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

The fusion of electroencephalography (EEG) with machine learning is transforming rehabilitation. Our study introduces a neural network model proficient in distinguishing pre- and post-rehabilitation states in patients with Broca's aphasia, based on brain connectivity metrics derived from EEG recordings during verbal and spatial working memory tasks. The Granger causality (GC), phase-locking value (PLV), weighted phase-lag index (wPLI), mutual information (MI), and complex Pearson correlation coefficient (CPCC) across the delta, theta, and low- and high-gamma bands were used (excluding GC, which spanned the entire frequency spectrum). Across eight participants, employing leave-one-out validation for each, we evaluated the intersubject prediction accuracy across all connectivity methods and frequency bands. GC, MI theta, and PLV low-gamma emerged as the top performers, achieving 89.4%, 85.8%, and 82.7% accuracy in classifying verbal working memory task data. Intriguingly, measures designed to eliminate volume conduction exhibited the poorest performance in predicting rehabilitation-induced brain changes. This observation, coupled with variations in model performance across frequency bands, implies that different connectivity measures capture distinct brain processes involved in rehabilitation. The results of this paper contribute to current knowledge by presenting a clear strategy of utilizing limited data to achieve valid and meaningful results of machine learning on post-stroke rehabilitation EEG data, and they show that the differences in classification accuracy likely reflect distinct brain processes underlying rehabilitation after stroke.

The electrophysiological correlates of the working memory subcomponents: evidence from high-density EEG and coherence analysis.

Synchronization between prefrontal (executive) and posterior (association) cortices seems a plausible mechanism for temporary maintenance of information. However, while EEG studies reported involvement of (pre)frontal midline structures in synchronization, functional neuroimaging elucidated the importance of lateral prefrontal cortex (PFC) in working memory (WM). Verbal and spatial WM rely on lateralized subsystems (phonological loop and visuospatial sketchpad, respectively), yet only trends for hemispheric dissociation of networks supporting rehearsal of verbal and spatial information were identified by EEG. As oscillatory activity is WM load dependent, we applied an individually tailored submaximal load for verbal (V) and spatial (S) task to enhance synchronization in the relevant functional networks. To map these networks, we used high-density EEG and coherence analysis. Our results imply that the synchronized activity is limited to highly specialized areas that correspond well with the areas identified by functional neuroimaging. In both V and S task, two independent networks of theta synchronization involving dorsolateral PFC of each hemisphere were revealed. In V task, left prefrontal and left parietal areas were functionally coupled in gamma frequencies. Theta synchronization thus provides the necessary interface for storage and manipulation of information, while left-lateralized gamma synchronization could represent the EEG correlate of the phonological loop.

Beyond aphasia: Altered EEG connectivity in Broca's patients during working memory task.

Broca's region and adjacent cortex presumably take part in working memory (WM) processes. Electrophysiologically, these processes are reflected in synchronized oscillations. We present the first study exploring the effects of a stroke causing Broca's aphasia on these processes and specifically on synchronized functional WM networks. We used high-density EEG and coherence analysis to map WM networks in ten Broca's patients and ten healthy controls during verbal WM task. Our results demonstrate that a stroke resulting in Broca's aphasia also alters two distinct WM networks. These theta and gamma functional networks likely reflect the executive and the phonological processes, respectively. The striking imbalance between task-related theta synchronization and desynchronization in Broca's patients might represent a disrupted balance between task-positive and WM-irrelevant functional networks. There is complete disintegration of left fronto-centroparietal gamma network in Broca's patients, which could reflect the damaged phonological loop.