Brain–computer interfaces for neuropsychiatric disorders

Abstract

Neuropsychiatric disorders such as major depression are a leading cause of disability worldwide with standard treatments, including psychotherapy or medication, failing many patients. Deep brain stimulation holds great potential as an alternative therapy for treatment-resistant cases; however, improving the efficacy of stimulation therapy for neuropsychiatric disorders is hindered by the complexity as well as inter-individual and intra-individual variability in symptom manifestations, neural representations and response to therapy. These challenges motivate the development of brain–computer interfaces (BCIs) that can decode the symptom state of a patient from brain activity as feedback to personalize the stimulation therapy in closed loop. Here we review progress on developing BCIs for neuropsychiatric care, focusing on neural biomarkers for decoding symptom states, stimulation site selection and closed-loop stimulation strategies. Moreover, we highlight promising data-driven machine learning and system design approaches and provide a roadmap for realizing these BCIs. Finally, we review current limitations, discuss extensions to other treatment modalities and outline the required scientific and technological advances. These advances can enable next-generation BCIs that provide an alternative therapy for treatment-resistant neuropsychiatric disorders. Stimulation therapy for neuropsychiatric disorders is hindered by the complexity and inter-individual and intra-individual variability in symptom manifestations, neural representations and response to therapy. Brain–computer interfaces could model the brain response to stimulation and decode the symptom state of a patient from brain activity as feedback to personalize the stimulation therapy in closed loop.