Development and Validation of an Artificial Intelligence-Based Motion Analysis System for Upper Extremity Rehabilitation Exercises in Patients with Spinal Cord Injury: A Randomized Controlled Trial

Abstract

In this study, we developed an AI-based real-time motion feedback system for patients with spinal cord injury (SCI) during rehabilitation, aiming to enhance their interest and motivation. The effectiveness of the system in improving upper-limb muscle strength during the Thera band exercises was evaluated. The motion analysis program, including exercise repetition counts and calorie consumption, was developed using MediaPipe, focusing on three key motions (chest press, shoulder press, and arm curl) for upper extremity exercises. The participants with SCI were randomly assigned to the experimental group (EG = 4) or control group (CG = 5), engaging in 1 h sessions three times a week for 8 weeks. Muscle strength tests (chest press, shoulder press, lat pull-down, and arm curl) were performed before and after exercises. Although both groups did not show significant differences, the EG group exhibited increased strength in all measured variables, whereas the CG group showed constant or reduced results. Consequently, the computer program-based system developed in this study could be effective in muscle strengthening. Furthermore, these findings may serve as a valuable foundation for future AI-driven rehabilitation exercise systems.

Keywords

• artificial intelligence
• motion feedback system
• spinal cord injury
• rehabilitation