Table 5.

Performance of the optimal models via tenfold cross validation

Models		Accuracy	Specificity	Sensitivity	AUC	F1-Score
RF Type D	Mean	0.7047	0.7075	0.6978	0.7027	0.5835
	95% CI	(0.69, 0.72)	(0.69, 0.72)	(0.68, 0.71)	(0.69, 0.71)	(0.57, 0.6)
	SD	0.0178	0.0207	0.024	0.0178	0.021
XGB Type D	Mean	0.6962	0.6837	0.7258	0.7048	0.5861
	95% CI	(0.69, 0.71)	(0.67, 0.69)	(0.71, 0.74)	(0.69, 0.72)	(0.57, 0.6)
	SD	0.0177	0.0168	0.0233	0.0189	0.0215
SVM Type C	Mean	0.7001	0.6985	0.7039	0.7012	0.5818
	95% CI	(0.69, 0.71)	(0.69, 0.71)	(0.69, 0.72)	(0.69, 0.71)	(0.57, 0.59)
	SD	0.0151	0.0161	0.0219	0.0159	0.0185
LR Type C	Mean	0.7021	0.7022	0.702	0.7021	0.5827
	95% CI	(0.69, 0.71)	(0.69, 0.71)	(0.69, 0.72)	(0.69, 0.71)	(0.57, 0.59)
	SD	0.0143	0.013	0.0241	0.0164	0.0192
ANN1 Type C	Mean	0.6981	0.6914	0.7142	0.7028	0.5837
	95% CI	(0.69, 0.71)	(0.68, 0.7)	(0.7, 0.73)	(0.69, 0.71)	(0.57, 0.6)
	SD	0.016	0.0171	0.0276	0.0178	0.0207
ANN2 Type D	Mean	0.6968	0.689	0.7152	0.7021	0.583
	95% CI	(0.69, 0.71)	(0.68, 0.7)	(0.71, 0.73)	(0.69, 0.71)	(0.57, 0.59)
	SD	0.0157	0.0192	0.0163	0.0144	0.0166

ANN1 = ANN model with 1 hidden layer; ANN2 = ANN model with 2 hidden layers