Development of an 'eyes-closed' brain-computer interface system for communication of patients with oculomotor impairment

The goal of this study was to develop a new steady-state visual evoked potential (SSVEP)-based BCI system, which can be applied to disabled individuals with impaired oculomotor function. The developed BCI system allows users to express their binary intentions without needing to open their eyes. To present visual stimuli, we used a pair of glasses with two LEDs flickering at different frequencies. EEG spectral patterns were classified in real time while participants were attending to one of the presented visual stimuli with their eyes closed. Through offline experiments performed with 11 healthy participants, we confirmed that SSVEP responses could be modulated by visual selective attention to a specific light stimulus penetrating through the eyelids, and could be classified with accuracy high enough for use in a practical BCI system. After customizing the parameters of the proposed SSVEP-based BCI paradigm based on the offline analysis results, binary intentions of five healthy participants and one locked-in state patient were classified online. The average ITR of the online experiments reached to 10.83 bits/min with an average accuracy of 95.3 %. An online experiment applied to a patient with ALS showed a classification accuracy of 80 % and an ITR of 2.78 bits/min, demonstrating the practical feasibility of our BCI paradigm.