Evaluation of a motor imagery electroencephalography brain-computer interface as a communication modality for children with cerebral palsy

House, Sarah 1,2; Chau, Tom 1,2

1 Institute of Biomaterials and Biomedical Engineering, University of Toronto ; 2 Bloorview Research Institute

Cerebral palsy (CP) is the most common cause of childhood disability, limiting the ability of affected children to coordinate their movements and move purposefully. Seventy-one percent of affected children also have speech and language impairments rendering typical communication methods difficult to use or outright impossible. For those with severe forms of CP, limited alternative methods of communication exist. Brain-computer interfaces (BCIs) controlled by imagination of movement of different body parts, known as motor imagery (MI), may serve as a simple and intuitive communication solution. The goal of this study is to create a MI-based pediatric BCI using electroencephalography (EEG) and evaluate the classification accuracies of the BCI when controlled by 20 typically developing children between the ages of 8 and 16. Classification accuracies above 70% indicate successful BCI control. To accomplish this, a MI-BCI has been created using MATLAB. EEG signals are first bandpass filtered to encompass the mu and beta frequency range (7-30 Hz). Features in the signal are extracted using the common spatial pattern algorithm and are then classified with participant specific classification algorithms. BCI performance is tested in one offline session, where the acquired data is used to train the classifier, and multiple online sessions during which visual neurofeedback is provided while participants perform MI to play a computer game. Participants, thus far, have achieved a classification accuracy between 70-89% in a single offline session. The addition of visual neurofeedback in upcoming online sessions is expected to improve achieved classification accuracies. The results of the online sessions will, for the first time, speak to the potential of a MI driven EEG-BCI to be translated to a pediatric population as a communication method and begin to address the lack of user-centered communication devices for children with CP.