Correlation and ANOVA-Based Validation of IoT-Derived Motion Metrics in Post-Stroke Hand Rehabilitation
DOI:
https://doi.org/10.56532/mjsat.v6i1.752Keywords:
Correlation analysis, Stroke rehabilitation, IoT, Remote monitoring, Clinical assessmentAbstract
Reliance on intermittent and subjective clinical assessment in stroke rehabilitation has remained a persistent weakness with limited information on daily recovery progress and it has impeded access to patients in the remote or underserved regions. To overcome this, the paper proposes RIoTv2, which is a system that can monitor motor activity in an objective and continuous manner. The vision-based system employed in the solution is that of MediaPipe Pose to extract 4D skeletal arm motion values using regular webcam when doing important key hand rehabilitation exercises, including Hand Strengthening and Hand Opposition. The algorithmic method of kinematic measurements (velocity, smoothness, range of motion, repetition accuracy) was conducted in a quasi-experimental study of 200 post-stroke patients. These RIoTv2 measurements were correlated with and compared to Fugl-Meyer Assessment (FMA) and Barthel Index (BI) scores under different degrees of impairment with the help of correlation analysis and ANOVA. This system was seen to be accurate in most cases (largely over 75 percent), which corresponds to pragmatic clinical limits (the error rate is often not far below 25 to 30 percent) with normalized kinematic errors of about 7 to 20 percent and FMA thresholds of remote monitoring literature. The RIoTv2 system is an efficient device that can be used as a remote-monitoring platform offering healthcare providers with objective and real-time information to use in personalized therapy and intervention. The critical social repercussion comprises the development of health equity by providing cost-effective and administrable technology to break geographic and economic boundaries, improving patient agency amid home-based care, and improving a more transparent and data-based paradigm on the care of post-stroke patients.
References
L. A. Ingram, A. A. Butler, M. A. Brodie, S. R. Lord, and S. C. Gandevia, “Quantifying upper limb motor impairment in chronic stroke: A physiological profiling approach,” Journal of Applied Physiology, vol. 131, no. 3, pp. 949–965, Sep. 2021, doi: https://doi.org/10.1152/japplphysiol.00078.2021.
D. T. H. Nguyen and D. T. T. Trinh, “Correlation of the Fugl Meyer assessment, Motricity Index and Barthel Index scales in the assessment of rehabilitation in post-stroke patients,” MedPharmRes, vol. 7, no. 4, pp. 1–10, Dec. 2023, doi: https://doi.org/10.32895/UMP.MPR.7.4.1.
C. D. Rocha, I. Carneiro, M. Torres, H. P. Oliveira, E. J. Solteiro Pires, and M. F. Silva, “Post-stroke upper limb rehabilitation: clinical practices, compensatory movements, assessment, and trends,” Progress in Biomedical Engineering, vol. 7, no. 4, Oct. 2025, doi: https://doi.org/10.1088/2516-1091/adeb1e.
D. T. H. Nguyen and D. T. T. Trinh, “Correlation of the Fugl Meyer assessment, Motricity Index and Barthel Index scales in the assessment of rehabilitation in post-stroke patients,” MedPharmRes, vol. 7, no. 4, pp. 1–10, Dec. 2023, doi: https://doi.org/10.32895/ump.mpr.7.4.1.
K. Hou, M. M. R. Khan, and M. H. Rahman, “An Accessible AI-Assisted Rehabilitation System for Guided Upper Limb Therapy,” Sensors (Basel)., vol. 25, no. 19, Oct. 2025, doi: https://doi.org/10.3390/s25196239.
N. H. M. Dhuzuki et al., “Design and Implementation of a Deep Learning-Based Hand Gesture Recognition System for Rehabilitation Internet-of-Things (RIoT) Environments Using MediaPipe,” IIUM Engineering Journal, vol. 26, no. 1, pp. 353–372, 2025, doi: https://doi.org/10.31436/IIUMEJ.V26I1.3455.
M. S. Islam et al., “Advanced Rehabilitation IoT (RIoT) System Utilizing IMAGy MEMS Sensors and Deep Learning for Hand Gesture Recognition,” 2025 International Conference on Electrical Engineering and Informatics (ICEEI), pp. 1–4, Nov. 2025, doi: https://doi.org/10.1109/ICEEI68459.2025.11331189.
M. S. Islam et al., “AI and RIoT for Rehabilitation: Advancing Hand Gesture Recognition and Voice Assistance,” pp. 439–453, 2026, doi: https://doi.org/10.1007/978-3-032-00232-7_28.
A. A. Zainuddin, M. S. Islam, D. Handayani, S. I. Kamarudin, M. I. Mohd Tamrin, and A. F. Misman, “Tolerance-Based Evaluation of a Shariah-Compliant Rehabilitation IoT Framework for Post-Stroke Hand Gesture Monitoring,” 2025 8th International Conference on Information and Communications Technology (ICOIACT), pp. 232–237, Dec. 2025, doi: https://doi.org/10.1109/ICOIACT67584.2025.11345020.
A. A. Zainuddin, N. H. M. Dhuzuki, A. A. Puzi, M. N. Johar, and M. Yazid, “Calibrating Hand Gesture Recognition for Stroke Rehabilitation Internet-of-Things (RIOT) Using MediaPipe in Smart Healthcare Systems,” International Journal of Advanced Computer Science and Applications, vol. 15, no. 7, pp. 568–583, Jul. 2024, doi: https://doi.org/10.14569/IJACSA.2024.0150756.
N. H. M. Dhuzuki, A. A. Zainuddin, S. I. Kamarudin, D. Handayani, K. Subramaniam, and M. I. M. Tamrin, “Web-Based Medical Information System for Stroke Rehabilitation Intemet-of-Things (RIOT) Patients: A Prototype,” 6th IEEE International Conference on Artificial Intelligence in Engineering and Technology, IICAIET 2024, pp. 326–330, 2024, doi: https://doi.org/10.1109/IICAIET62352.2024.10729958.
D. J. Gladstone, C. J. Danells, and S. E. Black, “The Fugl-Meyer Assessment of Motor Recovery after Stroke: A Critical Review of Its Measurement Properties,” Neurorehabilitation and Neural Repair, vol. 16, no. 3, pp. 232–240, 2002, doi: https://doi.org/10.1177/154596802401105171.
D. T. H. Nguyen and D. T. T. Trinh, “Correlation of the Fugl Meyer assessment, Motricity Index and Barthel Index scales in the assessment of rehabilitation in post-stroke patients,” MedPharmRes, vol. 7, no. 4, pp. 1–10, Dec. 2023, doi: https://doi.org/10.32895/ump.mpr.7.4.1.
M. Rana and V. Mittal, “Wearable Sensors for Real-Time Kinematics Analysis in Sports: A Review,” IEEE Sensors Journal, vol. 21, no. 2, pp. 1187–1207, Jan. 2021, doi: https://doi.org/10.1109/JSEN.2020.3019016.
R. De Fazio, V. M. Mastronardi, M. De Vittorio, and P. Visconti, “Wearable Sensors and Smart Devices to Monitor Rehabilitation Parameters and Sports Performance: An Overview,” Sensors (Basel)., vol. 23, no. 4, Feb. 2023, doi: https://doi.org/10.3390/s23041856.
D. S. Y. Vun, R. Bowers, and A. McGarry, “Vision-based motion capture for the gait analysis of neurodegenerative diseases: A review,” Gait & Posture, vol. 112, pp. 95–107, Jul. 2024, doi: https://doi.org/10.1016/j.gaitpost.2024.04.029.
“MediaPipe Hands: On-device Real-time Hand Tracking - Consensus.” Accessed: Feb. 27, 2026. [Online]. Available: https://consensus.app/papers/mediapipe-hands-ondevice-realtime-hand-tracking-zhang-bazarevsky/6526b10aff0452039f78bc323b196be4/
Q. Shi, H. Zhang, L. Dong, Q. Lei, and T. Hsiao, “Vision skeleton trajectory based motion assessment system for healthcare rehabilitation,” The Journal of Engineering, vol. 2020, no. 9, pp. 805–808, Sep. 2020, doi: https://doi.org/10.1049/joe.2019.1316.
G. Kwakkel et al., “Standardized measurement of sensorimotor recovery in stroke trials: Consensus-based core recommendations from the Stroke Recovery and Rehabilitation Roundtable,” International Journal of Stroke, vol. 12, no. 5, pp. 451–461, Jul. 2017, doi: https://doi.org/10.1177/1747493017711813.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Md Sariful Islam, Dr Ahmad Anwar Zainuddin, Ainul Hani Binti Mohd Manoj, Siti Maisarah Binti Abdul Aziz, Siti Aishah Binti Abdul Aziz, Nurul Farah Hanim Muhamad Nasir
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
