Dynamics of motor imagery skill formation using a brain – computer interface with multimodal feedback

Objective: to study the dynamics of motor imagery skill acquisition during the use of a brain – computer interface providing visual and vibrotactile biofeedback. Material and methods. The pilot study included 10 healthy volunteers aged 29–34 years. All subjects were right-handed. Within a five-day protocol, two feedback channels were used: visual and vibrotactile. Detection of moments of imagined movements was performed in real time using a classifier based on the analysis of EEG activity patterns. The success rate (proportion) of recognizing imagined movements of the left and right hand was assessed over the course of five experimental sessions. Results. It has been shown that learning is characterized by a U-shaped trajectory: after a short-term decrease in success rate in the middle of the training sessions (from initial values of 76 and 80% to 66 and 71% for the right and left hand, respectively), the performance significantly improves by the 4–5th session, reaching the maximum values for the entire experimental period (approximately 85 and 90%, respectively). This reflects the formation of stable neural patterns. Conclusion. The formation of motor imagery skill using a brain – computer interface with visual and vibrotactile feedback follows a U‑shaped trajectory, peaking on day 5 of training.