Table 5.

The performances of the final two-classification and the three-classification models.

Models	Data set	Sensitivity (95%CI)	Specificity (95%CI)	PPV (95%CI)	NPV (95%CI)	AUC (95%CI)	Accuracy (95%CI)
Two-classification (200 epochs, 1:9)	Training set	0.996 (0.992-1.000)	0.911 (0.895-0.926)	0.830 (0.802-0.858)	0.998 (0.996-1.000)	0.991 (0.988-0.993)	0.937 (0.926-0.948)
	Testing set	0.992 (0.980-1.000)	0.881 (0.854-0.908)	0.784 (0.737-0.830)	0.996 (0.990-1.000)	0.985 (0.979-0.991)	0.914 (0.895-0.934)
	Validate set	0.886 (0.843-0.929)	0.938 (0.916-0.960)	0.869 (0.824-0.914)	0.946 (0.926-0.967)	0.942 (0.918-0.967)	0.921 (0.901-0.942)
Three-classification (200 epochs, 1:9)	Training set	0.901 (0.884-0.917)	0.983 (0.977-0.988)	0.965 (0.955-0.975)	0.949 (0.940-0.957)	0.983 (0.979-0.987)	0.954 (0.947-0.961)
	Testing set	0.857 (0.828-0.886)	0.967 (0.956-0.978)	0.933 (0.911-0.955)	0.927 (0.911-0.942)	0.968 (0.960-0.976)	0.929 (0.916-0.941)
	Validate set	0.887 (0.858-0.916)	0.929 (0.912-0.946)	0.866 (0.835-0.897)	0.941 (0.925-0.957)	0.948 (0.935-0.961)	0.915 (0.900-0.930)

CI, confidence interval; PPV, positive predictive value; NPV, negative predictive value; AUC, area under the curve.