Table 3.

The performance of four prediction models on training set and test set

Model	Data set	Accuracy	Sensitivity	Specificity	AUC (95% CI)
ANN	Training set	0.801	0.833	0.785	0.901 (0.882,0.920)
	Test set	0.728	0.708	0.737	0.762 (0.714,0.810)
DBN	Training set	0.634	0.517	0.689	0.622 (0.585,0.659)
	Test set	0.629	0.496	0.695	0.618 (0.561,0.675)
SVM	Training set	0.772	0.920	0.492	0.698 (0.661,0.758)
	Test set	0.725	0.888	0.340	0.627 (0.588,0.625)
GA-DT	Training set	0.778	0.840	0.649	0.744 (0.710,0.779)
	Test set	0.763	0.849	0.585	0.724 (0.689,0.760)