The 2013 U.S. Veterans Administration/Department of Defense Clinical Practice Guidelines (VA/DoD CPG) require comprehensive suicide risk assessments for VA/DoD patients with mental disorders but provide minimal guidance on how to carry out these assessments. Given that clinician-based assessments are known not to be strong predictors of suicide, we investigated whether a precision medicine model using administrative data after outpatient mental health specialty visits could be developed to predict suicides among outpatients. We focused on male non-deployed Regular U.S. Army soldiers because they account for the vast majority of such suicides. Four machine learning classifiers (naïve Bayes, random forests, support vector regression, elastic net penalized regression) were explored. 41.5% of Army suicides in 2004-2009 occurred among the 12.0% of soldiers seen as outpatient by mental health specialists, with risk especially high within 26 weeks of visits. An elastic net classifier with 10-14 predictors optimized sensitivity (45.6% of suicide deaths occurring after the 15% of visits with highest predicted risk). Good model stability was found for a model using 2004-2007 data to predict 2008-2009 suicides, although stability decreased in a model using 2008-2009 data to predict 2010-2012 suicides. The 5% of visits with highest risk included only 0.1% of soldiers (1047.1 suicides/100,000 person-years in the 5 weeks after the visit). This is a high enough concentration of risk to have implications for targeting preventive interventions. An even better model might be developed in the future by including the enriched information on clinician-evaluated suicide risk mandated by the VA/DoD CPG to be recorded.

No abstract

Background Previous studies have documented the impact of domain-specific leadership behaviors on targeted health outcomes in employees. The goal of the present study was to determine the association between specific leadership behaviors addressing COVID-19 and US soldiers’ mental health and adherence to COVID-19 public health guidelines. Methods An electronic, anonymous survey was administered to US Army soldiers across three major commands (N = 7,829) from December 2020 to January 2021. The primary predictor of interest was soldiers’ ratings of their immediate supervisors’ behaviors related to COVID-19. The outcomes were soldiers’ mental health (i.e., depression and generalized anxiety) and adherence to COVID-19 public health guidelines. Covariates were rank, gender, ratings of immediate supervisors’ general leadership, level of COVID-19 concerns, and COVID-19 status (e.g., tested positive, became seriously ill). Logistic regressions were used to model the unique association of COVID-19 leadership behaviors with outcomes after adjusting for covariates. Results High levels of COVID-19 leadership behaviors were associated with lesser likelihood of soldiers’ screening positive for depression (AOR = 0.46; 95% CI [0.39, 0.54]) and anxiety (AOR = 0.54; 95% CI [0.45, 0.64]), and greater likelihood of frequent adherence to preventive health guidelines (AORs = 1.58; 95% CI [1.39, 1.80] to 2.50; 95% CI [2.01, 3.11]). Conclusion Higher levels of COVID-19 leadership behaviors may support soldiers’ mental health and encourage their adherence to COVID-19 public health guidelines. Given the link between these leader behaviors and soldier adaptation to the pandemic over and above general leadership, training for supervisors should focus on targeting specific health-promoting behaviors. Results can inform leader training for the military and other high-risk occupations.

Trends in rates of combat deaths and accident deaths declined although rates of suicides increased. The Army suicide rate increased in comparison to the United States. 70% of accident deaths were transportation related. Almost 70% of suicides and homicides were firearm related.

No abstract