Table 1.

Performance metrics for five models in the training dataset.

Model	AUC (SD)	Accuracy (SD)	Sensitivity (SD)	Specificity (SD)	PPV (SD)	NPV (SD)	F1 score (SD)	Kappa (SD)
XGBoost	0.986 (0.006)	0.885 (0.023)	0.907 (0.081)	0.964 (0.045)	0.960 (0.049)	0.838 (0.063)	0.928 (0.023)	0.771 (0.044)
RandomForest	1.000 (0.000)	0.942 (0.019)	1.000 (0.000)	1.000 (0.000)	1.000 (0.000)	0.897 (0.032)	1.000 (0.000)	0.885 (0.037)
GNB	0.975 (0.019)	0.885 (0.037)	0.964 (0.073)	0.905 (0.086)	0.910 (0.078)	0.875 (0.054)	0.931 (0.039)	0.771 (0.074)
logistic	0.884 (0.037)	0.875 (0.022)	0.924 (0.038)	0.924 (0.038)	0.918 (0.041)	0.842 (0.034)	0.920 (0.023)	0.750 (0.044)
SVM	0.893 (0.037)	0.875 (0.022)	0.924 (0.038)	0.924 (0.038)	0.918 (0.041)	0.842 (0.034)	0.920 (0.023)	0.750 (0.044)

PPV, Positive Predictive Value; NPV, Negative predictive value; XGBoost, eXtreme Gradient Boosting; SVM, support vector machines; SD, Standard Deviation.