BACKGROUND: Brain-machine interfaces (BMI) have recently been integrated within motor rehabilitation therapiesby actively involving the central nervous system (CNS) within the exercises. For instance, the onlinedecoding of intention of motion of a limb from pre-movement EEG correlates is being used to convertpassive rehabilitation strategies into active ones mediated by robotics. As early stages of upper limbmotor rehabilitation usually focus on analytic single-joint mobilizations, this paper investigates thefeasibility of building BMI decoders for these specific types of movements. METHODS: Two different experiments were performed within this study. For the first one, six healthy subjectsperformed seven self-initiated upper-limb analytic movements, involving from proximal to distal articulations.For the second experiment, three spinal cord injury patients performed two of the previouslystudied movements with their healthy elbow and paralyzed wrist. In both cases EEG neural correlatessuch as the event-related desynchronization (ERD) and movement related cortical potentials (MRCP)were analyzed, as well as the accuracies of continuous decoders built using the pre-movement featuresof these correlates (i.e., the intention of motion was decoded before movement onset). RESULTS: The studied movements could be decoded in both healthy subjects and patients. For healthy subjects there were significant differences in the EEG correlates and decoding accuracies, dependent onthe moving joint. Percentages of correctly anticipated trials ranged from 75% to 40% (with chancelevel being around 20%), with better performances for proximal than for distal movements. For themovements studied for the SCI patients the accuracies were similar to the ones of the healthy subjects. CONCLUSIONS: This paper shows how it is possible to build continuous decoders to detect movement intention fromEEG correlates for seven different upper-limb analytic movements. Furthermore we report differencesin accuracies among movements, which might have an impact on the design of the rehabilitationtechnologies that will integrate this new type of information. The applicability of the decoders wasshown in a clinical population, with similar performances between healthy subjects and patients.
López-Larraz, E., Montesano, L., Gil-Agudo, Á., & Minguez, J. (2014). Continuous decoding of movement intention of upper limb self-initiated analytic movements from pre-movement EEG correlates. Journal of NeuroEngineering and Rehabilitation, 11(1). https://doi.org/10.1186/1743-0003-11-153