Abstract
Hand function loss caused by conditions such as stroke, hand surgery, or neurological disorders significantly affects quality of life. Rehabilitation methods are essential for restoring these functions, and technology offers innovative, efficient, and accessible solutions. This study proposes a novel gamified system focusing on fine and gross motor skill assessment and improvement. The system uses the OpenCV hand tracking module with standard webcam to capture hand joint coordinates. These coordinates are utilized to calculate ROM angles and animate a virtual hand model in three Unity-based games designed for fine motor skill development. The system allows real-time interaction, accurate progress tracking, and seamless user engagement. A pilot study was conducted to evaluate usability and feasibility with 40 healthy individuals (aged 19–25 years) in a controlled environment. Additionally, a ROM angle calculation test was performed on four healthy participants (with a mean age of 23), comparing the system's measurements with traditional goniometer readings. The evaluation included joints across all fingers of the hand: distal interphalangeal (DIP), proximal interphalangeal (PIP) joints for all fingers, as well as the interphalangeal (IP) joint for the thumb. To ensure consistency, participants gripped predefined cylindrical objects of standard sizes during both measurements, reducing variability. Results showed strong correlations between the system's measurements and goniometer readings, with r-values ranging from 0.585 to 0.998. The PIP joints exhibited the strongest correlations, including 0.998 (p = 0.002) for the ring finger and 0.997 (p = 0.003) for the pinky finger. DIP joints showed high correlations such as 0.929 (p = 0.071) for the index finger and 0.883 (p = 0.117) for the ring finger. The thumb IP joint also showed a robust correlation of 0.934 (p = 0.066). These results suggest the system provides measurements comparable to traditional goniometers, particularly for PIP joints. Furthermore, user experience was also assessed using the System Usability Scale (SUS), which yielded an average score of 82.69, indicating high usability and accessibility, even for first-time users. The system's low latency (under 2 milliseconds) ensures a smooth user experience, essential for maintaining motivation during gamified rehabilitation activities. In conclusion, the proposed system is a reliable tool for hand rehabilitation, offering accurate and real-time ROM measurements and demonstrating high user usability. While some correlations did not achieve statistical significance due to the small sample size, our results show that the proposed solution can be a promising solution for home-based rehabilitation.
Keywords