Skip to main content

Table 7 Comparison results of NER on progress notes

From: A multitask bi-directional RNN model for named entity recognition on Chinese electronic medical records

 

Bi-RNN model

Our proposed model

Entity type

Precision

Recall

F-measure

Precision

Recall

F-measure

Disease

90.11

88.93

89.52

94.06

95.07

94.56

Symptom

87.67

88.335

88.00

94.50

90.79

92.61

Disease group

27.27

75.00

40.00

77.27

80.95

79.06

Treatment

71.06

77.80

74.28

88.15

87.19

87.67

Test

83.64

88.41

85.96

92.53

93.36

92.94

Macro average

71.95

83.69

75.55

89.31

89.47

89.37