Table 9 The overall results that are macro- and weighted-averaged, as well as the macro-averaged analysis of the results for each class provided with time-attribute provided in terms of Precision, Recall, and F1-measure.

From: Heart disease risk factors detection from electronic health records using advanced NLP and deep learning techniques

Risk indicator

Time attribute

Precision

Recall

F1-score

Support

Diabetes

Before_dct

0.78

0.85

0.81

278

During_dct

0.49

0.33

0.39

204

After_dct

0.00

0.00

0.00

100

CAD

After_dct

0.67

0.63

0.65

107

Before_dct

0.78

0.93

0.85

258

During_dct

0.00

0.00

0.00

81

Hypertension

After_dct

0.89

0.79

0.84

116

Before_dct

0.00

0.00

0.00

53

During_dct

0.79

0.87

0.83

495

Hyperlipidemia

After_dct

0.00

0.00

0.00

97

Before_dct

0.00

0.00

0.00

107

During_dct

0.66

0.95

0.78

27

OBESE

After_dct

0.73

0.67

0.70

15

Before_dct

0.00

0.00

0.00

41

During_dct

0.89

0.75

0.82

60

Medication

After_dct

0.61

0.26

0.36

706

Before_dct

0.62

0.42

0.50

798

During_dct

0.67

0.34

0.45

558

Accuracy

   

0.9366

42946

Macro average

 

0.3383

0.2920

0.2899

42946

Weighted avg

 

0.9265

0.9366

0.9290

42946

Micro average

   

0.9366

42946