Skip to main content

Table 5 AUC, accuracy (ACC), sensitivity (SEN) and specificity (SPE) for independent testing on van de Vijver et al. [23] (top) and Wang et al. [24] (bottom) for netSVM, other network-based methods and gene-based methods.

From: Identifying cancer biomarkers by network-constrained support vector machines

 

network-based method

gene-based method

previous study

 

net SVM

F∞-norm SVM

Larsnet

Chuang's method*

SVM

Lasso

t-test + LDA

70 genes [23]*

76 genes [24]*

AUC

0.61

0.50

0.58

0.72

0.55

0.51

0.54

-

0.50

ACC

0.67

0.64

0.70

0.56

0.62

0.66

0.62

-

0.49

SEN

0.47

0.36

0.38

0.90

0.47

0.33

0.62

-

0.37

SPE

0.75

0.75

0.82

0.43

0.68

0.78

0.62

-

0.54

AUC

0.64

0.60

0.66

0.63

0.62

0.61

0.60

0.60

-

ACC

0.65

0.59

0.60

0.49

0.64

0.62

0.57

0.59

-

SEN

0.53

0.63

0.47

0.90

0.51

0.60

0.44

0.45

-

SPE

0.73

0.58

0.82

0.24

0.72

0.65

0.66

0.67

-

  1. *: results are extracted from the study [14].