A machine-learning method isolating changes in wrist kinematics that identify age-related changes in arm movement

Abstract

Normal aging often results in an increase in physiological tremors and slowing of the movement of the hands, which can impair daily activities and quality of life. This study, using lightweight wearable non-invasive sensors, aimed to detect and identify age-related changes in wrist kinematics and response latency. Eighteen young (ages 18–20) and nine older (ages 49–57) adults performed two standard tasks with wearable inertial measurement units on their wrists. Frequency analysis revealed 5 kinematic variables distinguishing older from younger adults in a postural task, with best discrimination occurring in the 9–13 Hz range, agreeing with previously identified frequency range of age-related tremors, and achieving excellent classifier performance (0.86 AUROC score and 89% accuracy). In a second pronation–supination task, analysis of angular velocity in the roll axis identified a 71 ms delay in initiating arm movement in the older adults. This study demonstrates that an analysis of simple kinematic variables sampled at 100 Hz frequency with commercially available sensors is reliable, sensitive, and accurate at detecting age-related increases in physiological tremor and motor slowing. It remains to be seen if such sensitive methods may be accurate in distinguishing physiological tremors from tremors that occur in neurological diseases, such as Parkinson’s Disease.