Development of a model to predict psychotherapy response for depression among Veterans.
Development of a model to predict psychotherapy response for depression among Veterans.
复制标题
开发一个模型来预测退伍军人抑郁症的心理治疗反应。
DOI：
10.1017/s0033291722000228
复制
发表时间：
2023-06
影响因子：
6.9
通讯作者：
Kessler, Ronald C.
中科院分区：
文献类型：
--
作者：
Ziobrowski, Hannah N.;Cui, Ruifeng;Ross, Eric L.;Liu, Howard;Puac-Polanco, Victor;Turner, Brett;Leung, Lucinda B.;Bossarte, Robert M.;Bryant, Corey;Pigeon, Wilfred R.;Oslin, David W.;Post, Edward P.;Zaslavsky, Alan M.;Zubizarreta, Jose R.;Nierenberg, Andrew A.;Luedtke, Alex;Kennedy, Chris J.;Kessler, Ronald C.
不到一半的重度抑郁症（MDD）患者对心理治疗有反应。作为以患者为中心的治疗决策支持计划的一部分，预先告知患者其做出反应的可能性可能很有用。这项前瞻性观察性研究调查了 807 名在退伍军人健康管理局开始接受 MDD 心理治疗的全国样本。患者在基线和 3 个月随访时完成了自我报告调查（数据收集于 2018-2020 年）。我们开发了一个机器学习模型，使用 70% 训练样本中的基线调查、管理和地理空间变量来预测 3 个月时的心理治疗反应。然后在 30% 的测试样本中评估模型性能。 32.0%的患者在3个月后对治疗有反应。最佳机器学习模型在测试样本中的 AUC (SE) 为 0.652 (0.038)。在该模型排名最有可能有反应的三分之一患者中，测试样本中有 50.0% 对心理治疗有反应。相比之下，在其余三分之二的患者中，<25% 对心理治疗有反应。该模型选择了 43 个预测变量，其中几乎全部都是自我报告变量。使用基于自我报告数据的预测工具，MDD 患者可以预先获知他们对心理治疗做出反应的可能性。该工具可以有意义地帮助患者和提供者共同决策，尽管需要有关对替代治疗做出反应的可能性的并行信息来为多种治疗的决策提供信息。
Fewer than half of patients with major depressive disorder (MDD) respond to psychotherapy. Pre-emptively informing patients of their likelihood of responding could be useful as part of a patient-centered treatment decision-support plan. This prospective observational study examined a national sample of 807 patients beginning psychotherapy for MDD at the Veterans Health Administration. Patients completed a self-report survey at baseline and 3-months follow-up (data collected 2018-2020). We developed a machine learning model to predict psychotherapy response at 3 months using baseline survey, administrative, and geospatial variables in a 70% training sample. Model performance was then evaluated in the 30% test sample. 32.0% of patients responded to treatment after 3 months. The best machine learning model had an AUC (SE) of 0.652 (0.038) in the test sample. Among the one-third of patients ranked by the model as most likely to respond, 50.0% in the test sample responded to psychotherapy. In comparison, among the remaining two-thirds of patients, <25% responded to psychotherapy. The model selected 43 predictors, of which nearly all were self-report variables. Patients with MDD could pre-emptively be informed of their likelihood of responding to psychotherapy using a prediction tool based on self-report data. This tool could meaningfully help patients and providers in shared decision-making, although parallel information about likelihood of responding to alternative treatments would be needed to inform decision-making across multiple treatments.