Using brain–computer interfaces for personalized neurorehabilitation: the role of subjective perception and neurophysiological indicators

   The study was set to assess the correspondence between neurophysiological and subjective indicators of motor imagination in the context of neurorehabilitation using brain-computer interfaces (BCIs). It was conducted as part of the development of a software and hardware complex (SHC) aimed at restoring cognitive and motor functions of the upper limbs in individuals with mild to severe impairments.

   Materials and Methods: Twenty-four healthy volunteers participated in the study. Electroencephalographic activity was recorded during motor imagery tasks involving different types of visual stimuli. The analysis included the calculation of sensorimotor desynchronization (ERD), classification using spatial filters and linear discriminant analysis, and correlation with subjective self-assessments.

   Results: The lateralization of imagined motion had a significant effect on ERD expression. Participants’ subjective confidence did not correlate with either neurophysiological measures or the classifier’s confidence in recognizing the imagined motion. However, the models demonstrated high accuracy in classifying motor representations.

   Conclusions: The identified discrepancy between subjective and objective assessment highlights the need to implement biofeedback and personalized BCIs into SHC systems to enhance the effectiveness of neurorehabilitation.

1. Feigin VL, et al. World Stroke Organization: Global Stroke Fact Sheet 2025. International Journal of Stroke. 2025; 20(2): 132-144. doi: 10.1177/17474930241308142.

2. Mokienko OA, Suponeva GA, Aziatskaya GA. Insul't u vzroslyh: central'nyj parez verhnej konechnosti. Klinicheskie rekomendacii. O.A. Mokienko, N.A. Suponevа, editors. M.: MEDpress-Inform. 2018: 222. (In Russ.)

3. Joundi RA, et al. Magnitude and time-course of dementia risk in stroke survivors: a population-wide matched cohort study. Neurology. 2025; 104(1): e210131. doi: 10.1212/WNL.0000000000210131.

4. Wood GK, Moore DR, Moon EH, et al. Posthospitalization COVID-19 cognitive deficits at 1 year are global and associated with elevated brain injury markers and gray matter volume reduction. Nature Medicine. 2025; 31(1): 245-257. doi: 10.1038/s41591-024-03309-8.

5. Piradov MA, Hernikova NA, Suponeva AS, et. al. Perspektivy razvitiya robotizirovannyh ustrojstv dlya vosstanovleniya dvizhenij ruki. Roboticheskie tekhnologii v medicine. 2016: 122-130. (In Russ.)

6. Khorev V, Kurkin S, Badarin A, et al. Review on the use of brain computer interface rehabilitation methods for treating mental and neurological conditions. Journal of Integrative Neuroscience. 2024; 23(7): 125. doi: 10.31083/j.jin2307125.

7. Hramov AE, Maksimenko VA, Pisarchik AN. Physical principles of brain-computer interfaces and their applications for rehabilitation, robotics and control of human brain states. Physics Reports. 2021; 918: 1-133. doi: 10.1016/j.physrep.2021.03.002.

8. Frolov AA, Mokienko OA, Lyukmanov RH, et. al. Predvaritel'nye rezul'taty kontroliruemogo issledovaniya effektivnosti tekhnologii IMK-ekzoskelet pri postinsul'tnom pareze ruki. Vestnik Rossijskogo gosudarstvennogo medicinskogo universiteta. 2016; 2: 17-2. (In Russ.)

9. Frolov AA, Chernikova LA, Lyukmanov RH, et. al. Ispol'zovanie medicinskoj tekhnologii «Neinvazivnyj interfejs mozg — komp'yuter — ekzoskelet kisti». Metodicheskie rekomendacii. 2016. (In Russ.)

10. Huang G, Zhao Z, Zhang S, et al. Discrepancy between inter-and intra-subject variability in EEG-based motor imagery brain-computer interface: Evidence from multiple perspectives. Frontiers in Neuroscience. 2023; 17: 1122661. doi: 10.3389/fnins.2023.1122661.

11. Frolov AA, Aziatskaya GA, Bobrov PD, et. al. Elektrofiziologicheskaya aktivnost' mozga pri upravlenii interfejsom mozg-komp'yuter, osnovannym na voobrazhenii dvizheniya. Fiziologiya cheloveka. 2017; 43(5): 17-25. (In Russ).

12. Yang B, Rong F, Xie Y, et al. A multi-day and high-quality EEG dataset for motor imagery brain-computer interface. Scientific Data. 2025; 12(1): 488. doi: 10.1038/s41597-025-04826-y.