Table 3. Performance summary.

Shown are accuracy, sensitivity, and specificity of the three feature-based classifiers when using either the F-score or RF-based approach for feature selection prior to classification (95% CI for RF in parentheses).

	Deep learning		SVM		RF
	F-score	RF-feat	F-score	RF-feat	F-score	RF-feat
Accuracy	0.845	0.862	0.828	0.828	0.828 (0.793–0.862)	0.842 (0.810–0.862)
Sensitivity	0.880	0.840	0.800	0.760	0.768 (0.720–0.831)	0.787 (0.760–0.840)
Specificity	0.818	0.879	0.848	0.879	0.873 (0.848–0.909)	0.883 (0.849–0.909)