Comparing Recalibration Strategies for Electroencephalography-Based Decoders of Movement Intention in Neurological Patients with Motor Disability

Abstract

Motor rehabilitation based on the association of electroencephalographic (EEG) activity and proprioceptive feedback has been demonstrated as a feasible therapy for patients with paralysis. To promote long-lasting motor recovery, these interventions have to be carried out across several weeks or even months. The success of these therapies partly relies on the performance of the system decoding movement intentions, which normally has to be recalibrated to deal with the nonstationarities of the cortical activity. Minimizing the recalibration times is important to reduce the setup preparation and maximize the effective therapy time. To date, a systematic analysis of the effect of recalibration strategies in EEG-driven interfaces for motor rehabilitation has not yet been performed. Data from patients with stroke (4 patients, 8 sessions) and spinal cord injury (SCI) (4 patients, 5 sessions) undergoing two different paradigms (self-paced and cue-guided, respectively) are used to study the performance of the EEG-based classification of motor intentions. Four calibration schemes are compared, considering different combinations of training datasets from previous and/or the validated session. The results show significant differences in classifier performances in terms of the true and false positives (TPs) and (FPs). Combining training data from previous sessions with data from the validation session provides the best compromise between the amount of data needed for calibration and the classifier performance. With this scheme, the average true (false) positive rates obtained are 85.3% (17.3%) and 72.9% (30.3%) for the self-paced and the cue-guided protocols, respectively. These results suggest that the use of optimal recalibration schemes for EEG-based classifiers of motor intentions leads to enhanced performances of these technologies, while not requiring long calibration phases prior to starting the intervention.

Event-related desynchronization during movement attempt and execution in severely paralyzed stroke patients: An artifact removal relevance analysis

“…This is likely due to the higher degree of contamination that we found in the ipsilateral hemisphere during the attempts of movement. In addition, it has important implications for BMIs using the contralesional activity to detect movement attempts of stroke patients ( Ang et al, 2015 ; Antelis et al, 2017 ; López-Larraz et al, 2018a , 2017b; Ono et al, 2014 ; Tangwiriyasakul et al, 2014a ), since the training data should be more carefully cleaned to avoid biasing the classifier with artifacts.…”

“…We estimated the spectral power of the alpha and beta frequencies with an auto-regressive model and used a linear discriminant analysis as a classifier. There are several studies investigating how to optimize the feature processing and the classification algorithms ( Bashashati et al, 2007 , Bashashati et al, 2015 ; Brunner et al, 2011 ; López-Larraz et al, 2018a ; Lotte et al, 2007 ), and therefore, our approach may not be the best available method in terms of classification accuracy. Our motivation for using this design was based on our previous work ( Ramos-Murguialday et al, 2013 ), which proved the BMI rehabilitation efficacy (coupled with physiotherapy) of the contingent association between ipsilesional activity and peripheral feedback during movement attempts in stroke patients.…”

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

“…Complex spatial filters such as common spatial patterns (CSP) need a larger number of EEG electrodes to work properly. As time for BMI training is limited, time should be reserved for neuro-rehabilitation and keep the EEG preparation time and the BMI calibration to a minimum [ 47 ].…”

“…The choice of the classifier can have a significant impact on the BMI performance, although there is evidence suggesting that the features extracted to characterize the brain states to be classified might have a higher relevance than the classifier itself [ 19 ]. In BMI interventions requiring several sessions, adaptation or recalibration of the classifiers can be important to deal with the inherent non-stationarities of the EEG [ 47 ]. Our results showed how an adaptive SVM classifier outperformed the simple linear classifier that was used during the actual intervention with the patients.…”

Brain-machine interfaces for rehabilitation in stroke: A review

“…Two of the main challenges for the establishment of this technology in clinical practice or for neuroprosthetics control, especially with noninvasive recordings, are the session-to-session non-stationarities (i.e., the characteristics of the signals change with time) (López-Larraz et al, 2018;Shiman et al, 2017) and the signal contaminations by artifacts. These artifacts can be generated by the devices controlled with the BMI (e.g., noise generated by actuators based on electric/magnetic neurostimulation, or on robotic devices) (Insausti-Delgado et al, 2017;Walter et al, 2012) or have a physiological origin (e.g., compensatory movements, cranial and neck muscle activity, eye movements, swallowing, etc.)…”