Table 8 Summary of recent studies using Kinect-based gait analysis and machine learning for mood disorder recognition, comparing classification accuracies across different mental health conditions.

From: Recognition of anxiety and depression using gait data recorded by the kinect sensor: a machine learning approach with data augmentation

Paper

Mood disorder

Participants

Accuracy of the model

Lemke et al.35

Depression

32

62%

Zhao et al.36

Depression and anxiety

179

64% (depression); 76% (anxiety)

Li et al.37

Anger, happiness

59

51% (anger); 88% (happiness)

Kellokumpu et al.38

Positive-negative feeling

96

78%

Wentao et al.39

Depression

85

66% (men); 71.3% (women)

Yameng et al.40

Depression

247

59%

Propose model

Depression and anxiety

50

86.53% (depression); 61.67% (anxiety)

Back to article page