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

The cumulative strain of 14 years of war on service members, veterans, and their families, together with continuing global threats and the unique stresses of military service, are likely to be felt for years to come. Scientific as well as political factors have influenced how the military has addressed the mental health needs resulting from these wars. Two important differences between mental health care delivered during the Iraq and Afghanistan wars and previous wars are the degree to which research has directly informed care and the consolidated management of services. The U.S. Army Medical Command implemented programmatic changes to ensure delivery of high-quality standardized mental health services, including centralized workload management; consolidation of psychiatry, psychology, psychiatric nursing, and social work services under integrated behavioral health departments; creation of satellite mental health clinics embedded within brigade work areas; incorporation of mental health providers into primary care; routine mental health screening throughout soldiers' careers; standardization of clinical outcome measures; and improved services for family members. This transformation has been accompanied by reduction in psychiatric hospitalizations and improved continuity of care. Challenges remain, however, including continued underutilization of services by those most in need, problems with treatment of substance use disorders, overuse of opioid medications, concerns with the structure of care for chronic postdeployment (including postconcussion) symptoms, and ongoing questions concerning the causes of historically high suicide rates, efficacy of resilience training initiatives, and research priorities. It is critical to ensure that remaining gaps are addressed and that knowledge gained during these wars is retained and further evolved.

Measurement-based care (MBC) in behavioral health involves the repeated collection of patientreported data that is used to track progress, inform care, and engage patients in shared decision making about their treatment. Research suggests that MBC increases the quality and effectiveness of mental health care. However, there can be challenges to implementing MBC, such as time burden, lack of resources to support MBC, and clinician attitudes. The Veterans Health Administration (VHA) is currently undertaking a multiphase MBC roll-out, the first phase of which included 59 sites across the country. The present study examined implementation of this initiative in an effort to learn more about the process of implementation, including best practices, challenges, and innovations. Semistructured interviews were conducted with 20 MBC site champions and 60 staff members from 25 VHA medical centers across the country. Qualitative data analysis was conducted to identify key themes related to MBC implementation. Results were described for 3 components of MBC implementation: preparing for implementation, administering measures, and using and sharing data. Training and staff buy-in were key to the preparation phase. Staff members reported a variety of methods and frequencies for the collection of MBC data, with many staff members identifying a need to streamline the collection process. Staff members reported using data to track progress and adjust treatment with patients. Efforts to use data on a programmatic level were identified as a next step. Innovative solutions across clinics and sites are described in an effort to inform future MBC implementation, both within and outside of VHA.

No abstract