. Author manuscript; available in PMC: 2014 Aug 31.

Published in final edited form as: Cytometry A. 2012 Dec 13;83(1):150–160. doi: 10.1002/cyto.a.22240

Table 3.

Sensitivity, specificity, and accuracy of the five methods

		E-NET	RANDOM FOREST	DLDA	LASSO	BEST-1
Bootstrapped Estimates	Sensitivity	0.696	0.623	0.691	0.694	0.659
	Specificity	0.659	0.692	0.617	0.658	0.548
	Accuracy	0.679	0.654	0.658	0.678	0.609
Resubstitution Estimates	Sensitivity	0.895	1	0.895	0.895	0.684
	Specificity	0.938	1	0.875	0.938	0.750
	Accuracy	0.914	1	0.886	0.914	0.714

Sensitivity is defined as true positives (TP)/(TP + false negatives (FN)), Specificity = true NEGATIVES (TN)/(TN + False positives (FP)), Accuracy = (TP+TN)/(TP+TN+FP+FN).