Skip to main content

Table 5 Accuracy in predicting latent needs by SVM

From: Extracting the latent needs of dementia patients and caregivers from transcribed interviews in japanese: an initial assessment of the availability of morpheme selection as input data with Z-scores in machine learning

Position

Standard

Measures

Z-score

Yes

No

Caregivers

Accuracy

0.77

0.79

Precision

0.77

0.82

Recall

0.77

0.73

F-measure

0.77

0.77

TN

79

87

FP

24

16

FN

24

28

TP

79

75

Patients

Accuracy

0.82

0.82

Precision

0.83

0.93

Recall

0.79

0.68

F-measure

0.81

0.79

TN

16

18

FP

3

1

FN

4

6

TP

15

13

  1. TN True Negative, FP False Positive, FN False Negative, TP True Positive