The classification of walking and phases of gait using EEG: a scoping review.

Brain computer interfaces (BCI) have been highlighted as having potential to optimise therapeutic robotic assisted gait training by ‘closing the loop’ between humans and robotic devices. However, there is a need to first develop classification systems that can recognise distinct gait phases (e.g. stance and swing phases) and walking from other motor activity before entraining back to robotic devices in real time. No consensus exists on what EEG data is helpful or the optimal gait classification system. Therefore, the primary aim of this scoping review is to collate existing studies addressing the classification of gait (and phases of gait) using EEG, synthesize the research field and identify gaps and opportunities for further research studies. Specific objectives include: 1) To systematically identify and report all studies classifying gait and/or its relevant phases using EEG. 2) To determine what gait, as a global movement pattern, is being classified against and with what degrees of accuracy . 3) To identify the volume of studies that have addressed the classification of gait and gait phases by EEG, identify how gait is commonly broken down and described, as well as the accuracy level reported between the phases. 4)To describe the methodological processes described in the identified studies including the technology utilised, the frequency bands analysed, artifact management, the features extracted and used, the classification systems used. 5) To map the cortical activity described in the literature for the phases of gait.