Evaluation of Post-Stroke Impairment in Fine Tactile Sensation by Electroencephalography (EEG)-Based Machine Learning

Abstract

Electroencephalography (EEG)-based measurements of fine tactile sensation produce large amounts of data, with high costs for manual evaluation. In this study, an EEG-based machine-learning (ML) model with support vector machine (SVM) was established to automatically evaluate post-stroke impairments in fine tactile sensation. Stroke survivors (n = 12, stroke group) and unimpaired participants (n = 15, control group) received stimulations with cotton, nylon, and wool fabrics to the different upper limbs of a stroke participant and the dominant side of the control. The average and maximal values of relative spectral power (RSP) of EEG in the stimulations were used as the inputs to the SVM-ML model, which was first optimized for classification accuracies for different limb sides through hyperparameter selection (γ, C) in radial basis function (RBF) kernel and cross-validation during cotton stimulation. Model generalization was investigated by comparing accuracies during stimulations with different fabrics to different limbs. The highest accuracies were achieved with (γ = 21, C = 23) for the RBF kernel (76.8%) and six-fold cross-validation (75.4%), respectively, in the gamma band for cotton stimulation; these were selected as optimal parameters for the SVM-ML model. In model generalization, significant differences in the post-stroke fabric stimulation accuracies were shifted to higher (beta/gamma) bands. The EEG-based SVM-ML model generated results similar to manual evaluation of cortical responses to fabric stimulations; this may aid automatic assessments of post-stroke fine tactile sensations.

Personalized robots for long-term telerehabilitation after stroke: a perspective on technological readiness and clinical translation

“…Beyond leveraging state-of-the-art technology to lessen the need for professional intervention via remote monitoring, the technological preparedness of post-stroke personalized rehabilitation robots should also focus on the provision of tailored adaption and autonomous theranostics, congruent with the patient's unique requirements. Technological readiness should prioritize enhancing robot autonomy through cutting-edge artificial intelligence (AI) technology, which can learn from individual patient data, e.g., EMG ( 41 ), EEG ( 42 ), electrical impedance myography ( 43 ), etc., enabling the adaptation of more personalized telerehabilitation and offering automatic theranostics over long-term service. It presents an economical and timely method for bridging the gap between professionals and patients for diagnosis, treatment, and follow-up, which is unconstrained by geographical limitations.…”

Automatic theranostics for long-term neurorehabilitation after stroke

“…It has been proven that compared to the readings of human professionals, ML-based models could significantly reduce the evaluation time required to determine symptom onset related to stroke (Chae et al, 2020 ). In addition, the output predictions of the trained models with ML algorithms, such as random forest, support vector machine (SVM), and convolutional neural network (CNN), have been observed to correlate with clinical scores (Moghadam et al, 2022 ; Sung et al, 2022 ; Zhang et al, 2022 ). There were significant correlations between the outputs of the ML-based models and the manual results by human professionals, which has increased the readability of performance of the ML-based models (Ye et al, 2021 ).…”

Integrating EEG and Machine Learning to Analyze Brain Changes during the Rehabilitation of Broca’s Aphasia

“…Several reviews and meta-analyses have shown that EEG has good predictive value for several functions that can be impaired after stroke, from motor function to speech and cognition. Machine learning is increasingly being applied in the field of stroke rehabilitation, particularly as a tool to personalize therapy and monitor progress [ 16 , 17 , 18 , 19 ]. This is especially relevant given the wide variability in stroke symptoms and recovery trajectories.…”