Classification of left and right-hand motor imagery in acute stroke patients using EEG microstate

Abstract

Background: Stroke is one of the leading causes of adult disability, often resulting in motor dysfunction and brain network reorganization. Brain-computer interface (BCI) systems offer a novel approach to post-stroke motor rehabilitation, with motor imagery (MI) serving as a key paradigm that requires decoding left and right-hand MI differences to optimize system performance. However, the neural dynamics underlying these differences, especially from the perspective of Electroencephalography(EEG) microstate, remain poorly understood in acute stroke patients.

Methods: This study enrolled 14 acute stroke patients and recorded their EEG data during left and right-hand MI tasks. Four EEG microstate (A, B, C, and D) were analyzed to extract temporal feature parameters, including Duration, Occurrence Coverage, and transition probabilities(TP). Significant features were used to construct classification models using Linear Discriminant Analysis(LDA), Support Vector Machines(SVM), and K-Nearest Neighbors(KNN) algorithms.

Results: Microstate analysis revealed significant differences in temporal features of microstate A and C during left and right-hand MI tasks. During left-hand MI, microstate A exhibited longer Duration(P_fdr=0.032), higher Occurrence(P_fdr=0.018), and greater Coverage(P_fdr=0.004) compared to the right-hand, whereas microstate C showed the opposite pattern(P_fdr=0.044, P_fdr=0.004, P_fdr=0.004). Additionally, the TP from microstate B→A, D→A and D→C also demonstrated significant differences(P_fdr=0.04, P_fdr<0.001, P_fdr=0.006). Among classification models, the KNN algorithm achieved the highest accuracy of 75.00%, outperforming LDA and SVM. Fisher analysis indicated that the Occurrence of microstate C was the most discriminative feature for distinguishing between left and right-hand MI tasks in acute stroke patients.

Conclusion: Differences in EEG microstate features during left and right-hand MI tasks in acute stroke patients may reflect lateralized mechanisms of brain network reorganization. Microstate features hold significant potential for both post-stroke brain function assessment and the optimization of BCI systems. These features could enhance adaptive BCI strategies in acute stroke rehabilitation.

Keywords: Acute stroke; Brain network dynamics; Brain-Computer interface; EEG microstate; Motor imagery.

Fig. 1

Experimental flow. (a) MI task paradigm, (b) left-hand MI task, (c) right-hand MI task

Fig. 2

EEG acquisition and processing analysis. (a) electrode channel location, (b) EEG marker during the MI task, “2” indicates the start of MI, (c) EEG preprocessing process, (d) EEG microstate analysis process

Fig. 3

Topography of EEG microstate at left and right-hand MI. “L” represents the left-hand MI, “R” represents the right-hand MI

Fig. 4

EEG microstate GEV, Duration, Occurrence and Coverage at left and right-hand MI. (a) GEV, (b) Duration, (c) Occurrence, (d) Coverage

Fig. 5

TP of EEG microstate at left and right-hand MI. (a) A to others, (b) B to others, (c) C to others, and (d) D to others

Fig. 6

Machine learning classification results. (a) confusion matrix of the LDA model, (b) confusion matrix of the SVM model, (c) confusion matrix of the KNN model, and (d) the ROC curve of the three machine learning models. “L” indicates left-hand MI, “R” indicates right-hand MI

Fig. 7

Feature importance ranking based on Fisher analysis Occurrence-C represents the Occurrence of microstate C, D→A represents the TP from microstate D to A, and so on