Online detection of movement during natural and self-initiated reach-and-grasp actions from EEG signals.

Movement intention detection using electroencephalography (EEG) is a challenging but important component of brain-computer interfaces (BCIs) for people with motor disabilities. Objective​: The goal of this study is to exploit low-frequency time-domain EEG signals, concretely movement-related cortical potentials (MRCPs), to perform asynchronous online detection of movement. The experimental paradigm must be easily transferable to people without any residual upper-limb movement function. To achieve that goal, the BCI must be independent of upper-limb movement onset measurements and external cues. ​Approach​: In a study with non-disabled participants, we evaluated a novel BCI paradigm to detect self-initiated reach-and-grasp movements. Two experimental conditions were involved. In one condition, participants performed reach-and-grasp movements to a target and simultaneously shifted their gaze towards it. In a control condition, participants solely shifted their gaze towards the target (oculomotor task). The participants freely decided when to initiate the tasks. The saccade onset was used to label the EEG features, which were exploited on a hierarchical classification approach to detect movement asynchronously. ​Main results​: After correcting eye artifacts, movement information was mapped to sensorimotor, posterior parietal and occipital areas. With regards to BCI performance, 54.1% (14.4% SD) of the movements were correctly identified, and all participants achieved a performance above chance-level (around 12%). An average of 21.5% (14.1% SD) of the oculomotor tasks were falsely detected as upper-limb movement. In an additional rest condition, 1.7 (1.6 SD) false positives per minute were measured. ​Significance​: We present a new approach for movement detection which does not rely on upper-limb movement onset measurements or on the presentation of external cues. The task is intuitive and corresponds to the natural behavior of goal-directed movements, which also constitutes an advantage with respect to current BCI protocols.