AUTHOR=Hou Zhenghua , Li Tong , He Xiaofu , Zhang Yuqun , Chen Huanxin , Jiang Wenhao , Yin Yingying , Yuan Yonggui 

TITLE=Distinct Features of Cerebral Blood Flow and Spontaneous Neural Activity as Integrated Predictors of Early Response to Antidepressants

JOURNAL=Frontiers in Psychiatry

VOLUME=Volume 12 - 2021

YEAR=2022

URL=https://www.frontiersin.org/journals/psychiatry/articles/10.3389/fpsyt.2021.788398

DOI=10.3389/fpsyt.2021.788398

ISSN=1664-0640

ABSTRACT=Objective: The potential relevance of abnormal pretreatment cerebral blood flow (CBF) and amplitude of low-frequency fluctuation (ALFF), and there is no objective predictor that can indicate early antidepressant response in major depressive disorder (MDD). This study aimed to explore whether the predictors based on bimodal pretreatment functional features can discriminate the nonresponders to antidepressants medication at early stage. 
Methods: Forty-four treatment responsive depressed (RD) patients, thirty-six non-responding depressed (NRD) patients and forty-two well-matched healthy controls (HC). The regional CBF and ALFF values were calculated for further group comparisons and differentiating analysis. Correlation analyses were used for exploring the relationship between symptom improvement and the CBF/ALFF, the classification analysis and support vector machine classifier were applied for the discrimination of treatment response.  
Results: Compared with the HC, the RD and NRD groups commonly exhibited lower CBF and ALFF in the right cerebellum posterior lobe. Compared with the NRD group, the RD group showed distinct CBF patterns in the left frontostriatal regions and right frontal-sensorimotor-cerebellum areas, as well as distinct ALFF patterns in the left frontoparietal-striatum and right frontotemporal-sensorimotor-striatal-cerebellum regions. The further discriminate analyses revealed optimal differential power between the RD and NRD groups based on the combined imaging indexes (CBF & ALFF) using the ROC and 10-folds cross-validation support vector machine classifier. 
Conclusion: Distinct features of the CBF and ALFF in the frontal-striatal network might serve as a promising neuroimaging predictor for identifying depressed patients with blunted treatment responsiveness, which may facilitate the personalized antidepressants therapy.