Tong Xiaoyu, Zhao Kanhao, Fonzo Gregory A, Xie Hua, Carlisle Nancy B, Keller Corey J, Oathes Desmond J, Sheline Yvette, Nemeroff Charles B, Trivedi Madhukar, Etkin Amit, Zhang Yu
Department of Bioengineering, Lehigh University, Bethlehem, PA, USA.
Center for Psychedelic Research and Therapy, Department of Psychiatry and Behavioral Sciences, Dell Medical School, The University of Texas at Austin, Austin, TX, USA.
medRxiv. 2024 Oct 8:2024.04.11.24305583. doi: 10.1101/2024.04.11.24305583.
Major depressive disorder (MDD) is a common and often severe condition that profoundly diminishes quality of life for individuals across ages and demographic groups. Unfortunately, current antidepressant and psychotherapeutic treatments exhibit limited efficacy and unsatisfactory response rates in a substantial number of patients. The development of effective therapies for MDD is hindered by the insufficiently understood heterogeneity within the disorder and its elusive underlying mechanisms. To address these challenges, we present a target-oriented multimodal fusion framework that robustly predicts antidepressant response by integrating structural and functional connectivity data (sertraline: R = 0.31; placebo: R = 0.22). Remarkably, the sertraline response biomarker is further tested on an independent escitalopram-medicated cohort of MDD patients, validating its generalizability (p = 0.01) and suggesting an overlap of psychopharmacological mechanisms across selective serotonin reuptake inhibitors. Through the model, we identify multimodal neuroimaging biomarkers of antidepressant response and observe that sertraline and placebo show distinct predictive patterns. We further decompose the overall predictive patterns into constitutive with generalizable structural-functional co-variation, which exhibit treatment-specific association with personality traits and behavioral/cognitive task performance. Our innovative and interpretable multimodal framework provides novel and reliable insights into the intricate neuropsychopharmacology of antidepressant treatment, paving the way for advances in precision medicine and development of more targeted antidepressant therapeutics.
重度抑郁症（MDD）是一种常见且往往较为严重的疾病，它会严重降低各个年龄段和人口群体的个体生活质量。不幸的是，目前的抗抑郁药物和心理治疗方法在大量患者中疗效有限，反应率不尽人意。MDD有效治疗方法的开发受到该疾病中尚未充分理解的异质性及其难以捉摸的潜在机制的阻碍。为应对这些挑战，我们提出了一个以目标为导向的多模态融合框架，该框架通过整合结构和功能连接数据来稳健地预测抗抑郁反应（舍曲林：R = 0.31；安慰剂：R = 0.22）。值得注意的是，舍曲林反应生物标志物在一组独立的接受艾司西酞普兰治疗的MDD患者队列中进一步得到验证，证实了其可推广性（p = 0.01），并表明选择性5-羟色胺再摄取抑制剂之间存在心理药理学机制的重叠。通过该模型，我们识别出抗抑郁反应的多模态神经影像学生物标志物，并观察到舍曲林和安慰剂显示出不同的预测模式。我们进一步将整体预测模式分解为具有可推广的结构-功能共变的组成部分，这些部分与人格特质以及行为/认知任务表现呈现出特定于治疗的关联。我们创新且可解释的多模态框架为抗抑郁治疗复杂神经心理药理学提供了新颖且可靠的见解，为精准医学的进步以及更具针对性的抗抑郁治疗药物的开发铺平了道路。
