Traditional assessment instruments for post-stroke aphasia are typically extensive and asynchronous, providing results only after full administration. This delay limits their suitability for continuous clinical monitoring and real-time adaptive therapeutic adjustments. Objective: This study evaluates the feasibility of a low-cost, low-density EEG-based framework designed for the continuous estimation of working memory capacity as a key functional biomarker of rehabilitation progress. Methods: Electroencephalography (EEG) data were acquired from aphasic and control participants using a portable OpenBCI platform and a customized 3D-printed helmet of an n-back paradigm. Event-related potential (ERP) features, including P100, N100, P200, N200, and P300, were extracted to train linear (OLS) and a non-linear Support Vector Regression (SVR) model with a radial basis function (RBF) kernel against a composite ground-truth index (W). Results: Non-linear SVR models demonstrated superior performance and scalability compared to linear approaches. For groupings of 32 epochs, a statistically significant improvement was identified (p=0.04), with non-linear models showing a reduction in RMSE up to six times greater than linear models as effective training samples increased. Conclusion: These findings provide a proof-of-concept for a deployable, technology-assisted system capable of supporting individualized and adaptive cognitive monitoring in clinical post-stroke rehabilitation settings.

Aphasia is a neurological condition that manifests itself through deficiencies in linguistic functions, which are essential for social interaction and activities of daily living. This deficiency is associated with a loss of working memory capacity, which is responsible for the temporary storage of information. This work sought to develop an approach to aid professionals involved in aphasia treatment and rehabilitation programs, aiming to improve the manner in which evidences of rehabilitation are obtained. The methodology is based on an electroencephalography device, which captures brain signals from individuals while they execute a task that stimulates verbal working memory. The signals are processed using an approach based on event-related potentials, which are then used as input to a statistical model trained with a scientifically validated measurement of working memory. The results indicated that the error of the model was slightly larger than expected, but diminished proportionally to the amount of training samples. We conclude the study suggesting research paths to reduce the error of the model and investigate the feasibility of this approach in a clinical context.