Objectives
Comorbidity is a common feature of mental disorders. However, needs assessment surveys focus largely on individual disorders rather than on comorbidity even though the latter is more ...important for predicting suicidal thoughts and behaviors. In the current report, we take a step beyond this conventional approach by presenting data on the prevalence and correlates (sociodemographic factors, college‐related factors, and suicidal thoughts and behaviors) of the main multivariate profiles of common comorbid Diagnostic and Statistical Manual of Mental Disorders (DSM)‐IV disorders among students participating in the first phase of the World Health Organization World Mental Health International College Student initiative.
Method
A web‐based mental health survey was administered to first year students in 19 colleges across eight countries (Australia, Belgium, Germany, Mexico, Northern Ireland, South Africa, Spain, United States; 45.5% pooled response rate) to screen for seven common DSM‐IV mental disorders: major depression, mania/hypomania, generalized anxiety disorder, panic disorder, attention‐deficit/hyperactivity disorder, alcohol use disorder, and drug use disorder. We focus on the 14,348 respondents who provided complete data; 38.4% screened positive for at least one 12‐month disorder.
Results
Multivariate disorder profiles were detected using latent class analysis (LCA). The least common class (C1; 1.9% of students) was made up of students with high comorbidity (four or more disorders, the majority including mania/hypomania). The remaining 12‐month cases had profiles of internalizing–externalizing comorbidity (C2; 5.8%), internalizing comorbidity (C3; 14.6%), and pure disorders (C4; 16.1%). The 1.9% of students in C1 had much higher prevalence of suicidal thoughts and behaviors than other students. Specifically, 15.4% of students in C1 made a suicide attempt in the 12 months before the survey compared with 1.3–2.6% of students with disorders in C2–4, 0.2% of students with lifetime disorders but no 12‐month disorders (C5), and 0.1% of students with no lifetime disorders (C6).
Conclusions
In line with prior research, comorbid mental disorders were common; however, sociodemographic correlates of LCA profiles were modest. The high level of comorbidity underscores the need to develop and test transdiagnostic approaches for treatment in college students.
Background: Although post-traumatic stress disorder (PTSD) onset-persistence is thought to vary significantly by trauma type, most epidemiological surveys are incapable of assessing this because they ...evaluate lifetime PTSD only for traumas nominated by respondents as their 'worst.'
Objective: To review research on associations of trauma type with PTSD in the WHO World Mental Health (WMH) surveys, a series of epidemiological surveys that obtained representative data on trauma-specific PTSD.
Method: WMH Surveys in 24 countries (n = 68,894) assessed 29 lifetime traumas and evaluated PTSD twice for each respondent: once for the 'worst' lifetime trauma and separately for a randomly-selected trauma with weighting to adjust for individual differences in trauma exposures. PTSD onset-persistence was evaluated with the WHO Composite International Diagnostic Interview.
Results: In total, 70.4% of respondents experienced lifetime traumas, with exposure averaging 3.2 traumas per capita. Substantial between-trauma differences were found in PTSD onset but less in persistence. Traumas involving interpersonal violence had highest risk. Burden of PTSD, determined by multiplying trauma prevalence by trauma-specific PTSD risk and persistence, was 77.7 person-years/100 respondents. The trauma types with highest proportions of this burden were rape (13.1%), other sexual assault (15.1%), being stalked (9.8%), and unexpected death of a loved one (11.6%). The first three of these four represent relatively uncommon traumas with high PTSD risk and the last a very common trauma with low PTSD risk. The broad category of intimate partner sexual violence accounted for nearly 42.7% of all person-years with PTSD. Prior trauma history predicted both future trauma exposure and future PTSD risk.
Conclusions: Trauma exposure is common throughout the world, unequally distributed, and differential across trauma types with respect to PTSD risk. Although a substantial minority of PTSD cases remits within months after onset, mean symptom duration is considerably longer than previously recognized.
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.
IMPORTANCE: The US Army experienced a sharp increase in soldier suicides beginning in 2004. Administrative data reveal that among those at highest risk are soldiers in the 12 months after inpatient ...treatment of a psychiatric disorder. OBJECTIVE: To develop an actuarial risk algorithm predicting suicide in the 12 months after US Army soldier inpatient treatment of a psychiatric disorder to target expanded posthospitalization care. DESIGN, SETTING, AND PARTICIPANTS: There were 53 769 hospitalizations of active duty soldiers from January 1, 2004, through December 31, 2009, with International Classification of Diseases, Ninth Revision, Clinical Modification psychiatric admission diagnoses. Administrative data available before hospital discharge abstracted from a wide range of data systems (sociodemographic, US Army career, criminal justice, and medical or pharmacy) were used to predict suicides in the subsequent 12 months using machine learning methods (regression trees and penalized regressions) designed to evaluate cross-validated linear, nonlinear, and interactive predictive associations. MAIN OUTCOMES AND MEASURES: Suicides of soldiers hospitalized with psychiatric disorders in the 12 months after hospital discharge. RESULTS: Sixty-eight soldiers died by suicide within 12 months of hospital discharge (12.0% of all US Army suicides), equivalent to 263.9 suicides per 100 000 person-years compared with 18.5 suicides per 100 000 person-years in the total US Army. The strongest predictors included sociodemographics (male sex odds ratio (OR), 7.9; 95% CI, 1.9-32.6 and late age of enlistment OR, 1.9; 95% CI, 1.0-3.5), criminal offenses (verbal violence OR, 2.2; 95% CI, 1.2-4.0 and weapons possession OR, 5.6; 95% CI, 1.7-18.3), prior suicidality OR, 2.9; 95% CI, 1.7-4.9, aspects of prior psychiatric inpatient and outpatient treatment (eg, number of antidepressant prescriptions filled in the past 12 months OR, 1.3; 95% CI, 1.1-1.7), and disorders diagnosed during the focal hospitalizations (eg, nonaffective psychosis OR, 2.9; 95% CI, 1.2-7.0). A total of 52.9% of posthospitalization suicides occurred after the 5% of hospitalizations with highest predicted suicide risk (3824.1 suicides per 100 000 person-years). These highest-risk hospitalizations also accounted for significantly elevated proportions of several other adverse posthospitalization outcomes (unintentional injury deaths, suicide attempts, and subsequent hospitalizations). CONCLUSIONS AND RELEVANCE: The high concentration of risk of suicide and other adverse outcomes might justify targeting expanded posthospitalization interventions to soldiers classified as having highest posthospitalization suicide risk, although final determination requires careful consideration of intervention costs, comparative effectiveness, and possible adverse effects.
Objectives
The US Veterans Health Administration (VHA) has begun using predictive modeling to identify Veterans at high suicide risk to target care. Initial analyses are reported here.
Methods
A ...penalized logistic regression model was compared with an earlier proof‐of‐concept logistic model. Exploratory analyses then considered commonly‐used machine learning algorithms. Analyses were based on electronic medical records for all 6,360 individuals classified in the National Death Index as having died by suicide in fiscal years 2009–2011 who used VHA services the year of their death or prior year and a 1% probability sample of time‐matched VHA service users alive at the index date (n = 2,112,008).
Results
A penalized logistic model with 61 predictors had sensitivity comparable to the proof‐of‐concept model (which had 381 predictors) at target thresholds. The machine learning algorithms had relatively similar sensitivities, the highest being for Bayesian additive regression trees, with 10.7% of suicides occurred among the 1.0% of Veterans with highest predicted risk and 28.1% among the 5.0% of with highest predicted risk.
Conclusions
Based on these results, VHA is using penalized logistic regression in initial intervention implementation. The paper concludes with a discussion of other practical issues that might be explored to increase model performance.
The ability to predict and prevent homelessness has been an elusive goal. The purpose of this study was to develop a prediction model that identified U.S. Army soldiers at high risk of becoming ...homeless after transitioning to civilian life based on information available before the time of this transition.
The prospective cohort study consisted of observations from 16,589 soldiers who were separated or deactivated from service and who had previously participated in 1 of 3 baseline surveys of the Army Study to Assess Risk and Resilience in Servicemembers in 2011–2014. A machine learning model was developed in a 70% training sample and evaluated in the remaining 30% test sample to predict self-reported homelessness in 1 of 2 Longitudinal Study surveys administered in 2016–2018 and 2018–2019. Predictors included survey, administrative, and geospatial variables available before separation/deactivation. Analysis was conducted in November 2020–May 2021.
The 12-month prevalence of homelessness was 2.9% (SE=0.2%) in the total Longitudinal Study sample. The area under the receiver operating characteristic curve in the test sample was 0.78 (SE=0.02) for homelessness. The 4 highest ventiles (top 20%) of predicted risk included 61% of respondents with homelessness. Self-reported lifetime histories of depression, trauma of having a loved one murdered, and post-traumatic stress disorder were the 3 strongest predictors of homelessness.
A prediction model for homelessness can accurately target soldiers for preventive intervention before transition to civilian life.
Objectives
To illustrate the use of machine learning methods to search for heterogeneous effects of a target modifiable risk factor on suicide in observational studies. The illustration focuses on ...secondary analysis of a matched case‐control study of vitamin D deficiency predicting subsequent suicide.
Methods
We describe a variety of machine learning methods to search for prescriptive predictors; that is, predictors of significant variation in the association between a target risk factor and subsequent suicide. In each case, the purpose is to evaluate the potential value of selective intervention on the target risk factor to prevent the outcome based on the provisional assumption that the target risk factor is causal. The approaches illustrated include risk modeling based on the super learner ensemble machine learning method, Least Absolute Shrinkage and Selection Operator (Lasso) penalized regression, and the causal forest algorithm.
Results
The logic of estimating heterogeneous intervention effects is exposited along with the illustration of some widely used methods for implementing this logic.
Conclusions
In addition to describing best practices in using the machine learning methods considered here, we close with a discussion of broader design and analysis issues in planning an observational study to investigate heterogeneous effects of a modifiable risk factor.
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.
We revised the original model in a sample of
= 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.
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.
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.
Abstract
Study Objectives
Many patients in Emergency Departments (EDs) after motor vehicle collisions (MVCs) develop post-traumatic stress disorder (PTSD) or major depressive episode (MDE). This ...report from the AURORA study focuses on associations of pre-MVC sleep problems with these outcomes 8 weeks after MVC mediated through peritraumatic distress and dissociation and 2-week outcomes.
Methods
A total of 666 AURORA patients completed self-report assessments in the ED and at 2 and 8 weeks after MVC. Peritraumatic distress, peritraumatic dissociation, and pre-MVC sleep characteristics (insomnia, nightmares, daytime sleepiness, and sleep duration in the 30 days before the MVC, trait sleep stress reactivity) were assessed retrospectively in the ED. The survey assessed acute stress disorder (ASD) and MDE at 2 weeks and at 8 weeks assessed PTSD and MDE (past 30 days). Control variables included demographics, MVC characteristics, and retrospective reports about PTSD and MDE in the 30 days before the MVC.
Results
Prevalence estimates were 41.0% for 2-week ASD, 42.0% for 8-week PTSD, 30.5% for 2-week MDE, and 27.2% for 8-week MDE. Pre-MVC nightmares and sleep stress reactivity predicted 8-week PTSD (mediated through 2-week ASD) and MDE (mediated through the transition between 2-week and 8-week MDE). Pre-MVC insomnia predicted 8-week PTSD (mediated through 2-week ASD). Estimates of population attributable risk suggest that blocking effects of sleep disturbance might reduce prevalence of 8-week PTSD and MDE by as much as one-third.
Conclusions
Targeting disturbed sleep in the immediate aftermath of MVC might be one effective way of reducing MVC-related PTSD and MDE.