Accepted Articles
Back to the articles list |
Back to browse issues page
1- Department of Electrical and Biomedical Engineering, Faculty of Engineering and Technology, Shahid Ashrafi Esfahani University, Isfahan, Iran.
Abstract:
Noninvasive electroencephalography (EEG)-based brain–computer interfaces (BCIs) have emerged as promising tools for restoring motor and communication functions in individuals with neurological impairments. Despite substantial technological progress, the translation of EEG-based BCI systems from laboratory environments to routine clinical rehabilitation remains limited. This critical narrative review synthesizes advances reported between 2021 and 2025, focusing on endogenous paradigms such as motor imagery and exogenous paradigms including P300 and steady-state visually evoked potentials (SSVEP), as well as developments in signal processing, machine learning, and rehabilitation applications. Relevant peer-reviewed studies were identified through IEEE Xplore, PubMed, and Scopus and evaluated through a thematic synthesis approach. Owing to considerable methodological heterogeneity across paradigms, hardware configurations, and outcome measures, a formal meta-analysis was not performed. Instead, studies were critically examined in terms of acquisition hardware, feature extraction and classification strategies, and clinical rehabilitation applications. The reviewed literature indicates that EEG-based BCIs can achieve high classification accuracies under controlled conditions, ranging from 93.2% for motor imagery systems to over 99% for P300-based spellers. Recent self-supervised and transformer-based approaches have further improved cross-subject generalization and reduced calibration requirements, reporting accuracies of approximately 94–95%. However, real-world deployment continues to be constrained by signal instability, motion artifacts, limitations of low channel wearable devices, and a lack of longitudinal evidence demonstrating functional outcomes and usability. Future research should prioritize robustness, adaptability, and long-term clinical reliability through standardized real world validation, user-centered design, and interdisciplinary collaboration to facilitate the transition of EEG-based BCIs into scalable rehabilitation technologies.
Keywords: Brain-Computer Interface (BCI), Electroencephalography (EEG), Motor Imagery, Deep Learning, Neurorehabilitation, Clinical Translation
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
Copyright © The Author(s);
This is an open access article distributed under the terms of the Creative Commons Attribution License (CC-By-NC), which permits use, distribution, and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.
Contact Information
