Investigating the efficacy of AI-enhanced telerehabilitation in sarcopenic older individuals

Abstract

Objective: This study explores the effectiveness of 3D pose estimation technology in Yi Jin Jing (a traditional Chinese exercise) interventions for sarcopenic older individuals.

Design: A randomized controlled trial involving 93 participants (mean age: 71.64 ± 7.09 years; 41 males and 52 females) divided into three groups: a face-to-face offline traditional training group (OFFG), a general remote online training group (ONG), and an AI-based online remote training group (AIONG).

Methods: Participants in each group underwent their respective training programs. The effectiveness of the interventions was measured using Appendicular Skeletal Muscle Mass Index, Grip Strength, 6-meter Walking Speed, Timed-Up-and-Go Test, and Quality of Life assessments.

Results: Significant improvements were observed across all groups in ASMI, Grip Strength, 6-meter Walking Speed, TUGT, and QoL. However, there were no statistically significant differences between the groups in terms of the magnitude of these improvements. AIONG showed outcomes comparable to OFFG and ONG methods.

Conclusions: AI-based telerehabilitation with 3D pose estimation is a viable and effective alternative for remote exercise interventions. It offers precise guidance and enhances the quality of rehabilitation training, demonstrating outcomes comparable to traditional and general online methods.

Keywords: Chinese traditional exercise; Human pose estimation technology; Remote rehabilitation; Sarcopenia; Yi Jin Jing.