Predicting RTMS Treatment Effects Using Open-Loop Control and Neural Manifold

Hongyu Shi, Kaizhong Zheng, Huaning Wang, Baojuan Li, Badong Chen

Abstract: Repetitive transcranial magnetic stimulation (rTMS) is a common non-invasive treatment for medication-resistant major depressive disorder (MDD). It utilizes continuous and adjustable magnetic stimulation to modulate neural circuits implicated in the pathogenesis of depression. Nevertheless, constructing a universal and effective predictive factor for forecasting treatment outcomes remains challenging. To address this, we first collect neuroimaging data and five depression scales from 26 medication-resistant MDD patients before and after rTMS treatment. Then we propose a novel framework for predicting treatment effects precisely, which combines open-loop control and neural manifold estimation. This framework utilizes the geometric information of the manifold as a biomarker to predict the therapeutic efficacy of rTMS. Experiments based on the clinical dataset demonstrate the effectiveness and robustness of our framework.