Exploring Novel Practical Approach to Post-Stroke Upper-Limb Neurorehabilitation Based on Complex Motor Imagery Tasks.

Abstract

Motor imagery (MI) is one of the main strategies for upper-limb movement rehabilitation in post-stroke individuals. Promising results of MI applied for rehabilitation have been reported in the literature. However, there is currently a need related to the recovery of movements aimed to Activities of Daily Living (ADLs) for individuals with severe motor impairments. Therefore, this study presents the evaluation of a novel MI protocol for post-stroke upper-limb neurorehabilitation using complex tasks related to the manipulation of a drinking cup. The protocol is based on the Action Observation (AO), which was used under a first-person 2D virtual reality. Subjects had to simultaneously imagine the movements presented in AO for the manipulation of a cup varying in four positions. EEG signals were recorded from 16 channels located mainly in the motor cortex of the brain. Two computational strategies based on Riemannian Geometry (RG) with and without Feature Selection (FS) using Pair-Wise Feature Proximity (PWFP) were implemented for the binary identification of each complex MI-Task vs. MI-Rest. This approach was evaluated on 30 healthy individuals and 2 post-stroke individuals. Using Linear Discriminant Analysis (LDA) as a classifier, the results report a maximum accuracy of 0.78 for both healthy and post-stroke individuals, and a minimum FPR of 0.21 and 0.13 for healthy and post-stroke individuals, respectively. This highlights the potential use of this type of paradigms for the implementation of more robust BCI systems that allow the rehabilitation of movements close to ADLs. Therefore, complex MI tasks may be a suitable variant for rehabilitation in post-stroke individuals.