Learning Individualized Treatment Rules for Multiple-Domain Latent Outcomes

For many mental disorders, latent mental status from multiple-domain psychological or clinical symptoms may perform as a better characterization of the underlying disorder status than a simple summary score of the symptoms, and they may also serve as more reliable and representative features to differentiate treatment responses. Therefore, to address the complexity and heterogeneity of treatment responses for mental disorders, we provide a new paradigm for learning optimal individualized treatment rules (ITRs) by modeling patients’ latent mental status. We first learn the multi-domain latent states at baseline from the observed symptoms under a restricted Boltzmann machine (RBM) model, which encodes patients’ heterogeneous symptoms using an economical number of latent variables and yet remains flexible. We then optimize a value function defined by the latent states after treatment by exploiting a transformation of the observed symptoms based on the RBM without modeling the relationship between the latent mental states before and after treatment. The optimal treatment rules are derived using a weighted large margin classifier. We derive the convergence rate of the proposed estimator under the latent models. Simulation studies are conducted to test the performance of the proposed method. Finally, we apply the developed method to real world studies and we demonstrate the utility and advantage of our method in tailoring treatments for patients with major depression, and identify patient subgroups informative for treatment recommendations. Supplementary materials for this article are available online.

针对诸多精神障碍而言，基于多领域心理或临床症状所提取的潜在精神状态，相较于单纯的症状汇总评分，能更精准地表征疾病的内在状态；同时，这类潜在状态也可作为更可靠且具代表性的特征，用于区分不同的治疗响应情况。因此，为解决精神障碍治疗响应的复杂性与异质性问题，本研究提出一种全新范式：通过对患者的潜在精神状态进行建模，学习最优个体化治疗规则（ITR）。本研究首先基于受限玻尔兹曼机（Restricted Boltzmann Machine, RBM）模型，从基线阶段的观测症状中提取多领域潜在状态；该模型以精简的潜在变量集合对患者的异质性症状进行编码，同时保持良好的灵活性。随后，本研究无需对治疗前后的潜在精神状态间的关联进行建模，仅利用基于RBM得到的观测症状变换结果，对由治疗后潜在状态所定义的价值函数进行优化。最终通过加权大间隔分类器推导得到最优治疗规则。本研究推导了该估计量在潜在模型下的收敛速率，并通过仿真实验验证了所提方法的性能表现。最后，本研究将所提方法应用于真实世界研究，验证了其在为重度抑郁症患者定制治疗方案中的实用性与优势，并识别出可用于指导治疗推荐的患者亚组。本文的补充材料可在线获取。