Investigating the predictive models of efficacy of accelerated neuronavigation-guided rTMS for suicidal depression based on multimodal large-scale brain networks.

Background: Accelerated neuronavigation-guided high-dose repetitive transcranial magnetic stimulation (NH-rTMS) can rapidly reduce suicidal ideation and alleviate depressive symptoms in one week. Exploring accelerated NH-rTMS-related biomarkers will enhance the precision of treatment decisions for patients with major depressive disorder (MDD). This study aimed to establish predictive models of treatment response to accelerated NH-rTMS in MDD based on multimodal large-scale brain networks. Method: In this study, morphological, structural, and functional brain networks were constructed for untreated MDD patients with suicidal ideation before accelerated NH-rTMS treatment. Linear support vector regression methods were utilized to examine the ability of multimodal brain networks in predicting antidepressant and anti-suicidal effects of accelerated NH-rTMS. Results: We found that both the morphological and structural networks predicted the percentage changes of total Beck Scale of Suicidal Ideation and 24-item Hamilton Depression Rating Scale (HAMD-24) scores. Additionally, the functional networks predicted the percentage changes of total HAMD-24 scores. Further analyses revealed that the structural networks outperformed the morphological and functional networks and the somatomotor module outperformed other subnetworks in the prediction. Conclusions: In summary, our study provides brain connectome-based predictive models of treatment response to accelerated NH-rTMS in MDD patients with suicidal ideation.