Skip to main content

Table 8 Summary of classifiers for Rotterdam cohort, validated on Mainz cohort with relapse as endpoint

From: Elastic SCAD as a novel penalization method for SVM classification tasks in high-dimensional data

FS method

# features

test error(%)

sensitivity(%)

specificity(%)

Youden index

AUC

L2 SVM

22283 (all)

25

11

93

0.04

0.52

RFE SVM

22283 (all)

25

11

93

0.04

0.52

L1 SVM

8319

28

30

84

0.14

0.57

SCAD SVM

1284

35

41

72

0.13

0.565

Elastic Net SVM

272

28

37

81

0.19

0.595

Elastic SCAD SVM

2074

26

30

87

0.17

0.585

  1. Misclassification error, sensitivity, specificity, Youden index and AUC value for four feature selection methods, RFE SVM and standard SVM trained on the Rotterdam cohort and applied to the Mainz cohort.
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us