Investigation of Brain Computer Interface Based Exoskeleton in Rehabilitation

Authors

DOI:

https://doi.org/10.36283/pjr.zu.14.2/012

Keywords:

Brain-Computer Interfaces, Exoskeleton Device, Electroencephalography, Neurological Rehabilitation, Stroke Rehabilitation, Motor Activity

Abstract

 

Background of the study: The integration of Brain-Computer Interface (BCI) technology with exoskeletons has introduced novel solutions in the field of neurorehabilitation. BCI-based exoskeletons harness neural signals to control robotic limbs, offering enhanced motor restoration, improved patient engagement, and potential autonomy for individuals with disabilities. BCI-based exoskeletons offer a modern approach by utilizing neural signals to control robotic devices, enhancing movement ability and promoting rehabilitation in patients with motor dysfunctions. This article discussed recent advancements in BCI technology in the context of exoskeletons and analyzed the integration of BCI with exoskeletons.

Methodology: A literature review was conducted using IEEE Xplore to identify original studies from 2018 to 2023 implementing BCI-exoskeleton systems for clinical populations. Inclusion criteria required studies to involve clinical populations using BCI-exoskeletons for either upper or lower limb rehabilitation. Descriptive analysis and linear regression were applied to evaluate input signal types (EEG vs. EMG) and rehabilitation outcomes.

Results: All selected studies involved stroke patients, predominantly using EEG signals. EEG-based systems showed 67% greater improvement rates compared to EMG systems, though the result was not statistically significant (p = 0.200). Key challenges identified included limited clinical trials, high cost, bulky design, system safety, and lack of pediatric applications.

Conclusion: BCI-integrated exoskeletons represent a promising advancement in rehabilitation, enabling personalized and neuroadaptive support for individuals with motor dysfunctions. However, clinical validation remains limited for outcomes in real-world settings.

Author Biographies

  • Muhammad Mansoor Mughal, Hamdard University, Karachi, Pakistan/University of Houston, Texas, USA.

    Senior Lecturer, Department of Biomedical Engineering and Postgraduate Student

  • Tariq Javed, Hamdard University Karachi, Pakistan

    Professor and Chairman, Department of Biomedical Engineering

  • Muhammad Faris, Hamdard University Karachi, Pakistan

    Associate Professor and Head of Department, Department of Biomedical Engineering

References

Ferrero L, et al. Transfer learning with CNN models for brain-machine interfaces to command lower-limb exoskeletons: a solution for limited data. Proc IEEE Eng Med Biol Soc. 2023:1-4.

Zhang X, Wang M, Wang H, Wang F, Chen L, Mu W, et al. Design and performance analysis of a bioelectronic controlled hybrid serial-parallel wrist exoskeleton. IEEE Trans Neural Syst Rehabil Eng. 2023;31:1-1.

Zhang Y, Cao L, Xu M, Liu Y. A hybrid EEG-NIRS brain-computer interface for enhanced classification of motor imagery tasks. IEEE Trans Neural Syst Rehabil Eng. 2023;31:134-45.

Lu Z, Peng Y, Jin J, Wang X. Development of a soft wearable lower-limb exosuit for post-stroke gait rehabilitation. IEEE Trans Med Robot Bionics. 2021;3(2):248-56.

He J, Wang F, Lin L, Zhang D. Adaptive BCI based on Riemannian geometry for EEG motor imagery classification. IEEE Trans Neural Netw Learn Syst. 2023;34(4):1740-52.

Wu J, Zhou D, Wang Q, Zhang H. Deep learning-based BCI for post-stroke upper limb rehabilitation. IEEE Access. 2022;10:123456-69.

Wu L, Fan X, Wang Z, Sun J. Classification of motor imagery EEG signals based on multi-domain features. IEEE Trans Instrum Meas. 2023;72:1-10.

Yao L, Shi X, Zhang Y, Li Z. A hybrid fNIRS-EEG brain-computer interface system for motor control. IEEE Trans Biomed Circuits Syst. 2022;16(1):77-88.

Tiwari A, Kumar S, Sharma R. Real-time immersive virtual reality-based motor imagery BCI: a usability study. Front Hum Neurosci. 2021;15:620.

Rashid M, et al. Current status, challenges, and possible solutions of EEG-based brain-computer interface: a comprehensive review. Front Neurorobot. 2020;14:25.

Rahman MM, Begum S, Ahmad MO. Affective computing using EEG: a review of recent advances and future directions. IEEE Rev Biomed Eng. 2023;16:210-24.

Li X, Zhang Y, Jin H, Liu S. Design of a brain-computer interface system to control assistive service robots. IEEE Access. 2023;11:67890-67899.

Smith JS, et al. Design of a brain-computer interface to control an unmanned aerial vehicle using a consumer-grade EEG headset. Proc IEEE Aerosp Conf. 2020:1-10.

Jiang L, Zhang Q, Li G, Zhang H. Neural decoding of continuous finger kinematics from intracortical signals using deep learning. J Neural Eng. 2023;20(1):016012.

Khademi M, Fazli S, Müller KR. A hybrid EEG-based BCI for controlling a lower-limb exoskeleton in chronic stroke rehabilitation. IEEE Trans Neural Syst Rehabil Eng. 2022;30:456-65.

Bashashati A, Fatourechi M, Ward RK, Birch GE. EEG-based classification of mental tasks using empirical mode decomposition and support vector machines. IEEE Trans Biomed Eng. 2022;69(2):511-20.

Ahmed S, Tariq A, Jamil M, Khan A. Combining immersive virtual reality and EEG-based BCIs for enhanced neurofeedback training: a review. Front Virtual Real. 2023;4:1045992.

Ferrante S. Wearable robotics: challenges and trends. Cham: Springer; 2020.

Zhang L, Fan Y, Li J, Zhao X. A soft robotic exosuit with adaptive control for gait assistance in post-stroke patients. IEEE Trans Neural Syst Rehabil Eng. 2021;29:1120-29.

Kim H, Park J, Lee S, Lee Y. Pediatric lower-limb exoskeleton for gait rehabilitation: experimental study on control strategies. IEEE Access. 2023;11:44520-44531.

Lerner J, Chen B, Wang J, Steele K, Sung J. A robotic exoskeleton for treatment of overground gait rehabilitation in pediatric population. IEEE Trans Neural Syst Rehabil Eng. 2020;28(3):728-35.

GoGoA. Exoesqueletos [Internet]. Available from: https://www.gogoa.eu/en/exoesqueletos [cited 2024 Apr 20].

Eguren D, Contreras-Vidal JL. Navigating the FDA medical device regulatory pathways for pediatric lower limb exoskeleton devices. IEEE Syst J. 2021;15(2):2361-68.

U.S. Food and Drug Administration. Classify your medical device [Internet]. Available from: https://www.fda.gov/medical-devices/overview-device-regulation/classify-your-medical-device [cited 2024 Apr 20].

Eguren D, Contreras-Vidal JL. Navigating the FDA medical device regulatory pathways for pediatric lower limb exoskeleton devices. IEEE Syst J. 2021;15(2):2361.

Centers for Disease Control and Prevention. Falls prevention [Internet]. Available from: https://www.cdc.gov/falls/index.html [cited 2024 Apr 20].

Ravindran AS, Qian J, Adeli H, Sanei S, Chan A. Interpretable deep learning models for single trial prediction of balance loss. Proc IEEE Int Conf Syst Man Cybern. 2020:268-73.

Ravindran AS, Chan A, Sanei S, Adeli H. Decoding neural activity preceding balance loss during standing with a lower-limb exoskeleton using an interpretable deep learning model. J Neural Eng. 2022;19(3):036015.

Sharma A, Pathak P, Chauhan H, Mehta A. A modular wearable pediatric exoskeleton for adaptive rehabilitation: design and control validation. IEEE Trans Med Robot Bionics. 2023;5(2):115-25.

Arena Solutions. How to classify your medical device for FDA approval [Internet]. Available from: https://www.arenasolutions.com/resources/articles/how-to-classify-your-medical-device-for-fda-approval/ [cited 2024 Apr 20].

Downloads

Published

2025-07-07

Issue

Vol. 14 No. 02 (2025): Pakistan Journal of Rehabilitation

Section

Original Articles

License

Copyright (c) 2025 Pakistan Journal of Rehabilitation

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Metrics