The Effectiveness of Artificial Intelligence and Robotics-Based Physical Therapy in Rehabilitating Stroke Patients
DOI:
https://doi.org/10.69980/ajpr.v28i5.528Keywords:
stroke rehabilitation, robotics, artificial intelligence, motor recovery, meta-analysis.Abstract
Background: Stroke remains a leading cause of long-term disability, necessitating innovative rehabilitation approaches. Artificial intelligence (AI) and robotics-based physical therapy have emerged as promising interventions to enhance motor recovery, balance, and functional independence in stroke patients. This systematic review and meta-analysis evaluates the efficacy of these technologies compared to conventional rehabilitation methods.
Methods: Ten randomized controlled trials (RCTs) and proof-of-concept studies published between 2020 and 2025 were included. Studies assessed AI and robotic interventions, such as exoskeletons, brain-computer interfaces (BCIs), and adaptive robotic systems, focusing on outcomes like Fugl-Meyer Assessment (FMA), Berg Balance Scale (BBS), and gait metrics. Data were extracted by independent reviewers, and meta-analyses were conducted using random-effects models to pool mean differences (MD) with 95% confidence intervals (CI). Heterogeneity was assessed via the I² statistic, and risk of bias was evaluated using the Cochrane ROB tool.
Results: The meta-analysis revealed significant improvements in motor function (FMA: MD = 4.36, 95% CI: 2.46–6.26, p < 0.05) and balance (BBS: MD = 7.18, 95% CI: 4.79–9.57, p < 0.05) favoring robotic and AI-assisted interventions. Notable findings included the superiority of BCI training with exoskeleton feedback (12.77% improvement in FMA-UE) and adaptive systems like ROBiGAME (r = 0.84 for task adaptation). Telerehabilitation studies showed mixed outcomes, with robotic interventions excelling in mood improvement but lagging in motor gains compared to non-robotic approaches. Heterogeneity was low (I² < 25%), and most studies had low risk of bias.
Conclusion: AI and robotics-based rehabilitation significantly enhance motor and functional recovery post-stroke, offering personalized, scalable, and data-driven solutions. Future research should standardize protocols, address cost barriers, and explore long-term outcomes to facilitate clinical adoption. These technologies represent transformative adjuncts to traditional therapy, promising better recovery paradigms for stroke survivors.
References
1. CHEN, S., CAO, L., SHU, X., WANG, H., DING, L., WANG, S.-H. & JIA, J. 2020. Longitudinal electroencephalography analysis in subacute stroke patients during intervention of brain–computer interface with exoskeleton feedback. Frontiers in neuroscience, 14, 809.
2. DOUMAS, I., LEJEUNE, T., EDWARDS, M., STOQUART, G., VANDERMEEREN, Y., DEHEZ, B. & DEHEM, S. 2025. Clinical validation of an individualized auto-adaptative serious game for combined cognitive and upper limb motor robotic rehabilitation after stroke. Journal of NeuroEngineering and Rehabilitation, 22, 10.
3. HAOLIN, T., YUANBIN, Y., ZHANG, H., WENJING, Z., JING, Z., JINGFENG, T., LONG, H., XUECHAO, L., QINXUAN, S. & SHUAI, M. 2024. Efficacy of Daoyin combined with lower limb robot as a comprehensive rehabilitation intervention for stroke patients: a randomized controlled trial. Journal of Traditional Chinese Medicine, 44, 530.
4. HUO, C., SHAO, G., CHEN, T., LI, W., WANG, J., XIE, H., WANG, Y., LI, Z., ZHENG, P. & LI, L. 2024. Effectiveness of unilateral lower-limb exoskeleton robot on balance and gait recovery and neuroplasticity in patients with subacute stroke: a randomized controlled trial. Journal of NeuroEngineering and Rehabilitation, 21, 1-16.
5. LEE, J., CHUN, M. H., SEO, Y. J., LEE, A., CHOI, J. & SON, C. 2022a. Effects of a lower limb rehabilitation robot with various training modes in patients with stroke: A randomized controlled trial. Medicine, 101, e31590.
6. LEE, S.-H., KIM, S. S. & LEE, B.-H. 2022b. Action observation training and brain-computer interface controlled functional electrical stimulation enhance upper extremity performance and cortical activation in patients with stroke: a randomized controlled trial. Physiotherapy theory and practice, 38, 1126-1134.
7. MENG, G., MA, X., CHEN, P., XU, S., LI, M., ZHAO, Y., JIN, A. & LIU, X. 2022. Effect of early integrated robot-assisted gait training on motor and balance in patients with acute ischemic stroke: a single-blinded randomized controlled trial. Therapeutic Advances in Neurological Disorders, 15, 17562864221123195.
8. PAVAN, A., FASANO, A., LATTANZI, S., CORTELLINI, L., CIPOLLINI, V., INSALACO, S., MAURO, M. C., GERMANOTTA, M. & APRILE, I. G. 2024. Effectiveness of Two Models of Telerehabilitation in Improving Recovery from Subacute Upper Limb Disability after Stroke: Robotic vs. Non-Robotic. Brain Sciences, 14, 941.
9. ZHANG, H., LI, X., GONG, Y., WU, J., CHEN, J., CHEN, W., PEI, Z., ZHANG, W., DAI, L. & SHU, X. 2023. Three‐dimensional gait analysis and sEMG measures for robotic‐assisted gait training in subacute stroke: a randomized controlled trial. BioMed research international, 2023, 7563802.
10. ZHANG, Y., ZHAO, W., WAN, C., WU, X., HUANG, J., WANG, X., HUANG, G., DING, W., CHEN, Y. & YANG, J. 2024. Exoskeleton rehabilitation robot training for balance and lower limb function in sub-acute stroke patients: a pilot, randomized controlled trial. Journal of NeuroEngineering and Rehabilitation, 21, 98.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 American Journal of Psychiatric Rehabilitation
This work is licensed under a Creative Commons Attribution 4.0 International License.
This is an Open Access article distributed under the terms of the Creative Commons Attribution 4.0 International License permitting all use, distribution, and reproduction in any medium, provided the work is properly cited.
