Real-time neurofeedback is effective in reducing diversion of attention from a motor task in healthy individuals and patients with amyotrophic lateral sclerosis.

Abstract

The performance of brain-computer interface (BCI) systems is influenced by the user's mental state, such as attention diversion. In this study, we propose a novel online BCI system able to adapt with variations in the users' attention during real-time movement execution. Electroencephalography signals were recorded from healthy participants and patients with Amyotrophic Lateral Sclerosis while attention to the target task (a dorsiflexion movement) was drifted using an auditory oddball task. For each participant, the selected channels, classifiers and features from a training data set were used in the online phase to predict the attention status. For both healthy controls and patients, feedback to the user on attentional status reduced the amount of attention diversion. The findings presented here demonstrate successful monitoring of the users' attention in a fully online BCI system, and further, that real-time neurofeedback on the users' attention state can be implemented to focus the attention of the user back onto the main task.