Krusienski, Dean J.

A brain-computer interface (BCI) is a device that uses brain signals to provide a non-muscular communication channel [1], particularly for individuals with severe neuromuscular disabilities. One of the most promising signals for controlling a BCI are event-related potentials (ERPs) such as the P300. The P300 event related potential is an evoked response to an external stimulus that has been traditionally observed in scalp-recorded electroencephalography (EEG). The scalp-recorded P300 response has proven to be a reliable signal for controlling a BCI using the P300 Speller paradigm [2]. Recent studies have demonstrated that the P300 Speller has the potential to serve as an effective communication device for persons who have lost or are losing the ability to write and speak.

Objective. Brain–computer interfaces (BCIs) are devices that enable severely disabled people to communicate and interact with their environments using their brain waves. Most studies investigating BCI in humans have used scalp EEG as the source of electrical signals and focused on motor control of prostheses or computer cursors on a screen. The authors hypothesize that the use of brain signals obtained directly from the cortical surface will more effectively control a communication/spelling task compared to scalp EEG. Methods. A total of 6 patients with medically intractable epilepsy were tested for the ability to control a visual keyboard using electrocorticographic (ECOG) signals. ECOG data collected during a P300 visual task paradigm were preprocessed and used to train a linear classifier to subsequently predict the intended target letters. Results. The classifier was able to predict the intended target character at or near 100% accuracy using fewer than 15 stimulation sequences in 5 of the 6 people tested. ECOG data from electrodes outside the language cortex contributed to the classifier and enabled participants to write words on a visual keyboard. Conclusions. This is a novel finding because previous invasive BCI research in humans used signals exclusively from the motor cortex to control a computer cursor or prosthetic device. These results demonstrate that ECOG signals from electrodes both overlying and outside the language cortex can reliably control a visual keyboard to generate language output without voice or limb movements.