Skip to main content

Table 4 Balanced accuracy for trained classifiers (%)

From: Automated assessment of foot elevation in adults with hereditary spastic paraplegia using inertial measurements and machine learning

Classifier

Binary

Multiclass

Threshold range of motion

67 (65)

47 (46)

Gaussian Naive Bayes

75 (71)

62 (67)

Support vector machine

87 (89)

71 (78)

Random forest

86 (87)

74 (89)

Annotators average

88 (100)

82 (100)

  1. Values in brackets show the results for foot samples with total agreement among annotators (N = 47)