Table 2 Mean and standard deviation of the test scores over all eight folds of the outer cross-validation loop based on individual movement cycles.

From: The potential of machine learning in classifying relapse and non-relapse in children with clubfoot based on movement patterns

 

Outer CV loop (unseen data)

(mean ± sd)

AUC

Sensitivity

Specificity

Walking

0.71 ± 0.25

0.53 ± 0.38

0.71 ± 0.19

Toe walking

0.81 ± 0.10

0.54 ± 0.36

0.77 ± 0.18

Heel walking

0.70 ± 0.21

0.50 ± 0.28

0.74 ± 0.19

Running

0.62 ± 0.23

0.45 ± 0.37

0.78 ± 0.22

  1. AUC = area under the receiver operating characteristic curve