Sampson Laura, Jiang Tammy, Gradus Jaimie L, Cabral Howard J, Rosellini Anthony J, Calabrese Joseph R, Cohen Gregory H, Fink David S, King Anthony P, Liberzon Israel, Galea Sandro
Psychiatr Res Clin Pract. 2021 Fall;3(3):115-122. doi: 10.1176/appi.prcp.20200031. Epub 2021 Feb 12.
Depression is one of the most common mental disorders in the United States in both civilian and military populations, but few prospective studies assess a wide range of predictors across multiple domains for new-onset (incident) depression in adulthood. Supervised machine learning methods can identify predictors of incident depression out of many different candidate variables, without some of the assumptions and constraints that underlie traditional regression analyses. The objectives of this study were to identify predictors of incident depression across 5 years of follow-up using machine learning, and to assess prediction accuracy of the algorithms.
Data were from a cohort of Army National Guard members free of history of depression at baseline ( = 1951 men and 298 women), interviewed once per year for probable depression. Classification trees and random forests were constructed and cross-validated, using 84 candidate predictors from the baseline interviews.
Stressors and traumas such as emotional mistreatment and adverse childhood experiences, demographics such as being a parent or student, and military characteristics including paygrade and deployment location were predictive of probable depression. Cross-validated random forest algorithms were moderately accurate (68% for women and 73% for men).
Events and characteristics throughout the life course, both in and outside of deployment, predict incident depression in adulthood among military personnel. Although replication studies are needed, these results may help inform potential intervention targets to reduce depression incidence among military personnel. Future research should further refine and explore interactions between identified variables.
抑郁症是美国平民和军人中最常见的精神障碍之一，但很少有前瞻性研究评估成年期新发（ incident ）抑郁症在多个领域的广泛预测因素。监督式机器学习方法可以从许多不同的候选变量中识别出抑郁症发病的预测因素，而无需传统回归分析所依据的一些假设和限制。本研究的目的是使用机器学习确定5年随访期间抑郁症发病的预测因素，并评估算法的预测准确性。
数据来自一组基线时无抑郁症病史的陆军国民警卫队成员（1951名男性和298名女性），每年进行一次关于可能患抑郁症的访谈。使用基线访谈中的84个候选预测因素构建并交叉验证分类树和随机森林。
诸如情感虐待和不良童年经历等应激源和创伤、作为父母或学生等人口统计学特征以及包括薪资等级和部署地点在内的军事特征可预测可能患抑郁症。交叉验证的随机森林算法具有中等准确性（女性为68%，男性为73%）。
整个生命历程中的事件和特征，无论在部署期间还是之外，都可预测成年军人的抑郁症发病情况。尽管需要重复研究，但这些结果可能有助于为潜在的干预目标提供信息，以降低军人中的抑郁症发病率。未来的研究应进一步完善并探索已识别变量之间的相互作用。
