Table 4.

The performances of the AA, MDS, and AML three-classification model with different epochs.

Models	Data set	Sensitivity (95%CI)	Specificity (95%CI)	PPV (95%CI)	NPV (95%CI)	AUC (95%CI)	Accuracy (95%CI)
30 epochs, 1:9 outcome weight	Training set	0.890 (0.873-0.907)	0.986 (0.981-0.990)	0.970 (0.961-0.980)	0.944 (0.935-0.953)	0.976 (0.971-0.981)	0.952 (0.945-0.959)
	Testing set	0.841 (0.810-0.871)	0.972 (0.962-0.982)	0.941 (0.921-0.962)	0.920 (0.903-0.936)	0.958 (0.948-0.968)	0.926 (0.913-0.939)
	Validate set	0.852 (0.819-0.885)	0.901 (0.882-0.921)	0.817 (0.783-0.852)	0.921 (0.903-0.940)	0.925 (0.909-0.941)	0.884 (0.867-0.902)
50 epochs, 1:9 outcome weight	Training set	0.892 (0.875-0.909)	0.963 (0.956-0.971)	0.928 (0.914-0.942)	0.944 (0.934-0.953)	0.975 (0.970-0.979)	0.938 (0.931-0.946)
	Testing set	0.850 (0.820-0.880)	0.958 (0.946-0.971)	0.916 (0.892-0.940)	0.923 (0.907-0.939)	0.951 (0.939-0.963)	0.921 (0.907-0.934)
	Validate set	0.834 (0.800-0.868)	0.912 (0.893-0.931)	0.830 (0.796-0.865)	0.914 (0.895-0.932)	0.894 (0.873-0.916)	0.885 (0.868-0.902)
200 epochs, 1:9 outcome weight	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.