Abstract
Background. There are over 33 000 people in the US living with complete tetraplegia due to spinal cord injury (SCI). People with complete tetraplegia rank restoration of hand and arm function as their highest priority, as it would offer greater independence and improved quality of life. In this study, we show that subjects with chronic (>1-year post-injury) C5 or C6 level, motor-complete SCI are able to control a brain computer interface-functional electrical stimulation (BCI-FES) system to enable hand opening and closing. Methods: 8 subjects with C5 or C6 motor-level SCI and 6 uninjured, control subjects participated in 6 sessions of BCI-FES sessions. Electroencephalographic (EEG) signals were acquired using a wireless EEG system and subjects were asked to 'imagine moving their right hand' for motor imagery. Average power was extracted in 5 Hz bins (6-35 Hz) from C3, C1, Cz, C2, and C4 electrodes and input as features to a support vector machine classification algorithm. When 'movement intention' was classified correctly from the motor imagery period, a custom-designed stimulation sequence was delivered to the forearm muscles via surface electrodes to enable opening and closing of the hand. Results: Average online decoding accuracy during the closed-loop BCI-FES sessions was similar for the SCI (74.8% 17.76) and the control (75.5% 11.94) group. Online decoding accuracies were validated using Monte Carlo simulations that used 30%, 50%, and 70% training data to validate the decoded online accuracy and Wilcoxon rank sum test found no significant differences between the SCI and Control subjects. Conclusions: This study demonstrates that subjects with motor complete, cervical SCI were able to control a BCI-FES system with decoding accuracies similar to healthy controls after minimal BCI-training. Non-invasive BCI-FES systems may have the potential to restore hand function in people with motor-complete SCI to improve their quality of life.
