Skip to main content

Table 4 CFS prediction from in-data and tenfold cross-validations

From: Prediction of complex human diseases from pathway-focused candidate markers by joint estimation of marker effects: case of chronic fatigue syndrome

Model and prediction type

Accuracy

Sensitivity

Specificity

FDR

In-data-unconstrained model

100.0

100.0

100.0

0.0

In-data-constrained model

100.0

100.0

100.0

0.0

K-fold-constrained model

79.2

74.4

82.8

23.8

K-fold-set1

72.7

60.0

83.3

25.0

K-fold-set2

70.0

75.0

66.7

40.0

K-fold-set3

80.0

75.0

83.3

25.0

K-fold-set4

100.0

100.0

100.0

0.0

K-fold-set5

70.0

50.0

83.3

33.3

K-fold-set6

70.0

50.0

83.3

33.3

K-fold-set7

70.0

75.0

66.7

40.0

K-fold-set8

70.0

75.0

66.7

40.0

K-fold-set9

100.0

100.0

100.0

0.0

K-fold-set10

90.0

80.0

100.0

0.0