On the design of EEG-based movement decoders for completely paralyzed stroke patients

Martin Spüler,Eduardo López-Larraz,Ander Ramos-Murguialday

doi:10.1186/s12984-018-0438-z

Martin Spüler, Eduardo López-Larraz + Show 1 more

Open Access

https://doi.org/10.1186/s12984-018-0438-z

Copy DOI

Abstract

BackgroundBrain machine interface (BMI) technology has demonstrated its efficacy for rehabilitation of paralyzed chronic stroke patients. The critical component in BMI-training consists of the associative connection (contingency) between the intention and the feedback provided. However, the relationship between the BMI design and its performance in stroke patients is still an open question.MethodsIn this study we compare different methodologies to design a BMI for rehabilitation and evaluate their effects on movement intention decoding performance. We analyze the data of 37 chronic stroke patients who underwent 4 weeks of BMI intervention with different types of association between their brain activity and the proprioceptive feedback. We simulate the pseudo-online performance that a BMI would have under different conditions, varying: (1) the cortical source of activity (i.e., ipsilesional, contralesional, bihemispheric), (2) the type of spatial filter applied, (3) the EEG frequency band, (4) the type of classifier; and also evaluated the use of residual EMG activity to decode the movement intentions.ResultsWe observed a significant influence of the different BMI designs on the obtained performances. Our results revealed that using bihemispheric beta activity with a common average reference and an adaptive support vector machine led to the best classification results. Furthermore, the decoding results based on brain activity were significantly higher than those based on muscle activity.ConclusionsThis paper underscores the relevance of the different parameters used to decode movement, using EEG in severely paralyzed stroke patients. We demonstrated significant differences in performance for the different designs, which supports further research that should elucidate if those approaches leading to higher accuracies also induce higher motor recovery in paralyzed stroke patients.

Highlights

Brain machine interface (BMI) technology has demonstrated its efficacy for rehabilitation of paralyzed chronic stroke patients
We evaluated the influence on decoding accuracy of relying on: (1) the alpha band only (8–12 Hz), (2) the beta band only (15– 30 Hz), or alpha and beta bands together (8–30 Hz), Classifier For classification, we compared the simple linear classifier used for online feedback during the BMI training [2, 29], and an adaptive approach based on support vector machines (SVM), as proposed in [32]
The use of electrodes from both hemispheres, common average reference (CAR) as spatial filter, the beta band, and the adaptive SVM classifier resulted in the best BMI accuracy

Summary

Introduction

Brain machine interface (BMI) technology has demonstrated its efficacy for rehabilitation of paralyzed chronic stroke patients. In humans with stroke, when bihemispheric electroencephalographic (EEG) activity is considered to decode movement commands (i.e., motor attempt or motor imagery) of the paralyzed limbs, the achieved performances are higher than if only ipsilesional activity is considered [15, 16] It is unclear if using a BMI to link contralesional or bihemispheric brain activity with proprioceptive feedback in the paretic limb would elicit the same or better functional results than if ipsilesional activity is used [2] and it is out of the scope of this manuscript. In this manuscript we discuss different option to create that link (BMI design) to optimize motor control (BMI performance)

Methods

Results

Discussion

Conclusion