Using administrative data to identify U.S. Army soldiers at high-risk of perpetrating minor violent crimes

Pre-trauma predictors of severe psychiatric comorbidity 5 years following traumatic experiences

BACKGROUND

A minority of persons who have traumatic experiences go on to develop post-traumatic stress disorder (PTSD), leading to interest in who is at risk for psychopathology after these experiences. Complicating this effort is the observation that post-traumatic psychopathology is heterogeneous. The goal of this nested case-control study was to identify pre-trauma predictors of severe post-traumatic psychiatric comorbidity, using data from Danish registries.

METHODS

The source population for this study was the population of Denmark from 1994 through 2016. Cases had received three or more psychiatric diagnoses (across all ICD-10 categories) within 5 years of a traumatic experience (n = 20 361); controls were sampled from the parent cohort using risk-set sampling (n = 81 444). Analyses were repeated in samples stratified by pre-trauma psychiatric diagnoses. We used machine learning methods (classification and regression trees and random forest) to determine the important predictors of severe post-trauma psychiatric comorbidity from among hundreds of pre-trauma predictor variables spanning demographic and social variables, psychiatric and somatic diagnoses and filled medication prescriptions.

RESULTS

In the full sample, pre-trauma psychiatric diagnoses (e.g. stress disorders, alcohol-related disorders, personality disorders) were the most important predictors of severe post-trauma psychiatric comorbidity. Among persons with no pre-trauma psychiatric diagnoses, demographic and social variables (e.g. marital status), type of trauma, medications used primarily to treat psychiatric symptomatology, anti-inflammatory medications and gastrointestinal distress were important to prediction. Results among persons with pre-trauma psychiatric diagnoses were consistent with the overall sample.

CONCLUSIONS

This study builds on the understanding of pre-trauma factors that predict psychopathology following traumatic experiences, by examining a broad range of predictors of post-trauma psychopathology and comorbidity beyond PTSD.

Predicting Sex-Specific Nonfatal Suicide Attempt Risk Using Machine Learning and Data From Danish National Registries

Suicide attempts are a leading cause of injury globally. Accurate prediction of suicide attempts might offer opportunities for prevention. This case-cohort study used machine learning to examine sex-specific risk profiles for suicide attempts in Danish nationwide registry data. Cases were all persons who made a nonfatal suicide attempt between 1995 and 2015 (n = 22,974); the subcohort was a 5% random sample of the population at risk on January 1, 1995 (n = 265,183). We developed sex-stratified classification trees and random forests using 1,458 predictors, including demographic factors, family histories, psychiatric and physical health diagnoses, surgery, and prescribed medications. We found that substance use disorders/treatment, prescribed psychiatric medications, previous poisoning diagnoses, and stress disorders were important factors for predicting suicide attempts among men and women. Individuals in the top 5% of predicted risk accounted for 44.7% of all suicide attempts among men and 43.2% of all attempts among women. Our findings illuminate novel risk factors and interactions that are most predictive of nonfatal suicide attempts, while consistency between our findings and previous work in this area adds to the call to move machine learning suicide research toward the examination of high-risk subpopulations.

Sex-Specific Risk Profiles for Suicide Among Persons with Substance Use Disorders in Denmark

BACKGROUND AND AIMS

Persons with substance use disorders (SUDs) are at elevated risk of suicide death. We identified novel risk factors and interactions that predict suicide among men and women with SUD using machine learning.

DESIGN

Case-cohort study.

SETTING

Denmark.

PARTICIPANTS

The sample was restricted to persons with their first SUD diagnosis during 1995 to 2015. Cases were persons who died by suicide in Denmark during 1995 to 2015 (n = 2774) and the comparison subcohort was a 5% random sample of individuals in Denmark on 1 January 1995 (n = 13 179).

MEASUREMENTS

Suicide death was recorded in the Danish Cause of Death Registry. Predictors included social and demographic information, mental and physical health diagnoses, surgeries, medications, and poisonings.

FINDINGS

Persons among the highest risk for suicide, as identified by the classification trees, were men prescribed antidepressants in the 4 years before suicide and had a poisoning diagnosis in the 4 years before suicide; and women who were 30+ years old and had a poisoning diagnosis 4 years before and 12 months before suicide. Among men with SUD, the random forest identified five variables that were most important in predicting suicide; reaction to severe stress and adjustment disorders, drugs used to treat addictive disorders, age 30+ years, antidepressant use, and poisoning in the 4 prior years. Among women with SUD, the random forest found that the most important predictors of suicide were prior poisonings and reaction to severe stress and adjustment disorders. Individuals in the top 5% of predicted risk accounted for 15% of all suicide deaths among men and 24% of all suicides among women.

CONCLUSIONS

In Denmark, prior poisoning and comorbid psychiatric disorders may be among the most important indicators of suicide risk among persons with substance use disorders, particularly among women.

Risk and Protective Factors for Difficulty Controlling Violent Behavior in National Guard and Reserve Service Members

Violent behavior is an important problem for military service members and veterans. A representative cohort of U.S. Reserve and National Guard personnel (N = 1,293) were interviewed to assess self-reported problems controlling violent behavior, deployment traumas, posttraumatic stress disorder (PTSD), alcohol abuse, and social support. Poisson regression models were used to estimate the associations of violent behavior with risk and protective factors. Problems controlling violent behavior were uncommon among male (3.3%) and female (1.7%) service members. Adjusted prevalence ratios (aPR) showed associations between violent behavior and deployment traumas (aPR = 1.67, 95% confidence interval [CI] = [1.34, 2.08]), PTSD (aPR = 9.95, 95% CI = [5.09, 19.48]), and PTSD symptom severity (aPR for each additional PTSD symptom = 1.07, 95% CI = [1.06, 1.09]). Social support was associated with lower prevalence of violent behavior (aPR = 0.62, 95% CI = [0.52, 0.76]). The association between violent behavior and alcohol abuse was not statistically significant (aPR = 1.94, 95% CI = [0.92, 4.09]). Results were consistent when the population was restricted to personnel who had deployed to a war zone. Problems controlling violent behavior were less common in this cohort than has been documented in other studies. Associations of violent behavior with risk and protective factors are consistent with prior research.

Prediction of Sex-Specific Suicide Risk Using Machine Learning and Single-Payer Health Care Registry Data From Denmark

Importance

Suicide is a public health problem, with multiple causes that are poorly understood. The increased focus on combining health care data with machine-learning approaches in psychiatry may help advance the understanding of suicide risk.

Objective

To examine sex-specific risk profiles for death from suicide using machine-learning methods and data from the population of Denmark.

Design, Setting, and Participants

A case-cohort study nested within 8 national Danish health and social registries was conducted from January 1, 1995, through December 31, 2015. The source population was all persons born or residing in Denmark as of January 1, 1995. Data were analyzed from November 5, 2018, through May 13, 2019.

Exposures

Exposures included 1339 variables spanning domains of suicide risk factors.

Main Outcomes and Measures

Death from suicide from the Danish cause of death registry.

Results

A total of 14 103 individuals died by suicide between 1995 and 2015 (10 152 men [72.0%]; mean [SD] age, 43.5 [18.8] years and 3951 women [28.0%]; age, 47.6 [18.8] years). The comparison subcohort was a 5% random sample (n = 265 183) of living individuals in Denmark on January 1, 1995 (130 591 men [49.2%]; age, 37.4 [21.8] years and 134 592 women [50.8%]; age, 39.9 [23.4] years). With use of classification trees and random forests, sex-specific differences were noted in risk for suicide, with physical health more important to men's suicide risk than women's suicide risk. Psychiatric disorders and possibly associated medications were important to suicide risk, with specific results that may increase clarity in the literature. Generally, diagnoses and medications measured 48 months before suicide were more important indicators of suicide risk than when measured 6 months earlier. Individuals in the top 5% of predicted suicide risk appeared to account for 32.0% of all suicide cases in men and 53.4% of all cases in women.

Conclusions and Relevance

Despite decades of research on suicide risk factors, understanding of suicide remains poor. In this study, the first to date to develop risk profiles for suicide based on data from a full population, apparent consistency with what is known about suicide risk was noted, as well as potentially important, understudied risk factors with evidence of unique suicide risk profiles among specific subpopulations.

The Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS): progress toward understanding suicide among soldiers

Responding to an unprecedented increase in the suicide rate among soldiers, in 2008 the US Army and US National Institute of Mental Health funded the Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS), a multicomponent epidemiological and neurobiological study of risk and resilience factors for suicidal thoughts and behaviors, and their psychopathological correlates among Army personnel. Using a combination of administrative records, representative surveys, computerized neurocognitive tests, and blood samples, Army STARRS and its longitudinal follow-up study (STARRS-LS) are designed to identify potentially actionable findings to inform the Army's suicide prevention efforts. The current report presents a broad overview of Army STARRS and its findings to date on suicide deaths, attempts, and ideation, as well as other important outcomes that may increase suicide risk (e.g., mental disorders, sexual assault victimization). The findings highlight the complexity of environmental and genetic risk and protective factors in different settings and contexts, and the importance of life and career history in understanding suicidal thoughts and behaviors.

Risk Factors Associated With Attempted Suicide Among US Army Soldiers Without a History of Mental Health Diagnosis

IMPORTANCE

The US Army suicide attempt rate increased sharply during the wars in Afghanistan and Iraq. Although soldiers with a prior mental health diagnosis (MH-Dx) are known to be at risk, little is known about risk among those with no history of diagnosis.

OBJECTIVE

To examine risk factors for suicide attempt among soldiers without a previous MH-Dx.

DESIGN, SETTING, AND PARTICIPANTS

In this retrospective longitudinal cohort study using administrative data from the Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS), person-month records were identified for all active-duty Regular Army enlisted soldiers who had a medically documented suicide attempt from January 1, 2004, through December 31, 2009 (n = 9650), and an equal-probability sample of control person-months (n = 153 528). Data analysis in our study was from September 16, 2017, to June 6, 2018. In a stratified sample, it was examined whether risk factors for suicide attempt varied by history of MH-Dx.

MAIN OUTCOMES AND MEASURES

Suicide attempts were identified using Department of Defense Suicide Event Report records and International Classification of Diseases, Ninth Revision, Clinical Modification E95 × diagnostic codes. Mental health diagnoses and related codes, as well as sociodemographic, service-related, physical health care, injury, subjection to crime, crime perpetration, and family violence variables, were constructed from Army personnel, medical, legal, and family services records.

RESULTS

Among 9650 enlisted soldiers with a documented suicide attempt (74.8% male), 3507 (36.3%) did not have a previous MH-Dx. Among soldiers with no previous diagnosis, the highest adjusted odds of suicide attempt were for the following: female sex (odds ratio [OR], 2.6; 95% CI, 2.4-2.8), less than high school education (OR, 1.9; 95% CI, 1.8-2.0), first year of service (OR, 6.0; 95% CI, 4.7-7.7), previously deployed (OR, 2.4; 95% CI, 2.1-2.8), promotion delayed 2 months or less (OR, 2.1; 95% CI, 1.7-2.6), past-year demotion (OR, 1.6; 95% CI, 1.3-1.8), 8 or more outpatient physical health care visits in the past 2 months (OR, 3.3; 95% CI, 2.9-3.8), past-month injury-related outpatient (OR, 3.0; 95% CI, 2.8-3.3) and inpatient (OR, 3.8; 95% CI, 2.3-6.3) health care visits, previous combat injury (OR, 1.6; 95% CI, 1.0-2.4), subjection to minor violent crime (OR, 1.6; 95% CI, 1.1-2.4), major violent crime perpetration (OR, 2.0; 95% CI, 1.3-3.0), and family violence (OR, 2.9; 95% CI, 1.9-4.4). Most of these variables were also associated with suicide attempts among soldiers with a previous MH-Dx, although the strength of associations differed.

CONCLUSIONS AND RELEVANCE

Suicide attempt risk among soldiers with unrecognized mental health problems is a significant and important challenge. Administrative records from personnel, medical, legal, and family services systems can assist in identifying soldiers at risk.

Improving risk prediction accuracy for new soldiers in the U.S. Army by adding self-report survey data to administrative data

BACKGROUND

High rates of mental disorders, suicidality, and interpersonal violence early in the military career have raised interest in implementing preventive interventions with high-risk new enlistees. The Army Study to Assess Risk and Resilience in Servicemembers (STARRS) developed risk-targeting systems for these outcomes based on machine learning methods using administrative data predictors. However, administrative data omit many risk factors, raising the question whether risk targeting could be improved by adding self-report survey data to prediction models. If so, the Army may gain from routinely administering surveys that assess additional risk factors.

METHODS

The STARRS New Soldier Survey was administered to 21,790 Regular Army soldiers who agreed to have survey data linked to administrative records. As reported previously, machine learning models using administrative data as predictors found that small proportions of high-risk soldiers accounted for high proportions of negative outcomes. Other machine learning models using self-report survey data as predictors were developed previously for three of these outcomes: major physical violence and sexual violence perpetration among men and sexual violence victimization among women. Here we examined the extent to which this survey information increases prediction accuracy, over models based solely on administrative data, for those three outcomes. We used discrete-time survival analysis to estimate a series of models predicting first occurrence, assessing how model fit improved and concentration of risk increased when adding the predicted risk score based on survey data to the predicted risk score based on administrative data.

RESULTS

The addition of survey data improved prediction significantly for all outcomes. In the most extreme case, the percentage of reported sexual violence victimization among the 5% of female soldiers with highest predicted risk increased from 17.5% using only administrative predictors to 29.4% adding survey predictors, a 67.9% proportional increase in prediction accuracy. Other proportional increases in concentration of risk ranged from 4.8% to 49.5% (median = 26.0%).

CONCLUSIONS

Data from an ongoing New Soldier Survey could substantially improve accuracy of risk models compared to models based exclusively on administrative predictors. Depending upon the characteristics of interventions used, the increase in targeting accuracy from survey data might offset survey administration costs.

Predicting Sexual Assault Perpetration in the U.S. Army Using Administrative Data

INTRODUCTION

The Department of Defense uses a universal prevention framework for sexual assault prevention, with each branch implementing its own branch-wide programs. Intensive interventions exist, but would be cost effective only if targeted at high-risk personnel. This study developed actuarial models to identify male U.S. Army soldiers at high risk of administratively recorded sexual assault perpetration.

METHODS

This study investigated administratively recorded sexual assault perpetration among the 821,807 male Army soldiers serving 2004-2009. Administrative data were also used to operationalize the predictors. Penalized discrete-time (person-month) survival analysis (conducted in 2016) was used to select the smallest possible number of stable predictors to maximize number of sexual assaults among the 5% of soldiers with highest predicted risk of perpetration (top-ventile concentration of risk). Separate models were developed for assaults against non-family and intra-family adults and minors.

RESULTS

There were 4,640 male soldiers found to be perpetrators against non-family adults, 1,384 against non-family minors, 380 against intra-family adults, and 335 against intra-family minors. Top-ventile concentration of risk was 16.2%-20.2% predicting perpetration against non-family adults and minors and 34.2%-65.1% against intra-family adults and minors. Final predictors consisted largely of measures of prior crime involvement and the presence and treatment of mental disorders.

CONCLUSIONS

Administrative data can be used to develop actuarial models that identify a high proportion of sexual assault perpetrators. If a system is developed to consolidate administrative predictors routinely, then predictions could be generated periodically to identify those in need of preventive intervention. Whether this would be cost effective, though, would depend on intervention costs, effectiveness, and competing risks.