Predicting Neuroimaging Biomarkers for Antidepressant Selection in Early Treatment of Depression. Issue 2 (26th February 2021)

• Record Type: Journal Article
• Authors: Xue, Li; Pei, Cong; Wang, Xinyi; Wang, Huan; Tian, Shui; Yao, Zhijian; Lu, Qing
• Is Part Of: Journal of magnetic resonance imaging. Volume 54:Issue 2(2021)
• Page Start: 551
• Page End: 559
• Publication Date: 2021-02-26
• Subjects: diffusion tensor imaging -- depression -- fMRI -- biomarker -- ensemble learning -- early response -- antidepressant drug selection; Magnetic resonance imaging -- Periodicals; 616
• DOI: 10.1002/jmri.27577
• Languages: English
• ISSNs: 1053-1807

Abstract

Abstract : Background: Due to the biological heterogeneity, 60%–70% of patients with major depressive disorder (MDD) do not respond to or achieve remission from first‐line antidepressants. Predicting neuroimaging biomarkers for early antidepressant treatment could guide initial antidepressant therapy. Purpose: To assess for neuroimaging biomarkers for antidepressant selection in early antidepressant treatment. Study Type: Prospective. Subjects: A total of 85 MDD patients from the major site and 33 MDD patients from an out‐of‐sample test site. Field Strength/Sequence: A 3.0 T, T1‐weighted imaging using a magnetization‐prepared rapid acquisition gradient‐echo sequence and diffusion tensor imaging (DTI) using an echo‐planar sequence. Assessment: Baseline DTI data of patients who achieved early improvement after 2‐weeks of antidepressant treatment (selective serotonin reuptake inhibitors [SSRI] or serotonin‐norepinephrine reuptake inhibitors [SNRI]) were analyzed. An ensemble model was constructed using data from the major site and then applied to assess the early response of patients at the out‐of‐sample test site. Statistical Tests: Support vector machine combined with leave‐one‐out cross‐validation were applied to construct the whole model from individual base models from different brain regions. Discriminative biomarkers were evaluated by calculating the changes in sensitivity and specificity obtained when removing a single base model from the whole model, the base model being removed changing in each run. Results: Training performance over MDD patients at the major site achieved 75% accuracy while performance with accuracy of 70% was achieved in the out‐of‐sample test site. Assessing sensitivity and specificity changes following the removal of single base models from the prominent model highlighted the functions of two neural circuitries: SSRI‐related emotion regulation circuitry, centered on the hippocampus (sensitivity changes: 10%) and amygdala (sensitivity changes: 11%); and SNRI‐related emotion and reward circuitry, centered on the putamen (specificity changes: 8%) and orbital part of superior frontal gyrus (specificity changes: 12%). Data Conclusion: These findings support future research on clinical antidepressant selection for MDD. Evidence Level: 1 Technical Efficacy: Stage 2