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.