Table A2.

SVM model’s performance for the five-fold cross-validation.

	Target Class	Precision	Recall	F1-Score	AUC Score	Accuracy		Confusion Matrix
						Train	Test
Fold 1	Class 0	0.88	0.77	0.82	-	-	-	True label	Predicted label
	Class 1	0.65	0.80	0.72	-	-	-		77	23
	Average	0.76	0.78	0.77	0.85	0.88	0.78		11	43
Fold 2	Class 0	0.91	0.72	0.80	-	-	-	True label	Predicted label
	Class 1	0.63	0.87	0.73	-	-	-		72	28
	Average	0.77	0.80	0.77	0.87	0.87	0.72		7	47
Fold 3	Class 0	0.88	0.83	0.86	-	-	-	True label	Predicted label
	Class 1	0.72	0.80	0.75	-	-	-		83	17
	Average	0.80	0.81	0.81	0.90	0.87	0.81		11	43
Fold 4	Class 0	0.91	0.86	0.88	-	-	-	True label	Predicted label
	Class 1	0.76	0.83	0.79	-	-	-		86	14
	Average	0.83	0.85	0.85	0.89	0.86	0.85		9	44
Fold 5	Class 0	0.92	0.81	0.86	-	-	-	True label	Predicted label
	Class 1	0.71	0.87	0.78	-	-	-		81	19
	Average	0.81	0.84	0.82	0.90	0.86	0.83		7	46
	All folds’ average	0.79	0.81	0.80	0.88	0.87	0.79