On the control of brain-computer interfaces by users with cerebral palsy

Abstract

Objective: Brain-computer interfaces (BCIs) have been proposed as a potential assistive device for individuals with cerebral palsy (CP) to assist with their communication needs. However, it is unclear how well-suited BCIs are to individuals with CP. Therefore, this study aims to investigate to what extent these users are able to gain control of BCIs.

Methods: This study is conducted with 14 individuals with CP attempting to control two standard online BCIs (1) based upon sensorimotor rhythm modulations, and (2) based upon steady state visual evoked potentials.

Results: Of the 14 users, 8 are able to use one or other of the BCIs, online, with a statistically significant level of accuracy, without prior training. Classification results are driven by neurophysiological activity and not seen to correlate with occurrences of artifacts. However, many of these users' accuracies, while statistically significant, would require either more training or more advanced methods before practical BCI control would be possible.

Conclusions: The results indicate that BCIs may be controlled by individuals with CP but that many issues need to be overcome before practical application use may be achieved.

Significance: This is the first study to assess the ability of a large group of different individuals with CP to gain control of an online BCI system. The results indicate that six users could control a sensorimotor rhythm BCI and three a steady state visual evoked potential BCI at statistically significant levels of accuracy (SMR accuracies; mean ± STD, 0.821 ± 0.116, SSVEP accuracies; 0.422 ± 0.069).

Keywords: Brain-computer interface; Cerebral palsy; Mental task; Motor imagery; Sensorimotor rhythm; Steady-state visual evoked potential.