ImportanceThe suicide rate of military servicemembers increases sharply after returning to civilian life. Identifying high-risk servicemembers before they leave service could help target preventive interventions.ObjectiveTo develop a model based on administrative data for regular US Army soldiers that can predict suicides 1 to 120 months after leaving active service.Design, Setting, and ParticipantsIn this prognostic study, a consolidated administrative database was created for all regular US Army soldiers who left service from 2010 through 2019. Machine learning models were trained to predict suicides over the next 1 to 120 months in a random 70% training sample. Validation was implemented in the remaining 30%. Data were analyzed from March 2023 through March 2024.Main outcome and measuresThe outcome was suicide in the National Death Index. Predictors came from administrative records available before leaving service on sociodemographics, Army career characteristics, psychopathologic risk factors, indicators of physical health, social networks and supports, and stressors.ResultsOf the 800 579 soldiers in the cohort (84.9% male; median [IQR] age at discharge, 26 [23-33] years), 2084 suicides had occurred as of December 31, 2019 (51.6 per 100 000 person-years). A lasso model assuming consistent slopes over time discriminated as well over all but the shortest risk horizons as more complex stacked generalization ensemble machine learning models. Test sample area under the receiver operating characteristic curve ranged from 0.87 (SE = 0.06) for suicides in the first month after leaving service to 0.72 (SE = 0.003) for suicides over 120 months. The 10% of soldiers with highest predicted risk accounted for between 30.7% (SE = 1.8) and 46.6% (SE = 6.6) of all suicides across horizons. Calibration was for the most part better for the lasso model than the super learner model (both estimated over 120-month horizons.) Net benefit of a model-informed prevention strategy was positive compared with intervene-with-all or intervene-with-none strategies over a range of plausible intervention thresholds. Sociodemographics, Army career characteristics, and psychopathologic risk factors were the most important classes of predictors.Conclusions and relevanceThese results demonstrated that a model based on administrative variables available at the time of leaving active Army service can predict suicides with meaningful accuracy over the subsequent decade. However, final determination of cost-effectiveness would require information beyond the scope of this report about intervention content, costs, and effects over relevant horizons in relation to the monetary value placed on preventing suicides.

中文翻译：

---

预测美国陆军士兵退役后的自杀情况


重要性军人重返平民生活后的自杀率急剧上升。在高危军人退役前识别他们可能有助于有针对性地采取预防性干预措施。目的基于美国陆军正规士兵的行政数据开发一个模型，该模型可以预测退役后 1 至 120 个月的自杀情况。设计、设置和参与者在这项预后研究中，为 2010 年至 2019 年退役的所有美国正规军士兵创建了一个综合行政数据库。机器学习模型经过训练，可以在随机 70% 的训练样本中预测未来 1 到 120 个月的自杀情况。在其余 30% 中实施了验证。数据分析了 2023 年 3 月至 2024 年 3 月。主要结果和措施结果是全国死亡指数中的自杀。预测因子来自退役前可用的社会人口统计学、军队职业特征、精神病理学风险因素、身体健康指标、社交网络和支持以及压力源的行政记录。结果在该队列中的 800 579 名士兵中（84.9% 为男性;退伍时中位 [IQR] 年龄为 26 [23-33] 岁），截至 2019 年 12 月 31 日，已发生 2084 起自杀事件（每 100 000 人年 51.6 起）。一个假设斜率随时间变化一致的套索模型，除了最短的风险范围之外，其他所有风险范围都与更复杂的堆叠泛化集成机器学习模型不同。受试者工作特征曲线下的测试样本面积范围从离职后第一个月的自杀率 0.87 （SE = 0.06） 到 120 个月内自杀率的 0.72 （SE = 0.003）。预测风险最高的 10% 士兵占 30.7% （SE = 1.8） 和 46.6% （SE = 6.6） 跨 Horizons 的所有自杀事件。套索模型的校准在很大程度上优于超级学习器模型（两者都在 120 个月的范围内估计）。在一系列合理的干预阈值上，与全干预或无干预策略相比，模型知情预防策略的净收益是积极的。社会人口统计学、军队职业特征和精神病理学风险因素是最重要的预测因素类别。结论和相关性这些结果表明，基于退伍时可用的管理变量的模型可以有意义地准确地预测随后十年的自杀率。然而，最终确定成本效益需要超出本报告范围的信息，包括干预内容、成本和在相关范围内与预防自杀的货币价值相关的效果。