A practical risk calculator for suicidal behavior among transitioning U.S. Army soldiers: results from the Study to Assess Risk and Resilience in Servicemembers-Longitudinal Study (STARRS-LS)

Abstract

Background Risk of suicide-related behaviors is elevated among military personnel transitioning to civilian life. An earlier report showed that high-risk U.S. Army soldiers could be identified shortly before this transition with a machine learning model that included predictors from administrative systems, self-report surveys, and geospatial data. Based on this result, a Veterans Affairs and Army initiative was launched to evaluate a suicide-prevention intervention for high-risk transitioning soldiers. To make targeting practical, though, a streamlined model and risk calculator were needed that used only a short series of self-report survey questions. Methods We revised the original model in a sample of n = 8335 observations from the Study to Assess Risk and Resilience in Servicemembers-Longitudinal Study (STARRS-LS) who participated in one of three Army STARRS 2011–2014 baseline surveys while in service and in one or more subsequent panel surveys (LS1: 2016–2018, LS2: 2018–2019) after leaving service. We trained ensemble machine learning models with constrained numbers of item-level survey predictors in a 70% training sample. The outcome was self-reported post-transition suicide attempts (SA). The models were validated in the 30% test sample. Results Twelve-month post-transition SA prevalence was 1.0% (s.e. = 0.1). The best constrained model, with only 17 predictors, had a test sample ROC-AUC of 0.85 (s.e. = 0.03). The 10–30% of respondents with the highest predicted risk included 44.9–92.5% of 12-month SAs. Conclusions An accurate SA risk calculator based on a short self-report survey can target transitioning soldiers shortly before leaving service for intervention to prevent post-transition SA.

"This Is a Solvable Problem": Proceedings from a Roundtable on Providing Support to Veterans in the Transition from Military Service to Civilian Life

“…Another participant noted high rates of suicide attempts in the five years following separation. Indeed, research indicates that suicide risk is 2.5 times higher for veterans in the first year following separation relative to those who are still in the military, and a study on U.S. Army veterans found that 1 percent of veterans attempt suicide in the first year post-discharge (Geraci et al, undated;Kearns et al, 2023;Shen, Cunha, and Williams, 2016). Although risk decreases over time, one study identified that suicide risk remained high even six years after separation (Shen, Cunha, and Williams, 2016).…”

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

“…It is likely that attending the required and universal DoD Transition Assistance Program (U.S. Department of Defense, 2022) might be sufficient to assist many low-risk TSMVs in their transition to civilian life. However, TSMVs identified as high-risk by a practical risk calculator for suicidal behavior, based on the STARRS-LS model (Kearns et al, 2023), would most likely benefit from individualized and intensive interventions that consisted of community programs, a certified sponsor, and streamlined access to VA healthcare, including case management, primary care, and suicide-safety planning group treatment (Geraci, Borah, et al, 2023;Goodman et al, 2021).…”

External Validation and Updating of a Statistical Civilian-Based Suicide Risk Model in US Naval Primary Care

“…[13][14][15][16] All service members have been shown to have lower risk when they are focused on a clear mission such as during deployment, yet they experience a higher risk during the postdeployment adjustment period, and this risk increase continues into retirement. [17][18][19] US service members have contact with primary care practitioners in the month before suicide more than half the time. [20][21][22] Primary care practitioners seek tools to aid in identifying at-risk patients whom they otherwise may miss.…”

“…To better understand factors that might increase suicide risk in the military, numerous studies have analyzed protective and risk factors for service members . All service members have been shown to have lower risk when they are focused on a clear mission such as during deployment, yet they experience a higher risk during the postdeployment adjustment period, and this risk increase continues into retirement …”

“… 13 , 14 , 15 , 16 All service members have been shown to have lower risk when they are focused on a clear mission such as during deployment, yet they experience a higher risk during the postdeployment adjustment period, and this risk increase continues into retirement. 17 , 18 , 19 …”