Random Forest for Automatic Feature Importance Estimation and Selection for Explainable Postural Stability of a Multi-Factor Clinical Test

• Published in: Sensors (Basel, Switzerland) Vol. 21; no. 17; p. 5930
• Main Authors: Mendoza, Tomas, Lee, Chia-Hsuan, Huang, Chien-Hua, Sun, Tien-Lung
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 03.09.2021; MDPI
• Subjects: Acceleration; Accidental Falls; Adult; Aged; Balance; Entropy; Falls; features; Gait; Humans; inertial sensor; Mobility; multiscale entropy; permutation entropy; Physicians; Postural Balance; Professionals; Risk assessment; Sensors; short form berg balance scale (SFBBS); Time series; timed up and go (TUG); Walking; features; community-dwelling elderly; short form berg balance scale (SFBBS); inertial sensor; multiscale entropy; random forest; fall risk; permutation entropy; timed up and go (TUG)

Falling is a common incident that affects the health of elder adults worldwide. Postural instability is one of the major contributors to this problem. In this study, we propose a supplementary method for measuring postural stability that reduces doctor intervention. We used simple clinical tests, in...