Table 3.

Performance of the proposed classification model with different classifiers.

	SVM (linear)	SVM (RBF)	Logistic regression	Random forest
Accuracy (%)	80.4	79.6	79.4	77.9
Specificity (%)	73.3	73.8	78.8	80.4
Sensitivity (%)	87.5	85.5	80.0	75.4
AUC	0.78	0.79 (p = 0.633)	0.76 (p = 0.338)	0.80 (p = 0.635)

Data are given as mean (standard deviation). SVM, support vector machine; AUC, area under the receiver operating characteristic (ROC) curve. P-value indicates the significance in ROC curve comparison with the SVM model with linear kernel.