RESTORING EMOTIONAL STABILITY THROUGH NEUROFEEDBACK AND AI FOR TRANSFORMATIVE EMPOWERMENT (RESONATE)

Emotion regulation is a core transdiagnostic mechanism underlying mental well-being. Dysfunctions within the brain networks supporting emotion regulation are central to the development of psychiatric disorders, which collectively impose an economic burden exceeding €600 billion annually in Europe. This study focuses on Major Depressive Disorder (MDD), projected to become the leading cause of disability worldwide by 2030. Despite its high prevalence, conventional treatments remain ineffective for approximately 40–60% of patients, underscoring the urgent need for innovative and mechanistically informed interventions.

Neurofeedback (NF) training using functional magnetic resonance imaging has shown promising results in enhancing self-regulation of emotion-related brain circuits; however, its high cost and limited accessibility limit its clinical applicability. To bridge the gap between experimental research and clinical practice, we investigate the efficacy of electroencephalography (EEG)-based neurofeedback using Standardized Weighted Low Resolution Electromagnetic Tomography (swLORETA) targeting emotion regulation circuits, advancing beyond the current state of the art.

We conducted a randomized, placebo-controlled study with 72 patients with MDD assigned to EEG-NF, sham-NF, or control conditions. In this conference, we will present preliminary clinical and neurophysiological results from 44 patients. In parallel, we explore advanced deep learning approaches for EEG time-series analysis to characterize neural dynamics associated with successful training and to evaluate their potential for predicting individual neurofeedback responsiveness—one of the major challenges in the field.

The aims of this work are to: (1) assess the clinical efficacy of EEG-based neurofeedback in MDD; (2) identify neurophysiological mechanisms underlying successful emotion regulation training.