Table 3.

Prediction of the eight models of machine-learning analysis. The performance of the models was evaluated on the training set first by the accuracy and AUC, followed by the verification on the testing set. The values of the optimal model were bolded. Data were presented mean ± S.D.

	Training Set		Testing Set
	Accuracy	AUC	Accuracy	AUC
Elastic Net Regression	0.661 ± 0.005	0.695 ± 0.006	0.857	0.784
Random Forest	0.913 ± 0.006	0.969 ± 0.003	0.896	0.723
Support Vector Machine	0.772 ± 0.003	0.847 ± 0.004	0.862	0.545
Decision Tree	0.849 ± 0.007	0.919 ± 0.006	0.874	0.579
K-Nearest Neighbor	0.826 ± 0.006	0.917 ± 0.006	0.801	0.725
Naïve Bayes	0.693 ± 0.005	0.787 ± 0.007	0.930	0.619
Boost Tree	0.971 ± 0.002	0.991 ± 0.001	0.951	0.701
Multilayer Perceptron	0.899 ± 0.007	0.919 ± 0.006	0.811	0.670

AUC: area under the receiver operating characteristic curve.