Table 2.

Multi-model classification–training set results.

Model	AUC(SD)	Cut off (SD)	Accuracy (SD)	Sensitivity (SD)	Specificity (SD)	Positive predictive value (SD)	Negative predictive value (SD)	F1 score (SD)	Kappa (SD)
XG Boost	1.000 (0.000)	0.873 (0.012)	0.996 (0.000)	1.000 (0.000)	1.000 (0.000)	1.000 (0.000)	0.989 (0.000)	1.000 (0.000)	0.991 (0.000)
logistic	0.789 (0.016)	0.553 (0.036)	0.744 (0.013)	0.784 (0.038)	0.694 (0.034)	0.792 (0.012)	0.679 (0.031)	0.787 (0.016)	0.469 (0.022)
Light GBM	1.000 (0.000)	0.567 (0.024)	0.994 (0.002)	0.997 (0.004)	1.000 (0.000)	1.000 (0.000)	0.985 (0.005)	0.998 (0.002)	0.987 (0.005)
RandomForest	1.000 (0.000)	0.540 (0.037)	0.987 (0.012)	0.997 (0.004)	0.998 (0.004)	1.000 (0.000)	0.970 (0.027)	0.999 (0.002)	0.974 (0.024)
GNB	0.765 (0.017)	0.728 (0.120)	0.734 (0.012)	0.732 (0.027)	0.748 (0.036)	0.812 (0.019)	0.646 (0.018)	0.769 (0.012)	0.460 (0.023)
SVM	0.787 (0.018)	0.602 (0.031)	0.733 (0.015)	0.759 (0.052)	0.705 (0.056)	0.793 (0.021)	0.659 (0.034)	0.774 (0.020)	0.451 (0.027)
KNN	0.834 (0.020)	0.680 (0.098)	0.640 (0.075)	0.743 (0.112)	0.748 (0.127)	0.916 (0.070)	0.541 (0.059)	0.810 (0.046)	0.336 (0.104)
CNB	0.742 (0.022)	0.195 (0.388)	0.700 (0.023)	0.693 (0.062)	0.721 (0.052)	0.787 (0.020)	0.609 (0.029)	0.735 (0.034)	0.395 (0.037)