TOSHFA: A Mobile VR-Based System for Pose-Guided Exercise Rehabilitation for Low Back Pain

TL;DR

Low back pain (LBP) poses a global health burden, with traditional rehab hampered by access barriers and adherence gaps. This paper presents TOSHFA, a clinically grounded, pose-guided rehabilitation system that runs on low-cost hardware by combining MediaPipe-based pose estimation with mobile VR delivered via a cardboard headset; it provides real-time biofeedback and gamified motivation. In a pilot with 20 participants, the system achieved a mean SUS of 47.4 (poor-to-marginal usability) but demonstrated high engagement on GEQ with strong positive affect and enjoyment, indicating gamification can mitigate interface friction. The work establishes a feasible telerehabilitation framework and lays the groundwork for multi-exercise, longitudinal clinical trials, aiming to scale accessible, home-based LBP management.

Abstract

Low back pain (LBP) is a pervasive global health challenge, affecting approximately 80% of adults and frequently progressing into chronic or recurrent episodes. While exercise therapy is a primary clinical intervention, traditional at-home programs suffer from low adherence rates and the absence of professional supervision. This study introduces TOSHFA, an accessible mobile VR-based rehabilitation system that bridges this gap by combining computer vision with affordable hardware. The system utilizes a laptop webcam to perform real-time pose estimation via the MediaPipe framework, tracking 33 skeletal landmarks to provide immediate biofeedback. This data is streamed via low-latency UDP protocols to a smartphone mounted in a cardboard-style VR headset, where patients interact with a gamified 3D environment. A pilot study with 20 participants evaluated the system's performance and user engagement. Quantitative results yielded a mean System Usability Scale (SUS) score of 47.4, indicating marginal usability and a need for interface optimization. However, Game Experience Questionnaire (GEQ) data revealed high scores in positive affect and enjoyment, suggesting that the gamification elements--such as coin rewards and streak tracking--successfully maintained user motivation despite technical friction. These findings validate the feasibility of a smartphone-based tele-rehabilitation model and establish a technical foundation for future clinical trials involving multi-exercise protocols.

Figures (6)

• Figure 1: High-level overview of the TOSHFA software architecture, illustrating the low-latency UDP communication between the Python-based pose estimation backend and the Unity 3D mobile VR frontend.
• Figure 2: Modular components of the Unity frontend architecture, detailing the integration of the 33-joint skeletal avatar, real-time feedback UI, and gamified reward mechanisms.
• Figure 3: Experimental setup and research team environment during the pilot usability study sessions.
• Figure 4: Visualization of the "Seated Torso Rotation" state machine, demonstrating the system's ability to provide real-time postural correction and angle-specific scoring bonuses.
• Figure 5: Methodological workflow of the pilot study, depicting the sequential stages of participant onboarding, supervised exercise trials, and multi-metric post-session evaluations.