User Adaptation to Closed-Loop Decoding of Motor Imagery Termination

One of the most popular methods in non-invasive brain machine interfaces (BMI) relies on the decoding of sensorimotor rhythms associated to sustained motor imagery. Although motor imagery has been intensively studied, its termination is mostly neglected. Objective: Here, we provide insights in the decoding of motor imagery termination and investigate the use of such decoder in closed-loop BMI. Methods: Participants (N = 9) were asked to perform kinesthetic motor imagery of both hands simultaneously cued with a clock indicating the initiation and termination of the action. Using electroencephalogram (EEG) signals, we built a decoder to detect the transition between event-related desynchronization and event-related synchronization. Features for this decoder were correlates of motor termination in the upper mu and beta bands. Results: The decoder reached an accuracy of 76.2% (N = 9), revealing the high robustness of our approach. More importantly, this paper shows that the decoding of motor termination has an intrinsic latency mainly due to the delayed appearance of its correlates. Because the latency was consistent and thus predictable, users were able to compensate it after training. Conclusion: Using our decoding system, BMI users were able to adapt their behavior and modulate their sensorimotor rhythm to stop the device (clock) accurately on time. Significance: These results show the importance of closed-loop evaluations of BMI decoders and open new possibilities for BMI control using decoding of movement termination.