Predicting Suicides Among US Army Soldiers After Leaving Active Service.

Importance: The suicide rate of military servicemembers increases sharply after returning to civilian life. Identifying high-risk servicemembers before they leave service could help target preventive interventions. Objective: To develop a model based on administrative data for regular US Army soldiers that can predict suicides 1 to 120 months after leaving active service. Design, Setting, and Participants: In this prognostic study, a consolidated administrative database was created for all regular US Army soldiers who left service from 2010 through 2019. Machine learning models were trained to predict suicides over the next 1 to 120 months in a random 70% training sample. Validation was implemented in the remaining 30%. Data were analyzed from March 2023 through March 2024. Main outcome and measures: The outcome was suicide in the National Death Index. Predictors came from administrative records available before leaving service on sociodemographics, Army career characteristics, psychopathologic risk factors, indicators of physical health, social networks and supports, and stressors. Results: Of the 800 579 soldiers in the cohort (84.9% male; median [IQR] age at discharge, 26 [23-33] years), 2084 suicides had occurred as of December 31, 2019 (51.6 per 100 000 person-years). A lasso model assuming consistent slopes over time discriminated as well over all but the shortest risk horizons as more complex stacked generalization ensemble machine learning models. Test sample area under the receiver operating characteristic curve ranged from 0.87 (SE = 0.06) for suicides in the first month after leaving service to 0.72 (SE = 0.003) for suicides over 120 months. The 10% of soldiers with highest predicted risk accounted for between 30.7% (SE = 1.8) and 46.6% (SE = 6.6) of all suicides across horizons. Calibration was for the most part better for the lasso model than the super learner model (both estimated over 120-month horizons.) Net benefit of a model-informed prevention strategy was positive compared with intervene-with-all or intervene-with-none strategies over a range of plausible intervention thresholds. Sociodemographics, Army career characteristics, and psychopathologic risk factors were the most important classes of predictors. Conclusions and relevance: These results demonstrated that a model based on administrative variables available at the time of leaving active Army service can predict suicides with meaningful accuracy over the subsequent decade. However, final determination of cost-effectiveness would require information beyond the scope of this report about intervention content, costs, and effects over relevant horizons in relation to the monetary value placed on preventing suicides.

Partnership building for scale-up in the Veteran Sponsorship Initiative: Strategies for harnessing collaboration to accelerate impact in suicide prevention.

OBJECTIVE: To evaluate the implementation and trust-building strategies associated with successful partnership formation in scale-up of the Veteran Sponsorship Initiative (VSI), an evidence-based suicide prevention intervention enhancing connection to U.S. Department of Veterans Affairs (VA) and other resources during the military-to-civilian transition period. DATA SOURCES AND STUDY SETTING: Scaling VSI nationally required establishing partnerships across VA, the U.S. Department of Defense (DoD), and diverse public and private Veteran-serving organizations. We assessed partnerships formalized with a signed memorandum during pre- and early implementation periods (October 2020-October 2022). To capture implementation activities, we conducted 39 periodic reflections with implementation team members over the same period. STUDY DESIGN: We conducted a qualitative case study evaluating the number of formalized VSI partnerships alongside directed qualitative content analysis of periodic reflections data using Atlas.ti 22.0. DATA COLLECTION/EXTRACTION METHODS: We first independently coded reflections for implementation strategies, following the Expert Recommendations for Implementing Change (ERIC) taxonomy, and for trust-building strategies, following the Theoretical Model for Trusting Relationships and Implementation; a second round of inductive coding explored emergent themes associated with partnership formation. PRINCIPAL FINDINGS: During this period, VSI established 12 active partnerships with public and non-profit agencies. The VSI team reported using 35 ERIC implementation strategies, including building a coalition and developing educational and procedural documents, and trust-building strategies including demonstrating competence and credibility, frequent interactions, and responsiveness. Cultural competence in navigating DoD and VA and accepting and persisting through conflict also appeared to support scale-up. CONCLUSIONS: VSI's partnership-formation efforts leveraged a variety of implementation strategies, particularly around strengthening stakeholder interrelationships and refining procedures for coordination and communication. VSI implementation activities were further characterized by an intentional focus on trust-building over time. VSI's rapid scale-up highlights the value of partnership formation for achieving coordinated interventions to address complex problems.

Veteran Cultural Competence Training: Initial Effectiveness and National-Level Implementation.

OBJECTIVE: Because service professionals often lack cultural competence in working with veterans, veterans often perceive such professionals as "not understanding." The authors developed, evaluated, and implemented Veteran Cultural Competence Training (VCCT), combining educational and experiential components in an in-person training focused on building awareness, knowledge, and skills to better work with veterans. METHODS: Study 1 was a type 1 effectiveness-implementation hybrid trial examining VCCT effectiveness in a sample of social service professionals (N=41) compared with a matched comparison group (N=41) via the Multicultural Counseling Self-Efficacy Scale-Veteran Form (MCSE-V) instrument. In study 2, the authors used the reach, effectiveness, adoption, implementation, and maintenance (RE-AIM) framework to conduct a type 2 effectiveness-implementation hybrid trial and implemented VCCT with an expanded population (N=312) during eight training sessions in three U.S. states. RESULTS: Results from study 1 indicated that VCCT significantly increased self-efficacy of trainees in veteran cultural competence compared with the matched group (p<0.001). In study 2, the RE-AIM framework highlighted the importance of building coalitions and utilizing implementation facilitation to maintain fidelity. The within-group effectiveness of VCCT was statistically significant and maintained across settings and professions (p<0.001), and trainees were satisfied with VCCT. Maintenance analysis revealed expansion of VCCT after implementation in terms of the number of training sessions (N=9), regions hosting the training (N=5), staff hired (N=13), and trainee applications (N=1,018). CONCLUSIONS: VCCT effectively increases self-efficacy in veteran cultural competence. Gains appeared across different professions, demographic characteristics, and locations. Participation in VCCT may increase professionals' competence in understanding veteran culture, thereby potentially improving veteran services.

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.

Situational stress and suicide attempt behavior in Army soldiers and veterans: Insights from the Army Study to Assess Risk and Resilience in Servicemembers-Longitudinal Study.

INTRODUCTION: Prevention of suicide-related behaviors is considered a top clinical priority within the Departments of Veterans Affairs and Defense. Despite previous literature attesting to the likely importance of situational stress as a key correlate of acute changes in suicide risk, longitudinal research into associations between situational stress and suicide-related outcomes among military personnel has been relatively limited. METHODS: The current study examined associations between situational stress, recent suicide attempt, and future suicide attempt using data from 14,508 Army soldiers and recently discharged veterans enrolled in the Army Study to Assess Risk and Resilience in Servicemembers-Longitudinal Studies (STARRS-LS). RESULTS: Recent situational stress was more common among recently discharged veterans (vs. soldiers), those with a recent suicide attempt (vs. those without), and those with a subsequent suicide attempt (vs. those without). Job loss was more closely associated with suicide attempts among soldiers, whereas financial crisis, police contact, and death, illness, or injury of close others were more closely associated with suicide attempts among recently discharged veterans. CONCLUSION: Findings further highlight situational stress as a salient risk factor for suicide-related outcomes among military personnel, particularly among recently discharged veterans. Implications for screening and treatment of at-risk military personnel are discussed.

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

Transitioning servicemembers and veterans (TSMVs) face difficulties throughout their reintegration to civilian life, including challenges with employment, poor social connection, and elevated risk for suicide. To meet the needs of this high-risk population, national initiatives have leveraged community-based interventions. Authors conducted a three-arm randomized controlled trial (n = 200) to evaluate two community-based interventions. The first, Team Red, White, and Blue (RWB), connects TSMVs to their community through physical/social activities. The second, Expiration Term of Service Sponsorship Program (ETS-SP) provides one-on-one certified sponsors to TSMVs who provide support during the reintegration process. TSMVs were assessed at baseline, 3, 6, and 12 months. The primary hypothesis was not supported as reintegration difficulties and social support were not significantly different for participants randomly assigned to the two community-based interventions (Arm-2/RWB and Arm-3/RWB + ETS-SP), when the data from the separate arms were collapsed and combined, compared to the waitlist. The results did support the secondary hypothesis as Arm-3/RWB + ETS-SP had less reintegration difficulties over 12 months and initially had more social support compared to Arm-2/RWB, which suggest that augmenting interventions with sponsors outperforms participation in community-based interventions alone. Overall, the results show some limitations of the studied community-based interventions, as implemented and researched within this study. The authors identified factors that may have contributed to the null findings for the primary hypothesis, which can be addressed in future studies, such as addressing the unique needs of TSMVs, enrolling TSMVs into interventions prior to military discharge, measuring and improving participation levels, and providing stepped-care interventions based on risk levels. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Supporting the nation's transitioning veterans: Narrative review of practices and recommendations for psychotherapy and counseling of veterans separating from military service.

Each year, approximately 200,000 service members transition out of military service and return to civilian life. For many, the stresses of this military-to-civilian transition are vast and include instabilities in mental health, relationships, employment, education, and housing. Given their unique training, mental health professionals often find themselves on the front lines of efforts to support this population. However, to date, literature to guide work with this population has been scant and disorganized. This narrative review provides practitioners both within and outside the Veterans Health Administration with an overview of relevant literature in this area and offers concrete, practical recommendations for how to best support transitioning Veterans through psychotherapy and counseling. Three major themes are reviewed: (a) Engagement strategies, including clinical style, mitigation of privacy concerns, and consideration of broader psychosocial issues; (b) contextual considerations, including challenges of the "Thank You for Your Service" phenomenon, identity considerations, and circumstances of discharge; and (c) information about available services. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Machine learning hypothesis-generation for patient stratification and target discovery in rare disease: our experience with Open Science in ALS.

Introduction: Advances in machine learning (ML) methodologies, combined with multidisciplinary collaborations across biological and physical sciences, has the potential to propel drug discovery and development. Open Science fosters this collaboration by releasing datasets and methods into the public space; however, further education and widespread acceptance and adoption of Open Science approaches are necessary to tackle the plethora of known disease states. Motivation: In addition to providing much needed insights into potential therapeutic protein targets, we also aim to demonstrate that small patient datasets have the potential to provide insights that usually require many samples (>5,000). There are many such datasets available and novel advancements in ML can provide valuable insights from these patient datasets. Problem statement: Using a public dataset made available by patient advocacy group AnswerALS and a multidisciplinary Open Science approach with a systems biology augmented ML technology, we aim to validate previously reported drug targets in ALS and provide novel insights about ALS subpopulations and potential drug targets using a unique combination of ML methods and graph theory. Methodology: We use NetraAI to generate hypotheses about specific patient subpopulations, which were then refined and validated through a combination of ML techniques, systems biology methods, and expert input. Results: We extracted 8 target classes, each comprising of several genes that shed light into ALS pathophysiology and represent new avenues for treatment. These target classes are broadly categorized as inflammation, epigenetic, heat shock, neuromuscular junction, autophagy, apoptosis, axonal transport, and excitotoxicity. These findings are not mutually exclusive, and instead represent a systematic view of ALS pathophysiology. Based on these findings, we suggest that simultaneous targeting of ALS has the potential to mitigate ALS progression, with the plausibility of maintaining and sustaining an improved quality of life (QoL) for ALS patients. Even further, we identified subpopulations based on disease onset. Conclusion: In the spirit of Open Science, this work aims to bridge the knowledge gap in ALS pathophysiology to aid in diagnostic, prognostic, and therapeutic strategies and pave the way for the development of personalized treatments tailored to the individual's needs.

Technical and clinical considerations for electroencephalography-based biomarkers for major depressive disorder.

Major depressive disorder (MDD) is a prevalent and debilitating psychiatric disease that leads to substantial loss of quality of life. There has been little progress in developing new MDD therapeutics due to a poor understanding of disease heterogeneity and individuals' responses to treatments. Electroencephalography (EEG) is poised to improve this, owing to the ease of large-scale data collection and the advancement of computational methods to address artifacts. This review summarizes the viability of EEG for developing brain-based biomarkers in MDD. We examine the properties of well-established EEG preprocessing pipelines and consider factors leading to the discovery of sensitive and reliable biomarkers.

Respondents of health survey powered by the innovative NURO app exhibit correlations between exercise frequencies and diet habits, and between stress levels and sleep wellness.

Nurosene's NURO app (nurosene.com) is an innovative smartphone application that gathers and analyzes active self-report metrics from users, empowering them with data-driven health machine intelligence. We present the data collected and analyzed from the initial round of participants who responded to a 12-question survey on their life-style and health status. Exploratory results using a variational autoencoder (VAE) suggested that much of the variability of the 12 dimensional data could be accounted for by two approximately uncorrelated latent variables: one pertaining to stress and sleep, and the other pertaining to exercise and diet. Subsequent modeling of the data using exploratory and confirmatory factor analyses (EFAs and CFAs) found that optimal data fits consisted of four factors, namely exercise, diet, stress, and sleep. Covariance values were high between exercise and diet, and between stress and sleep, but much lower between other pairings of non-identical factors. Both EFAs and CFAs provided extra contexts to and quantified the more preliminary VAE observations. Overall, our results significantly reduce the apparent complexity of the response data. This reduction allows for more efficient future stratification and analyses of participants based on simpler latent variables. Our discovery of novel relationships between stress and sleep, and between exercise and diet suggests the possibility of applying predictive analytics in future efforts.

Dialectical behavior therapy for justice-involved veterans (DBT-J): Feasibility and acceptability.

Justice-involved veterans are a high-risk, high-need subgroup serviced by behavioral health services within the Veterans Health Administration (VHA) system. Justice-involved veterans often have complex mental health and substance use difficulties, a myriad of case management needs, and a range of criminogenic needs that are difficult to treat with traditional outpatient VHA services. The present study represents an initial evaluation of dialectical behavior therapy for justice-involved veterans (DBT-J), a novel psychotherapy program providing 16 weeks of skills-based group therapy and individualized case management services to veterans with current or recent involvement with the criminal justice system. A total of 13 veterans were successfully enrolled into this initial acceptability and feasibility trial. Results broadly suggested DBT-J to be characterized by high ease of implementation, successful recruitment efforts, strong participant attendance and retention, high treatment fidelity, and high acceptability by veteran participants, DBT-J providers, and adjunctive care providers alike. Although continued research using comparison conditions is necessary, veterans who completed participation in DBT-J tended to show reductions in criminogenic risk across the course of treatment. Cumulatively, these findings suggest DBT-J holds potential as a VHA-based intervention to address the various needs of justice-involved veterans. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Partnered implementation of the veteran sponsorship initiative: protocol for a randomized hybrid type 2 effectiveness-implementation trial.

BACKGROUND: The USA is undergoing a suicide epidemic for its youngest Veterans (18-to-34-years-old) as their suicide rate has almost doubled since 2001. Veterans are at the highest risk during their first-year post-discharge, thus creating a "deadly gap." In response, the nation has developed strategies that emphasize a preventive, universal, and public health approach and embrace the value of community interventions. The three-step theory of suicide suggests that community interventions that reduce reintegration difficulties and promote connectedness for Veterans as they transition to civilian life have the greatest likelihood of reducing suicide. Recent research shows that the effectiveness of community interventions can be enhanced when augmented by volunteer and certified sponsors (1-on-1) who actively engage with Veterans, as part of the Veteran Sponsorship Initiative (VSI). METHOD/DESIGN: The purpose of this randomized hybrid type 2 effectiveness-implementation trial is to evaluate the implementation of the VSI in six cities in Texas in collaboration with the US Departments of Defense, Labor and Veterans Affairs, Texas government, and local stakeholders. Texas is an optimal location for this large-scale implementation as it has the second largest population of these young Veterans and is home to the largest US military installation, Fort Hood. The first aim is to determine the effectiveness of the VSI, as evidenced by measures of reintegration difficulties, health/psychological distress, VA healthcare utilization, connectedness, and suicidal risk. The second aim is to determine the feasibility and potential utility of a stakeholder-engaged plan for implementing the VSI in Texas with the intent of future expansion in more states. The evaluators will use a stepped wedge design with a sequential roll-out to participating cities over time. Participants (n=630) will be enrolled on military installations six months prior to discharge. Implementation efforts will draw upon a bundled implementation strategy that includes strategies such as ongoing training, implementation facilitation, and audit and feedback. Formative and summative evaluations will be guided by the Reach, Effectiveness, Adoption, Implementation, and Maintenance (RE-AIM) framework and will include interviews with participants and periodic reflections with key stakeholders to longitudinally identify barriers and facilitators to implementation. DISCUSSION: This evaluation will have important implications for the national implementation of community interventions that address the epidemic of Veteran suicide. Aligned with the Evidence Act, it is the first large-scale implementation of an evidence-based practice that conducts a thorough assessment of TSMVs during the "deadly gap." TRIAL REGISTRATION: ClinicalTrials.gov ID number: NCT05224440 . Registered on 04 February 2022.

Prevalence of Personality Disorders Across Veteran Samples: A Meta-Analysis.

Despite priorities around mental health, Veteran health care organizations have historically considered personality disorders to be preexisting conditions ineligible for disability benefits. However, growing evidence suggests potentially elevated prevalence of these disorders among military and Veteran samples and attests to implications of risk. The current study provides a meta-analytic review of literature on the prevalence of personality disorders in Veteran samples. Analysis of 27 unique samples, comprising 7,161 Veterans, suggests alarmingly high rates of Veteran personality disorders. Prevalence was highest for paranoid (23%) and borderline (21%) personality disorders and lowest for histrionic (0.8%) personality disorder. Rates were generally highest among Veterans experiencing substance use or elevated suicide risk and among studies establishing diagnoses through clinical interview (versus official medical record review). Results attest to the need for Veteran health care organizations to acknowledge personality disorders in this population, through both research and treatment, and to consider reclassifying personality disorders as potential "service-connected conditions."

Using Artificial Intelligence-based Methods to Address the Placebo Response in Clinical Trials.

The placebo response is a highly complex psychosocial-biological phenomenon that has challenged drug development for decades, particularly in neurological and psychiatric disease. While decades of research have aimed to understand clinical trial factors that contribute to the placebo response, a comprehensive solution to manage the placebo response in drug development has yet to emerge. Advanced data analytic techniques, such as artificial intelligence (AI), might be needed to take the next leap forward in mitigating the negative consequences of high placebo-response rates. The objective of this review was to explore the use of techniques such as AI and the sub-discipline of machine learning (ML) to address placebo response in practical ways that can positively impact drug development. This examination focused on the critical factors that should be considered in applying AI and ML to the placebo response issue, examples of how these techniques can be used, and the regulatory considerations for integrating these approaches into clinical trials.

Demographic and socioeconomic correlates of suicide deaths and nonfatal self-injury related hospital visits: An analysis of counties in New York State.

For many years, suicide rates in U.S. general and veteran populations have steadily increased, stimulating research into suicide and nonfatal self-injury (NFSI). However, little research has examined community correlates of suicide and NFSI. This study used county data from New York State to identify community correlates of veteran and general population suicide deaths and general population NFSI-related hospitalization. In bivariate analyses, both suicide and NFSI-related hospitalization were associated with measures of social disintegration (i.e., smaller population size, larger male and/or White population) and socioeconomic disadvantage (i.e., higher disability rates disability, lower household incomes, more limited-English speaking households). In regression analyses, general-population suicide was independently associated with higher disability and veteran-suicide rates, whereas NFSI-related hospitalization was independently associated with lower household income. Findings attest the importance of low-cost, accessible, outpatient services and highlight social disintegration and socioeconomic disadvantage as salient, community risk factors for suicide and NFSI.

Arrest history and psychopathology among veterans at risk for suicide.

While preliminary evidence suggests an association between legal involvement and suicide risk among veterans, no research to date has explored the prevalence and/or correlates of legal involvement among veterans at high risk for suicide. The current study examined the relation of suicide attempt, suicidal ideation, and psychopathology to history of criminal arrest in a sample of 286 veterans at risk for suicide. Results indicated approximately half (47%) of at-risk veterans had a history of arrest. Inconsistent with hypotheses, arrest history was not associated with history of suicide attempt, current suicidal ideation, or severity of psychopathological symptoms. Arrest history was, however, associated with diagnoses of substance use disorder and antisocial personality disorder in this high-suicide risk sample. Further, likelihood of an antisocial personality disorder diagnosis was associated with higher frequency of past arrests. Taken together, results indicate that many veterans at risk for suicide have a history of arrest, and at-risk veterans with such history likely have a specific pattern of psychopathology, including antisocial personality traits and substance use. As such, legal status and history of justice involvement may be important considerations when assessing suicide risk and management of this high-risk population. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Evaluation of postmortem microarray data in bipolar disorder using traditional data comparison and artificial intelligence reveals novel gene targets.

Large-scale microarray studies on post-mortem brain tissues have been utilized to investigate the complex molecular pathology of bipolar disorder. However, a major challenge in characterizing the dysregulation of gene expression in patients with bipolar disorder includes the lack of convergence between different studies, limiting comprehensive understanding from individual results. In this study, we aimed to identify genes that are both validated in published literature and are important classification features of unsupervised machine learning analysis of Stanley Brain Bank microarray database, followed by augmented intelligence method to identify distinct patient molecular subgroups. Through combining traditional literature approaches and machine learning, we identified TBL1XR1, SMARCA2, and CHMP5 to be replicated in 3 of the 4 studies included our analysis. The expression of these genes segregated unique subgroups of patients with bipolar disorder. Our study suggests the involvement of PPARγ pathway regulation in patients with bipolar disorder.

Shattering cancer with quantum machine learning: A preview.

Machine learning has become a standard tool for medical researchers attempting to model disease in various ways, including building models to predict response to medications, classifying disease subtypes, and discovering new therapies. In this preview, we review a paper that utilizes quantum computation in order to tackle a critical issue that exists with medical datasets: they are small, in that they contain few samples. The authors' work demonstrates the possibility that these quantum-based methods may provide an advantage for small datasets and thus have a real impact for medical researchers in the future.

The deadly gap: Understanding suicide among veterans transitioning out of the military.

In the period following separation from the military, service members face the challenge of transitioning to a post-military civilian life. Some evidence suggests these transitioning Veterans are at higher risk for suicide compared with both the broader Veteran population and the United States public, yet they often do not receive adequate support and resources. In this review, we use the Three-Step Theory of suicide to outline characteristics of transitioning Veterans and the transition process that may affect suicide risk. We then highlight relevant services available to this specific subgroup of Veterans and make recommendations that address barriers to care. Cumulatively, this literature suggests transitioning Veterans fall within a "deadly gap" between the end of their military service and transition into civilian life. This "deadly gap" consists of limited psychiatric services and increased suicide risk factors which together may explain the increase in suicide during this transition period.