A test of the interpersonal theory of suicide in a large, representative, retrospective and prospective study: Results from the Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS)

Heterogeneity in suicide risk: Evidence from personalized dynamic models

Most theories of suicide propose within-person changes in psychological states cause suicidal thoughts/behaviors; however, most studies use between-person analyses. Thus, there are little empirical data exploring current theories in the way they are hypothesized to occur. We used a form of statistical modeling called group iterative multiple model estimation (GIMME) to explore one theory of suicide: The Interpersonal Theory of Suicide (IPTS). GIMME estimates personalized statistical models for each individual and associations shared across individuals. Data were from a real-time monitoring study of individuals with a history of suicidal thoughts/behavior (adult sample: participants = 111, observations = 25,242; adolescent sample: participants = 145, observations = 26,182). Across both samples, none of theorized IPTS effects (i.e., contemporaneous effect from hopeless to suicidal thinking) were shared at the group level. There was significant heterogeneity in the personalized models, suggesting there are different pathways through which different people come to experience suicidal thoughts/behaviors. These findings highlight the complexity of suicide risk and the need for more personalized approaches to assessment and prediction.

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)

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.

Transition to a first suicide attempt among young and middle-aged males with a history of suicidal thoughts: A two-year cohort study

INTRODUCTION

Although many studies have examined the risk and protective factors associated with suicidal behavior, little is known about the probability of transition from suicidal thoughts to suicidal attempts and the factors that distinguish those who have suicidal thoughts from those who progress to a suicide attempt.

OBJECTIVES

To determine the probability and predictors of transition to a suicide attempt among young and middle-aged males with a history of suicidal thoughts but no prior history of attempting suicide.

METHODS

We used data from the first two waves of the Australian Longitudinal Study on Male Health, approximately two years apart. We followed the cohort of males aged 18-55 years who, at wave 1, reported a lifetime history of suicidal ideation but no history of a prior suicide attempt. We report transition probabilities to a first suicide attempt at Wave 2 and used logistic regression models to examine baseline predictors of transition to a first suicide attempt over the two-year period among males aged 18 years and older.

RESULTS

From the 1,564 males with suicidal thoughts at wave 1,140 participants (8.9%; 95% CI:7.6,10.5) reported to have had their first suicide attempt in the two-year period. In multivariate analyses, males aged 30-39 (OR=0.31; 95% CI: 0.16,0.60), 40-49 (OR=0.47; 95% CI:0.24,0.91) and 50-55 (OR=0.31; 95% CI: 0.13,0.73) all had lower odds of a first suicide attempt compared to males aged 18-29 years. The odds of a first suicide attempt were significantly higher for males who were: living in inner regional areas (ref: major cities) (OR=2.32; 95% CI: 1.33,4.04); homosexual or bisexual (OR=2.51; 95% CI: 1.17,5.36); working night shift as their main job (OR=1.75; 95% CI: 1.05,2.91); and, living with a disability (OR=1.99; 95% CI: 1.07,3.65). Clinical indicators such as symptoms of depression and illicit substance use were not significant predictors of transition to a first suicide attempt in multivariate models, nor were indicators of social connection.

CONCLUSION

We estimated that 8.9% of Australian males aged 15-55 years with a history of suicidal thoughts and no prior history of suicide attempts will progress to a first suicide attempt within two-years. Neither psychological distress, illicit substance use nor social connection indicators were correlated with transition to a first suicide attempt. Rather, it was socio-demographic indicators that were associated with transition to a first suicide attempt.

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)

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 0.74 (0.06). 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.