Skip to main content

Table 6 Classification performance of naïve Bayes algorithm with nested 10 fold CV obtained by different methods on Pomeroy medulloblastoma outcome dataset.

From: Refining gene signatures: a Bayesian approach

 

Pomeroy Signature

Wrapper

Boulle

corr1

Average # of genes

100

11.5

4.8

11

ACC (%)

73.33

71.67

61.67

75.00

SENS (%)

76.92

74.36

76.92

82.05

SPEC (%)

66.67

66.67

33.33

61.90

PPV (%)

81.08

80.56

68.18

80.00

NPV (%)

60.87

58.33

43.75

65.00

AUC

0.8168

0.8180

0.7410

0.7800

  1. The average number of genes represents the average over the nested 10 fold CV.