Table 7 Comparison of predictions of classification algorithms to recommend sports protocols between men and women groups.

From: Artificial intelligence used to diagnose osteoporosis from risk factors in clinical data and proposing sports protocols

 

Models

AUROC

Accuracy

Precision

Sensitivity

specificity

F-score

Men

DT

0.86

0.78

0.51

0.56

0.96

0.52

RF

0.89

0.84

0.70

0.67

0.97

0.64

KNN

0.81

0.56

0.45

0.50

0.90

0.46

SVM

0.82

0.70

0.56

0.52

0.94

0.52

GB

0.95

0.84

0.78

0.69

0.87

0.70

ET

0.94

0.82

0.73

0.68

0.96

0.67

AB

0.96

0.82

0.75

0.67

0.96

0.67

ANN

0.88

0.71

0.57

0.58

0.94

0.56

Women

DT

0.94

0.92

0.90

0.88

0.98

0.87

RF

0.98

0.98

0.99

0.97

0.99

0.98

KNN

0.86

0.65

0.50

0.49

0.92

0.48

SVM

0.91

0.76

0.59

0.58

0.95

0.58

GB

0.93

0.97

0.93

0.97

0.99

0.94

ET

0.98

0.93

0.90

0.92

0.98

0.90

AB

0.99

0.94

0.96

0.90

0.98

0.92

ANN

0.89

0.53

0.45

0.37

0.89

0.34