Skip to main content

Table 2 Classification matrix and subset accuracy of machine learning models to predict one-year chiropractic service utilization, based on parameters from initial development phase

From: Exploring supervised machine learning approaches to predicting Veterans Health Administration chiropractic service utilization

Model/Class

Precision (%)

Recall (%)

F-measure (%)

Accuracy (%)

Gradient Boosted Classifier

1 Visit

43.5

61.7

51.0

 

2–3 Visits

36.3

32.5

34.3

 

4–6 Visits

34.0

9.2

14.5

 

7+ Visits

46.2

57.8

51.0

 

Averagea

40.3

42.1

39.1

42.1

Stochastic Gradient Descent Classifier

1 Visit

43.9

53.1

48.1

 

2–3 Visits

32.3

29.9

31.0

 

4–6 Visits

24.9

14.8

18.6

 

7+ Visits

43.4

51.2

47.0

 

Averagea

36.8

38.6

37.2

38.6

Support Vector Classifier

1 Visit

42.6

60.8

50.1

 

2–3 Visits

35.3

26.1

30.0

 

4–6 Visits

32.0

11.3

16.7

 

7+ Visits

45.3

60.3

51.7

 

Averagea

39.2

41.4

38.4

41.4

Artificial Neural Network

1 Visit

42.9

56.2

48.7

 

2–3 Visits

35.9

30.6

33.1

 

4–6 Visits

25.3

12.1

16.4

 

7+ Visits

45.1

55.9

49.9

 

Averagea

38.0

40.3

38.2

40.3

  1. aSupport-weighted average