Dimensional approaches improve prediction of antidepressant outcomes via neuromodulation

Abstract

Repetitive transcranial magnetic stimulation (rTMS) is a non-invasive treatment for depression. However, few studies have explored whether pretreatment functional neuroimaging can be used to predict rTMS-induced changes in depressive symptoms. Using machine learning, we identified that changes in a distinct symptom cluster of core mood and anhedonia, could be predicted more accurately than overall symptom severity.