Skip to main content

Table 4 Provides the overall tenfold cross-validation performance of the models generated using training dataset with biological, chemical, and phenotypic features and the combination of the two and three levels of features

From: Computational models for the prediction of adverse cardiovascular drug reactions

Type of feature

RF

SMO

ACC

Precision

Recall

F-score

AUC

PRC

ACC

Precision

Recall

F-score

AUC

PRC

Biological

78.11

0.77

0.99

0.87

0.62

0.81

76.73

0.76

0.99

0.86

0.58

0.73

Chemical

83.34

0.84

0.97

0.89

0.78

0.89

76.32

0.78

0.94

0.85

0.68

0.74

Phenotypic

77.06

0.75

1.00

0.86

0.54

0.75

77.91

0.77

1.00

0.87

0.54

0.74

Biological + chemical

84.80

0.86

0.95

0.90

0.81

0.91

78.87

0.80

0.95

0.86

0.72

0.75

Biological + phenotypic

80.87

0.80

0.99

0.88

0.66

0.82

79.13

0.78

0.99

0.87

0.63

0.75

Chemical + phenotypic

83.69

0.84

0.97

0.89

0.79

0.90

77.79

0.79

0.96

0.86

0.69

0.75

Biological + chemical + phenotypic

85.25

0.85

0.96

0.90

0.82

0.91

89.07

0.94

0.95

0.94

0.47

0.75