Skip to main content

Table 8 Sensitivity and specificity of various classifiers trained on the acute renal failure data set for difference cost values of cost-sensitive learning

From: Improving sensitivity of machine learning methods for automated case identification from free-text electronic medical records

 

SVM

MyC

RIPPER

C4.5

Cost

Sens.

Spec.

Sens.

Spec.

Sens.

Spec.

Sens.

Spec.

1

0.59

0.92

0.74

0.85

0.78

0.80

0.67

0.73

10

0.59

0.92

0.81

0.63

0.78

0.80

0.73

0.69

25

0.59

0.92

0.81

0.63

0.78

0.80

0.76

0.64

50

0.59

0.92

0.89

0.35

0.78

0.80

0.78

0.60

100

0.59

0.92

1.00

0.00

0.78

0.80

0.97

0.11

200

0.59

0.92

1.00

0.00

1.00

0.00

1.00

0.00

400

0.59

0.92

1.00

0.00

1.00

0.00

1.00

0.00

800

0.59

0.92

1.00

0.00

1.00

0.00

1.00

0.00

1000

0.59

0.92

1.00

0.00

1.00

0.00

1.00

0.00