020)
Logistic-all	0.811	0.909	0.333	0.870	0.889	0.478
Logistic-step	0.792	0.889	0.250	0.870	0.879	0.472
RF	0.792	0.429	0.848	0.300	0.353	0.638
SVM	0.868	0.500	0.898	0.286	0.364	0.621
XGBoost	0.792	0.571	0.826	0.333	0.421	0.699
Barca (2020)
Logistic-all	0.667	0.600	0.778	0.818	0.692	0.671
Logistic-step	0.750	0.692	0.818	0.818	0.750	0.748
RF	0.667	0.538	0.818	0.778	0.636	0.678
SVM	0.667	0.727	0.615	0.615	0.667	0.671
XGBoost	0.792	0.692	0.909	0.900	0.783	0.801