Center for Anxiety and Related Disorders, Boston University, Boston, Massachusetts.
Departments of Psychiatry and Family Medicine and Public Health, University of California San Diego, La Jolla, California.
Depress Anxiety. 2018 Nov;35(11):1073-1080. doi: 10.1002/da.22807. Epub 2018 Aug 13.
Preventing suicides, mental disorders, and noncombat-related interpersonal violence during deployment are priorities of the US Army. We used predeployment survey and administrative data to develop actuarial models to identify soldiers at high risk of these outcomes during combat deployment.
The models were developed in the Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS) Pre-Post Deployment Study, a panel study of soldiers deployed to Afghanistan in 2012-2013. Soldiers completed self-administered questionnaires before deployment and one (T1), three (T2), and nine months (T3) after deployment, and consented to administrative data linkage. Seven during-deployment outcomes were operationalized using the postdeployment surveys. Two overlapping samples were used because some outcomes were assessed at T1 (n = 7,048) and others at T2-T3 (n = 7,081). Ensemble machine learning was used to develop a model for each outcome from 273 predeployment predictors, which were compared to simple logistic regression models.
The relative improvement in area under the receiver operating characteristic curve (AUC) obtained by machine learning compared to the logistic models ranged from 1.11 (major depression) to 1.83 (suicidality).The best-performing machine learning models were for major depression (AUC = 0.88), suicidality (0.86), and generalized anxiety disorder (0.85). Roughly 40% of these outcomes occurred among the 5% of soldiers with highest predicted risk.
Actuarial models could be used to identify high risk soldiers either for exclusion from deployment or preventive interventions. However, the ultimate value of this approach depends on the associated costs, competing risks (e.g. stigma), and the effectiveness to-be-determined interventions.
预防自杀、精神障碍和非战斗相关人际暴力是美国陆军的优先事项。我们使用部署前调查和行政数据来开发精算模型，以确定在战斗部署期间这些结果风险较高的士兵。
该模型是在陆军士兵风险和韧性评估研究（Army STARRS）部署前-后研究中开发的，这是一项对 2012-2013 年部署到阿富汗的士兵进行的面板研究。士兵在部署前完成了自我管理问卷，在部署后一个（T1）、三个（T2）和九个月（T3）完成了调查，并同意进行行政数据链接。使用部署后的调查来确定七个部署期间的结果。由于某些结果在 T1 进行评估（n=7048），而其他结果在 T2-T3 进行评估（n=7081），因此使用了两个重叠的样本。使用集成机器学习为每个结果从 273 个部署前预测因素中开发一个模型，并与简单的逻辑回归模型进行比较。
机器学习与逻辑模型相比，获得的接收者操作特征曲线下面积（AUC）的相对改善范围从 1.11（重度抑郁症）到 1.83（自杀倾向）。表现最好的机器学习模型是用于重度抑郁症（AUC=0.88）、自杀倾向（0.86）和广泛性焦虑症（0.85）。这些结果中的大约 40%发生在预测风险最高的 5%的士兵中。
精算模型可用于识别高风险士兵，要么将其排除在部署之外，要么进行预防性干预。然而，这种方法的最终价值取决于相关成本、竞争风险（例如耻辱感）以及有待确定的干预措施的有效性。
