Evaluating Implementation of Functional Connectivity on Brain Computer Interface to Assist Depression Recovery

Abstract

Brain computer interface (BCI) has experienced exceptional development through past scientific studies. Yet it possesses few practical methods of assisting the treatment of major depressive disorder (MDD) patients or individuals suffering from depression. This paper evaluates the feasibility of BCI-related technology providing assistance for efficient countermeasures for MDD and general depression with the combination of the functional connectivity (FC) concept. Three correlated works are included for evaluation: A six-month BCI-guided training therapy of robotic hand program, an evaluation of BCI integrated systems implemented with noninvasive MDD recovery methods, and a deep learning model of detecting depression with electroencephalography (EEG) signals calculated from FC matrices. The robotic hand therapy indicates the contribution of EEG obtained by BCI for assessing the FC of subjects. The utilization of BCI systems has presented a success in completing the neuromodulation process, especially in repetitive transcranial magnetic stimulation (rTMS) and magnetic seizure therapy (MST) methods. Signal graphs used in FC matrices when detecting depression were established by the combination of different EEG signal bands, demonstrating a possibility of BCI coping with FC in disposing of depression treatment. This study suggests a potential approach for the practical application of BCI technology along with FC as an important assessment criterion when confronting MDD therapies and depression countermeasures. The evaluation results may contribute to further clinical practice and assistance in correlated studies on depression-related disorders.