Skip to main content

Table 6 The rank of the average performance of each model

From: Joint modeling strategy for using electronic medical records data to build machine learning models: an example of intracerebral hemorrhage

 

Accuracy

Sensitivity

Specificity

AUC

Precision

F1 score

Sum*

Rank*

LR

7

4

7

4.5

7

6

35.5

7

RF

1

6

1

1

1

5

15

1

ANN

2.5

4

3

2

2

3

16.5

2

SVM

6

1

6

3

5

3

24

5

KNN

5

7

2

7

6

7

34

6

Stacking

4

2

5

6

4

1

22

4

AdaBoost

2.5

4

4

4.5

3

3

21

3

  1. *Lower rank is better; Sum = sum of ranks of six indicators; Rank = rank of sum of ranks