BMC Bioinformatics

Table 9 Mean performance metrics values of the three datasets tested (test set) obtained for the classification methods applied to different gene sets based on DEGs, EN and iTwiner

From: Identification of biomarkers predictive of metastasis development in early-stage colorectal cancer using network-based regularization

Combined methods	Acc	Sensitivity	Specificity	AUC
DEGs+
DT	0.62	0.62	0.67	0.62
svmL	0.70	0.60	0.82	0.69
svmR	0.60	0.56	0.67	0.60
LR	0.66	0.64	0.72	0.65
RF	0.71	0.66	0.82	0.71
EN +
DT	0.67	0.68	0.67	0.67
svmL	0.71	0.61	0.85	0.71
svmR	0.77	0.80	0.71	0.77
LR	0.73	0.68	0.78	0.73
RF	0.77	0.68	0.89	0.77
iTwiner +
DT	0.71	0.68	0.78	0.71
svmL	0.77	0.60	0.93	0.76
svmR	0.69	0.72	0.78	0.69
LR	0.67	0.56	0.78	0.66
RF	0.81	0.64	1.00	0.81

Acc—accuracy, Sensitivity—fraction of actual positive cases (P); Specificity—fraction of actual negative cases (PM), AUC—area under the ROC curve

Back to article page

ISSN: 1471-2105

Contact us

General enquiries: journalsubmissions@springernature.com