A telerehabilitation system to assess upper limb motor function using IMUs and Machine Learning
DOI:
https://doi.org/10.17979/ja-cea.2025.46.12166Keywords:
Assitive technology and rehabilitation engineering, Rehabilitation engineering and healthcare delivery, Decision making and cognitive processes, Human centred automation, Intelligent interfacesAbstract
Neurological injuries can cause significant disability, especially in the motor function of the upper extremities, causing an
impairment in patients’ ability to perform activities of daily living (ADL). In order to develop a telerehabilitation system that
allows remote patient assessment, a system based on three magneto-inertial units (IMUs) is proposed. These IMUs measure
joint trajectories that are used as input for a Machine Learning (ML) model in charge of recognizing twelve ADLs. In addition,
this study compares the trajectories of patients with motor disabilities and non-disabled users using the Dynamic Time Warping
(DTW) technique to calculate similarity indices. These indices can be used to enable the assessment of impairment levels as mild
or moderate. The feasibility of the system has been evaluated with 31 patients and 9 control users, demonstrating its effectiveness
in identifying activities and assessing motor function.
References
Bertomeu-Motos, A., Blanco, A., Badesa, F. J., Barios, J. A., Zollo, L., Garcia-Aracil, N., 2018. Human arm joints reconstruction algorithm in rehabilitation therapies assisted by end-effector robotic devices. Journal of neuroengineering and rehabilitation 15, 1–11.
Bertomeu-Motos, A., Ezquerro, S., Barios, J. A., Catalán, J. M., Blanco- Ivorra, A., Martinez-Pascual, D., Garcia-Aracil, N., 2023. Feasibility of an intelligent home-based neurorehabilitation system for upper extremity mobility assessment. IEEE Sensors Journal 23 (24), 31117–31124. DOI: 10.1109/JSEN.2023.3326531
Bohannon, R. W., Smith, M. B., 1987. Interrater reliability of a modified ashworth scale of muscle spasticity. Physical therapy 67 (2), 206–207. Fugl-Meyer, A. R., J¨a¨ask¨o, L., Leyman, I., Olsson, S., Steglind, S., 1975. A method for evaluation of physical performance. Scand J Rehabil Med 7 (1), 13–31.
Gorelick, P. B., 2019. The global burden of stroke: persistent and disabling. The Lancet Neurology 18 (5), 417–418.
Le Guennec, A., Malinowski, S., Tavenard, R., 2016. Data augmentation for time series classification using convolutional neural networks. In: ECML/PKDD workshop on advanced analytics and learning on temporal data.
Maceira-Elvira, P., Popa, T., Schmid, A.-C., Hummel, F. C., 2019. Wearable technology in stroke rehabilitation: towards improved diagnosis and treatment of upper-limb motor impairment. Journal of neuroengineering and rehabilitation 16, 1–18.
Moulaei, K., Sheikhtaheri, A., Nezhad, M. S., Haghdoost, A., Gheysari, M., Bahaadinbeigy, K., 2022. Telerehabilitation for upper limb disabilities: a scoping review on functions, outcomes, and evaluation methods. Archives of Public Health 80 (1), 196.
Panwar, M., Biswas, D., Bajaj, H., J¨obges, M., Turk, R., Maharatna, K., Acharyya, A., 2019. Rehab-net: Deep learning framework for arm movement classification using wearable sensors for stroke rehabilitation. IEEE Transactions on Biomedical Engineering 66 (11), 3026–3037.
Rosafalco, L., Manzoni, A., Mariani, S., Corigliano, A., 2020. Fully convolutional networks for structural health monitoring through multivariate time series classification. Advanced Modeling and Simulation in Engineering Sciences 7 (1), 38.
Sakoe, H., Chiba, S., 1978. Dynamic programming algorithm optimization for spoken word recognition. IEEE transactions on acoustics, speech, and signal processing 26 (1), 43–49.
Schwarz, A., Bhagubai, M. M., Nies, S. H., Held, J. P., Veltink, P. H., Buurke, J. H., Luft, A. R., 2022. Characterization of stroke-related upper limb motor impairments across various upper limb activities by use of kinematic core set measures. Journal of neuroengineering and rehabilitation 19, 1–18.
See, J., Dodakian, L., Chou, C., Chan, V., McKenzie, A., Reinkensmeyer, D. J., Cramer, S. C., 2013. A standardized approach to the fugl-meyer assessment and its implications for clinical trials. Neurorehabilitation and neural repair 27 (8), 732–741.
Serra, J., Pascual, S., Karatzoglou, A., 2018. Towards a universal neural network encoder for time series. In: CCIA. pp. 120–129.
Steinmetz, J. D., Seeher, K. M., Schiess, N., Nichols, E., Cao, B., Servili, C., Cavallera, V., Cousin, E., Hagins, H., Moberg, M. E., et al., 2024. Global, regional, and national burden of disorders affecting the nervous system, 1990–2021: a systematic analysis for the global burden of disease study 2021. The Lancet Neurology 23 (4), 344–381.
Velozo, C. A.,Woodbury, M. L., 2011. Translating measurement findings into rehabilitation practice: an example using fugl-meyer assessment-upper extremity with patients following stroke. Journal of Rehabilitation Research & Development 48 (10).
Wang, X., Zhang, J., Xie, S. Q., Shi, C., Li, J., Zhang, Z.-Q., 2024. Quantitative upper limb impairment assessment for stroke rehabilitation: a review. IEEE Sensors Journal 24 (6), 7432–7447.
Wang, Z., Yan, W., Oates, T., 2017. Time series classification from scratch with deep neural networks: A strong baseline. In: 2017 International joint conference on neural networks (IJCNN). IEEE, pp. 1578–1585.
Zhao, B., Lu, H., Chen, S., Liu, J., Wu, D., 2017. Convolutional neural networks for time series classification. Journal of Systems Engineering and Electronics 28 (1), 162–169.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 David Martínez Pascual, Yolanda Vales, Raúl Martín Batanero, Pablo Rubira Úbeda, José María Catalán Orts, Luís Daniel Lledó Pérez, Nicolás Manuel García Aracil
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
