Predicting suicide attempts among U.S. Army soldiers after leaving active duty using information available before leaving active duty: results from the Study to Assess Risk and Resilience in Servicemembers-Longitudinal Study (STARRS-LS)

Abstract

Suicide risk is elevated among military service members who recently transitioned to civilian life. Identifying high-risk service members before this transition could facilitate provision of targeted preventive interventions. We investigated the feasibility of doing this by attempting to develop a prediction model for self-reported suicide attempts (SAs) after leaving or being released from active duty in the Study to Assess Risk and Resilience in Servicemembers-Longitudinal Study (STARRS-LS). This study included two self-report panel surveys (LS1: 2016–2018, LS2: 2018–2019) administered to respondents who previously participated while on active duty in one of three Army STARRS 2011–2014 baseline self-report surveys. We focus on respondents who left active duty >12 months before their LS survey (n=8899). An ensemble machine learning model using predictors available prior to leaving active duty was developed in a 70% training sample and validated in a 30% test sample. The 12-month self-reported SA prevalence (SE) was 1.0% (0.1). Test sample AUC (SE) was .74 (.06). The 15% of respondents with highest predicted risk included nearly two-thirds of 12-month SAs and over 80% of medically serious 12-month SAs. These results show that it is possible to identify soldiers at high post-transition self-report SA risk before the transition. Future model development is needed to examine prediction of SAs assessed by administrative data and using surveys administered closer to the time of leaving active duty.

Supporting servicemembers and veterans during their transition to civilian life using certified sponsors: A three-arm randomized controlled trial.

“…This limitation is minimized by the fact that the average time since discharge was 2.80 years and still within the target window of 3 years postmilitary discharge (Elbogen et al, 2022; Shen et al, 2016). Though, many researchers have recently recommended that the optimal time for enrollment of TSMVs into such preventive interventions is prior to military discharge (Chu et al, 2022; Hoffmire et al, 2022; Koh et al, 2022; Stanley et al, 2022; D. S. Vogt et al, 2020).…”

“…Vogt et al, 2021). Rates of psychiatric disorders, such as mood disorders, posttraumatic stress, and personality disorders, also tend to exceed those of their civilian peers (Derefinko et al, 2019; Edwards, Dichiara, et al, 2022), and an early diagnosis of depression similarly tends to predict later poor well-being, homelessness, and suicide attempts throughout the reintegration process (Koh et al, 2022; Stanley et al, 2022; D. Vogt et al, 2021).…”

Exposure to Bullying or Hazing During Deployment and Mental Health Outcomes Among US Army Soldiers

“…STARRS-LS1 participants provided written informed consent, and the study was approved by the human subjects committees of the collaborating institutions. Other information regarding STARRS-LS1 and the study measures is provided in the eMethods in Supplement 1 and a prior publication . This study followed the Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) reporting guideline.…”

“…Weights developed for the NSS and STARRS-LS1 surveys were applied to adjust for nonresponse and for differences between respondents and the population of soldiers they were intended to represent (ie, poststratification weights). Details about the weights are provided elsewhere . Differences between respondents who reported vs denied being bullied or hazed during deployment were evaluated using design-based Wald tests and 2-sided, unpaired t tests for categorical and continuous variables, respectively.…”

Study protocol of an open-label proof-of-concept trial examining the safety and clinical efficacy of psilocybin-assisted therapy for veterans with PTSD

“…In addition, there has been an alarming increase in the incidence of suicides among Veterans, set in the context of limited effective treatment methods for this unique population 12 13. Although the association between PTSD and suicide risk is complex and sometimes related to other factors, such as psychiatric comorbidity and demographic, social and psychological characteristics,14 15 the need to reduce the risk associated with suicidality in this population remains critical. Moreover, evidence suggests a general association between psychedelic administration and reduced suicidality in the general population and in PAT trials,16–18 suggesting this approach could be helpful regardless of the aetiology of suicidality.…”