Developing an individualized treatment rule for Veterans with major depressive disorder using electronic health records.

Efforts to develop an individualized treatment rule (ITR) to optimize major depressive disorder (MDD) treatment with antidepressant medication (ADM), psychotherapy, or combined ADM-psychotherapy have been hampered by small samples, small predictor sets, and suboptimal analysis methods. Analyses of large administrative databases designed to approximate experiments followed iteratively by pragmatic trials hold promise for resolving these problems. The current report presents a proof-of-concept study using electronic health records (EHR) of n = 43,470 outpatients beginning MDD treatment in Veterans Health Administration Primary Care Mental Health Integration (PC-MHI) clinics, which offer access not only to ADMs but also psychotherapy and combined ADM-psychotherapy. EHR and geospatial databases were used to generate an extensive baseline predictor set (5,865 variables). The outcome was a composite measure of at least one serious negative event (suicide attempt, psychiatric emergency department visit, psychiatric hospitalization, suicide death) over the next 12 months. Best-practices methods were used to adjust for nonrandom treatment assignment and to estimate a preliminary ITR in a 70% training sample and to evaluate the ITR in the 30% test sample. Statistically significant aggregate variation was found in overall probability of the outcome related to baseline predictors (AU-ROC = 0.68, S.E. = 0.01), with test sample outcome prevalence of 32.6% among the 5% of patients having highest predicted risk compared to 7.1% in the remainder of the test sample. The ITR found that psychotherapy-only was the optimal treatment for 56.0% of patients (roughly 20% lower risk of the outcome than if receiving one of the other treatments) and that treatment type was unrelated to outcome risk among other patients. Change in aggregate treatment costs of implementing this ITR would be negligible, as 16.1% fewer patients would be prescribed ADMs and 2.9% more would receive psychotherapy. A pragmatic trial would be needed to confirm the accuracy of the ITR.

Estimated Average Treatment Effect of Psychiatric Hospitalization in Patients With Suicidal Behaviors: A Precision Treatment Analysis.

Importance: Psychiatric hospitalization is the standard of care for patients presenting to an emergency department (ED) or urgent care (UC) with high suicide risk. However, the effect of hospitalization in reducing subsequent suicidal behaviors is poorly understood and likely heterogeneous. Objectives: To estimate the association of psychiatric hospitalization with subsequent suicidal behaviors using observational data and develop a preliminary predictive analytics individualized treatment rule accounting for heterogeneity in this association across patients. Design, Setting, and Participants: A machine learning analysis of retrospective data was conducted. All veterans presenting with suicidal ideation (SI) or suicide attempt (SA) from January 1, 2010, to December 31, 2015, were included. Data were analyzed from September 1, 2022, to March 10, 2023. Subgroups were defined by primary psychiatric diagnosis (nonaffective psychosis, bipolar disorder, major depressive disorder, and other) and suicidality (SI only, SA in past 2-7 days, and SA in past day). Models were trained in 70.0% of the training samples and tested in the remaining 30.0%. Exposures: Psychiatric hospitalization vs nonhospitalization. Main Outcomes and Measures: Fatal and nonfatal SAs within 12 months of ED/UC visits were identified in administrative records and the National Death Index. Baseline covariates were drawn from electronic health records and geospatial databases. Results: Of 196 610 visits (90.3% men; median [IQR] age, 53 [41-59] years), 71.5% resulted in hospitalization. The 12-month SA risk was 11.9% with hospitalization and 12.0% with nonhospitalization (difference, -0.1%; 95% CI, -0.4% to 0.2%). In patients with SI only or SA in the past 2 to 7 days, most hospitalization was not associated with subsequent SAs. For patients with SA in the past day, hospitalization was associated with risk reductions ranging from -6.9% to -9.6% across diagnoses. Accounting for heterogeneity, hospitalization was associated with reduced risk of subsequent SAs in 28.1% of the patients and increased risk in 24.0%. An individualized treatment rule based on these associations may reduce SAs by 16.0% and hospitalizations by 13.0% compared with current rates. Conclusions and Relevance: The findings of this study suggest that psychiatric hospitalization is associated with reduced average SA risk in the immediate aftermath of an SA but not after other recent SAs or SI only. Substantial heterogeneity exists in these associations across patients. An individualized treatment rule accounting for this heterogeneity could both reduce SAs and avert hospitalizations.

Development of a model to predict antidepressant treatment response for depression among Veterans.

BACKGROUND: Only a limited number of patients with major depressive disorder (MDD) respond to a first course of antidepressant medication (ADM). We investigated the feasibility of creating a baseline model to determine which of these would be among patients beginning ADM treatment in the US Veterans Health Administration (VHA). METHODS: A 2018-2020 national sample of n = 660 VHA patients receiving ADM treatment for MDD completed an extensive baseline self-report assessment near the beginning of treatment and a 3-month self-report follow-up assessment. Using baseline self-report data along with administrative and geospatial data, an ensemble machine learning method was used to develop a model for 3-month treatment response defined by the Quick Inventory of Depression Symptomatology Self-Report and a modified Sheehan Disability Scale. The model was developed in a 70% training sample and tested in the remaining 30% test sample. RESULTS: In total, 35.7% of patients responded to treatment. The prediction model had an area under the ROC curve (s.e.) of 0.66 (0.04) in the test sample. A strong gradient in probability (s.e.) of treatment response was found across three subsamples of the test sample using training sample thresholds for high [45.6% (5.5)], intermediate [34.5% (7.6)], and low [11.1% (4.9)] probabilities of response. Baseline symptom severity, comorbidity, treatment characteristics (expectations, history, and aspects of current treatment), and protective/resilience factors were the most important predictors. CONCLUSIONS: Although these results are promising, parallel models to predict response to alternative treatments based on data collected before initiating treatment would be needed for such models to help guide treatment selection.

A two-phase, prescriptive comparative effectiveness study to optimize the treatment of co-occurring insomnia and depression with digital interventions.

BACKGROUND: Insomnia and depression frequently co-occur. Significant barriers preclude a majority of patients from receiving first line treatments for both disorders in a sequential treatment episode. Although digital versions of cognitive behavioral therapy for insomnia (CBTI) and for depression (CBTD) hold some promise to meet demand, especially when paired with human support, it is unknown whether heterogeneity of treatment effects exist, such that some patients would be optimally treated with single or sequential interventions. OBJECTIVE: Describe the protocol for a two-phase, prescriptive comparative effectiveness study to develop and evaluate an individualized intervention rule (IIR) for prescribing the optimal digital treament of co-occurring insomnia and depression. METHODS: The proposed sample size is 2300 U.S. military veterans with insomnia and depression recruited nationally (Phase 1 = 1500; Phase 2 = 800). In each phase, the primary endpoint will be remission of both depression and insomnia 3 months following a 12-week intervention period. Phase 1 is a 5-arm randomized trial: two single digital interventions (CBT-I or CBT-D); two sequenced interventions (CBT-I + D or CBT-D + I); and a mood monitoring control condition. A cutting-edge ensemble machine learning method will be used to develop the IIR. Phase 2 will evaluate the IIR by randomizing participants with equal allocation to either the IIR predicted optimal intervention for that individual or by randomization to one the four CBT interventions. RESULTS: Study procedures are ongoing. Results will be reported in future manuscripts. CONCLUSION: The study will generate evidence on the optimal scalable approach to treat co-occurring insomnia and depression.

Evaluation of a Model to Target High-risk Psychiatric Inpatients for an Intensive Postdischarge Suicide Prevention Intervention.

Importance: The months after psychiatric hospital discharge are a time of high risk for suicide. Intensive postdischarge case management, although potentially effective in suicide prevention, is likely to be cost-effective only if targeted at high-risk patients. A previously developed machine learning (ML) model showed that postdischarge suicides can be predicted from electronic health records and geospatial data, but it is unknown if prediction could be improved by adding additional information. Objective: To determine whether model prediction could be improved by adding information extracted from clinical notes and public records. Design, Setting, and Participants: Models were trained to predict suicides in the 12 months after Veterans Health Administration (VHA) short-term (less than 365 days) psychiatric hospitalizations between the beginning of 2010 and September 1, 2012 (299 050 hospitalizations, with 916 hospitalizations followed within 12 months by suicides) and tested in the hospitalizations from September 2, 2012, to December 31, 2013 (149 738 hospitalizations, with 393 hospitalizations followed within 12 months by suicides). Validation focused on net benefit across a range of plausible decision thresholds. Predictor importance was assessed with Shapley additive explanations (SHAP) values. Data were analyzed from January to August 2022. Main Outcomes and Measures: Suicides were defined by the National Death Index. Base model predictors included VHA electronic health records and patient residential data. The expanded predictors came from natural language processing (NLP) of clinical notes and a social determinants of health (SDOH) public records database. Results: The model included 448 788 unique hospitalizations. Net benefit over risk horizons between 3 and 12 months was generally highest for the model that included both NLP and SDOH predictors (area under the receiver operating characteristic curve range, 0.747-0.780; area under the precision recall curve relative to the suicide rate range, 3.87-5.75). NLP and SDOH predictors also had the highest predictor class-level SHAP values (proportional SHAP = 64.0% and 49.3%, respectively), although the single highest positive variable-level SHAP value was for a count of medications classified by the US Food and Drug Administration as increasing suicide risk prescribed the year before hospitalization (proportional SHAP = 15.0%). Conclusions and Relevance: In this study, clinical notes and public records were found to improve ML model prediction of suicide after psychiatric hospitalization. The model had positive net benefit over 3-month to 12-month risk horizons for plausible decision thresholds. Although caution is needed in inferring causality based on predictor importance, several key predictors have potential intervention implications that should be investigated in future studies.

Development of a model to predict combined antidepressant medication and psychotherapy treatment response for depression among veterans.

BACKGROUND: Although research shows that more depressed patients respond to combined antidepressants (ADM) and psychotherapy than either alone, many patients do not respond even to combined treatment. A reliable prediction model for this could help treatment decision-making. We attempted to create such a model using machine learning methods among patients in the US Veterans Health Administration (VHA). METHODS: A 2018-2020 national sample of VHA patients beginning combined depression treatment completed self-report assessments at baseline and 3 months (n = 658). A learning model was developed using baseline self-report, administrative, and geospatial data to predict 3-month treatment response defined by reductions in the Quick Inventory of Depression Symptomatology Self-Report and/or in the Sheehan Disability Scale. The model was developed in a 70 % training sample and tested in the remaining 30 % test sample. RESULTS: 30.0 % of patients responded to treatment. The prediction model had a test sample AUC-ROC of 0.657. A strong gradient was found in probability of treatment response from 52.7 % in the highest predicted quintile to 14.4 % in the lowest predicted quintile. The most important predictors were episode characteristics (symptoms, comorbidities, history), personality/psychological resilience, recent stressors, and treatment characteristics. LIMITATIONS: Restrictions in sample definition, a low recruitment rate, and reliance on patient self-report rather than clinician assessments to determine treatment response limited the generalizability of results. CONCLUSIONS: A machine learning model could help depressed patients and providers predict likely response to combined ADM-psychotherapy. Parallel information about potential harms and costs of alternative treatments would be needed, though, to inform optimal treatment selection.

Development of a model to predict psychotherapy response for depression among Veterans.

BACKGROUND: Fewer than half of patients with major depressive disorder (MDD) respond to psychotherapy. Pre-emptively informing patients of their likelihood of responding could be useful as part of a patient-centered treatment decision-support plan. METHODS: This prospective observational study examined a national sample of 807 patients beginning psychotherapy for MDD at the Veterans Health Administration. Patients completed a self-report survey at baseline and 3-months follow-up (data collected 2018-2020). We developed a machine learning (ML) model to predict psychotherapy response at 3 months using baseline survey, administrative, and geospatial variables in a 70% training sample. Model performance was then evaluated in the 30% test sample. RESULTS: 32.0% of patients responded to treatment after 3 months. The best ML model had an AUC (SE) of 0.652 (0.038) in the test sample. Among the one-third of patients ranked by the model as most likely to respond, 50.0% in the test sample responded to psychotherapy. In comparison, among the remaining two-thirds of patients, <25% responded to psychotherapy. The model selected 43 predictors, of which nearly all were self-report variables. CONCLUSIONS: Patients with MDD could pre-emptively be informed of their likelihood of responding to psychotherapy using a prediction tool based on self-report data. This tool could meaningfully help patients and providers in shared decision-making, although parallel information about the likelihood of responding to alternative treatments would be needed to inform decision-making across multiple treatments.

The Appalachia Mind Health Initiative (AMHI): a pragmatic randomized clinical trial of adjunctive internet-based cognitive behavior therapy for treating major depressive disorder among primary care patients.

BACKGROUND: Major depressive disorder (MDD) is a leading cause of disease morbidity. Combined treatment with antidepressant medication (ADM) plus psychotherapy yields a much higher MDD remission rate than ADM only. But 77% of US MDD patients are nonetheless treated with ADM only despite strong patient preferences for psychotherapy. This mismatch is due at least in part to a combination of cost considerations and limited availability of psychotherapists, although stigma and reluctance of PCPs to refer patients for psychotherapy are also involved. Internet-based cognitive behaviorial therapy (i-CBT) addresses all of these problems. METHODS: Enrolled patients (n = 3360) will be those who are beginning ADM-only treatment of MDD in primary care facilities throughout West Virginia, one of the poorest and most rural states in the country. Participating treatment providers and study staff at West Virginia University School of Medicine (WVU) will recruit patients and, after obtaining informed consent, administer a baseline self-report questionnaire (SRQ) and then randomize patients to 1 of 3 treatment arms with equal allocation: ADM only, ADM + self-guided i-CBT, and ADM + guided i-CBT. Follow-up SRQs will be administered 2, 4, 8, 13, 16, 26, 39, and 52 weeks after randomization. The trial has two primary objectives: to evaluate aggregate comparative treatment effects across the 3 arms and to estimate heterogeneity of treatment effects (HTE). The primary outcome will be episode remission based on a modified version of the patient-centered Remission from Depression Questionnaire (RDQ). The sample was powered to detect predictors of HTE that would increase the proportional remission rate by 20% by optimally assigning individuals as opposed to randomly assigning them into three treatment groups of equal size. Aggregate comparative treatment effects will be estimated using intent-to-treat analysis methods. Cumulative inverse probability weights will be used to deal with loss to follow-up. A wide range of self-report predictors of MDD heterogeneity of treatment effects based on previous studies will be included in the baseline SRQ. A state-of-the-art ensemble machine learning method will be used to estimate HTE. DISCUSSION: The study is innovative in using a rich baseline assessment and in having a sample large enough to carry out a well-powered analysis of heterogeneity of treatment effects. We anticipate finding that self-guided and guided i-CBT will both improve outcomes compared to ADM only. We also anticipate finding that the comparative advantages of adding i-CBT to ADM will vary significantly across patients. We hope to develop a stable individualized treatment rule that will allow patients and treatment providers to improve aggregate treatment outcomes by deciding collaboratively when ADM treatment should be augmented with i-CBT. TRIAL REGISTRATION: ClinicalTrials.gov NCT04120285 . Registered on October 19, 2019.

Designing mental health promotion campaigns: segmenting U.S. Veteran audiences to address public stigma.

BACKGROUND: Public stigma is a significant deterrent to mental health service use for U.S. veterans. Media campaigns are often used to dispel stigmatizing beliefs and actions. Segmentation is an evidence-based practice for their effective use; however, little data has been published on veteran segments to target with anti-stigma messages. AIMS: This article aims to identify and describe initial typologies of stigmatizing attitudes within a group of U.S. military veterans. METHODS: Telephone-based cross-sectional surveys were conducted with a national random sample of veterans from 2014 to 2016 (N = 2142). Stigma outcomes were measured using a brief, validated instrument used in population-based surveys of public perceptions toward people with mental illness. Cluster analysis was conducted to identify specific groupings along multiple dimensions. RESULTS: A final four-cluster solution was identified among veterans with distinct patterns of attitudes toward mental illness and include: 1) the undecided, 2) the influencer, 3) the ambivalent, and 4) the potential ally. Several strategies were also identified for designing anti-stigma messaging toward these segments. CONCLUSIONS: This research demonstrates veterans can be segmented by attitudes to target with anti-stigma campaign messages.

Trends in comorbid opioid and stimulant use disorders among Veterans receiving care from the Veterans Health Administration, 2005-2019.

BACKGROUND: Identifying solutions to the continued rise in overdose deaths is a public health priority. However, there is evidence of change in recent substance type associated with morbidity and mortality. To better understand the continued rise in overdose deaths, in particular those attributed to opioid and stimulant use disorders, increased knowledge of patterns of use is needed. METHODS: Retrospective cohort study of Veterans diagnosed with an opioid or stimulant use disorder between 2005 and 2019. The outcome of interest was diagnosis of substance use disorders, specifically examining combinations of opioid and stimulant use disorders among this population. RESULTS: A total of 1932,188 Veterans were diagnosed with at least one substance use disorder (SUD) during the study period, 2005 through 2019. While the annual prevalence of opioid use disorder (OUD) diagnoses increased more than 155%, OUD diagnoses absent of any other SUD diagnosis increased by an average of 6.9% (95% CI, 6.4, 7.5) per year between 2005 and 2019. Between 2011 and 2019, diagnoses of co-morbid methamphetamine use disorder (MUD) and OUD increased at a higher rate than other SUD combinations. CONCLUSIONS: The prevalence of comorbid SUD, in particular co-occurring opioid and methamphetamine use disorder, increased at a higher rate than other combinations between 2005 and 2019. These findings underscore the urgent need to offer patients a combination of evidence-based treatments for each co-morbid SUD, such MOUD and contingency management for persons with comorbid opioid and methamphetamine use disorders.

Are Veterans Getting Their Preferred Depression Treatment? A National Observational Study in the Veterans Health Administration.

BACKGROUND: Physician responsiveness to patient preferences for depression treatment may improve treatment adherence and clinical outcomes. OBJECTIVE: To examine associations of patient treatment preferences with types of depression treatment received and treatment adherence among Veterans initiating depression treatment. DESIGN: Patient self-report surveys at treatment initiation linked to medical records. SETTING: Veterans Health Administration (VA) clinics nationally, 2018-2020. PARTICIPANTS: A total of 2582 patients (76.7% male, mean age 48.7 years, 62.3% Non-Hispanic White) MAIN MEASURES: Patient self-reported preferences for medication and psychotherapy on 0-10 self-anchoring visual analog scales (0="completely unwilling"; 10="completely willing"). Treatment receipt and adherence (refilling medications; attending 3+ psychotherapy sessions) over 3 months. Logistic regression models controlled for socio-demographics and geographic variables. KEY RESULTS: More patients reported strong preferences (10/10) for psychotherapy than medication (51.2% versus 36.7%, McNemar χ21=175.3, p<0.001). A total of 32.1% of patients who preferred (7-10/10) medication and 21.8% who preferred psychotherapy did not receive these treatments. Patients who strongly preferred medication were substantially more likely to receive medication than those who had strong negative preferences (odds ratios [OR]=17.5; 95% confidence interval [CI]=12.5-24.5). Compared with patients who had strong negative psychotherapy preferences, those with strong psychotherapy preferences were about twice as likely to receive psychotherapy (OR=1.9; 95% CI=1.0-3.5). Patients who strongly preferred psychotherapy were more likely to adhere to psychotherapy than those with strong negative preferences (OR=3.3; 95% CI=1.4-7.4). Treatment preferences were not associated with medication or combined treatment adherence. Patients in primary care settings had lower odds of receiving (but not adhering to) psychotherapy than patients in specialty mental health settings. Depression severity was not associated with treatment receipt or adherence. CONCLUSIONS: Mismatches between treatment preferences and treatment type received were common and associated with worse treatment adherence for psychotherapy. Future research could examine ways to decrease mismatch between patient preferences and treatments received and potential effects on patient outcomes.

Mental Disorders, Gun Ownership, and Gun Carrying Among Soldiers After Leaving the Army, 2016-2019.

Objectives. To examine associations of current mental and substance use disorders with self-reported gun ownership and carrying among recently separated US Army soldiers. Veterans have high rates of both gun ownership and mental disorders, the conjunction of which might contribute to the high suicide rate in this group. Methods. Cross-sectional survey data were collected in 2018-2019 from 5682 recently separated personnel who took part in the Army Study to Assess Risk and Resilience in Servicemembers. Validated measures assessed recent mood, anxiety, substance use, and externalizing disorders. Logistic regression models examined associations of sociodemographic characteristics, service characteristics, and mental disorders with gun ownership and carrying. Results. Of the participants, 50% reported gun ownership. About half of owners reported carrying some or most of the time. Mental disorders were not associated significantly with gun ownership. However, among gun owners, major depressive disorder, panic disorder, posttraumatic stress disorder, and intermittent explosive disorder were associated with significantly elevated odds of carrying at least some of the time. Conclusions. Mental disorders are not associated with gun ownership among recently separated Army personnel, but some mental disorders are associated with carrying among gun owners. (Am J Public Health. 2021;111(10):1855-1864. https://doi.org/10.2105/AJPH.2021.306420).

The association of pre-war medical conditions to Gulf War Illness.

AIMS: Gulf War Illness (GWI) remains a significant health concern for many veterans. The relation of pre-war health conditions and symptoms to GWI could aid in developing a more accurate case definition of GWI. The objective of this study was to investigate pre-war predictors of GWI in a population-based sample of Gulf War veterans using two definitions of GWI. MAIN METHODS: Data come from the 1995-1997 National Health Survey of Persian Gulf War Era Veterans, a survey of a representative sample of deployed and non-deployed US veterans. Using two definitions of GWI (CDC/Kansas and a newly developed 3-domain definition), we conducted a series of multivariable logistic regression analyses to assess the associations of demographic, lifestyle factors, and pre-war medical conditions and symptoms to subsequent GWI. KEY FINDINGS: All pre-war symptom predictor domains were significantly and positively associated with GWI using a new 3-domain definition with aORs for individual domains ranging from 2.17 (95% CI = 1.99-2.38) for dermatologic conditions to 3.06 (95% CI = 2.78-3.37) for neurological conditions. All symptom predictor domains were associated with significantly increased likelihood of GWI using the CDC/Kansas definition, with aORs ranging from 2.54 (95% CI = 2.31-2.81) for inflammatory conditions to 3.22 (95% CI = 2.94-3.55) for neurological conditions. These estimates were attenuated but remained significant after inclusion of all significant symptom predictor domains. SIGNIFICANCE: Results from this study suggest that demographic/lifestyle factors and pre-war medical conditions are strong predictors of GWI. Additional research is needed to confirm these findings, and to clarify the unique characteristics of this common, but still poorly understood illness.

Comorbid mental disorders, depression symptom severity, and role impairment among Veterans initiating depression treatment through the Veterans Health Administration.

BACKGROUND: Psychiatric comorbidities may complicate depression treatment by being associated with increased role impairments. However, depression symptom severity might account for these associations. Understanding the independent associations of depression severity and comorbidity with impairments could help in treatment planning. This is especially true for depressed Veterans, who have high psychiatric comorbidity rates. METHODS: 2,610 Veterans beginning major depression treatment at the Veterans Health Administration (VHA) were administered a baseline self-report survey that screened for diverse psychiatric comorbidities and assessed depression severity and role impairments. Logistic and generalized linear regression models estimated univariable and multivariable associations of depression severity and comorbidities with impairments. Population attributable risk proportions (PARPs) estimated the relative importance of depression severity and comorbidities in accounting for role impairments. RESULTS: Nearly all patients (97.8%) screened positive for at least one comorbidity and half (49.8%) for 4+ comorbidities. The most common positive screens were for generalized anxiety disorder (80.2%), posttraumatic stress disorder (77.9%), and panic/phobia (77.4%). Depression severity and comorbidities were significantly and additively associated with impairments in multivariable models. Associations were attenuated much less for depression severity than for comorbidities in multivariable versus univariable models. PARPs indicated that 15-60% of role impairments were attributable to depression severity and 5-32% to comorbidities. LIMITATIONS: The screening scales could have over-estimated comorbidity prevalence. The cross-sectional observational design cannot determine either temporal or causal priorities. CONCLUSIONS: Although positive screens for psychiatric comorbidity are pervasive among depressed VHA patients, depression severity accounts for most of the associations of these comorbidities with role impairments.

Treatment Differences in Primary and Specialty Settings in Veterans with Major Depression.

INTRODUCTION: The Veterans Health Administration (VHA) supports the nation's largest primary care-mental health integration (PC-MHI) collaborative care model to increase treatment of mild to moderate common mental disorders in primary care (PC) and refer more severe-complex cases to specialty mental health (SMH) settings. It is unclear how this treatment assignment works in practice. METHODS: Patients (n = 2610) who sought incident episode VHA treatment for depression completed a baseline self-report questionnaire about depression severity-complexity. Administrative data were used to determine settings and types of treatment during the next 30 days. RESULTS: Thirty-four percent (34.2%) of depressed patients received treatment in PC settings, 65.8% in SMH settings. PC patients had less severe and fewer comorbid depressive episodes. Patients with lowest severity and/or complexity were most likely to receive PC antidepressant medication treatment; those with highest severity and/or complexity were most likely to receive combined treatment in SMH settings. Assignment of patients across settings and types of treatment was stronger than found in previous civilian studies but less pronounced than expected (cross-validated AUC = 0.50-0.68). DISCUSSION: By expanding access to evidence-based treatments, VHA's PC-MHI increases consistency of treatment assignment. Reasons for assignment being less pronounced than expected and implications for treatment response will require continued study.

Invited Commentary: New Directions in Machine Learning Analyses of Administrative Data to Prevent Suicide-Related Behaviors.

This issue contains a thoughtful report by Gradus et al. (Am J Epidemiol. 2021;190(12):2517-2527) on a machine learning analysis of administrative variables to predict suicide attempts over 2 decades throughout Denmark. This is one of numerous recent studies that document strong concentration of risk of suicide-related behaviors among patients with high scores on machine learning models. The clear exposition of Gradus et al. provides an opportunity to review major challenges in developing, interpreting, and using such models: defining appropriate controls and time horizons, selecting comprehensive predictors, dealing with imbalanced outcomes, choosing classifiers, tuning hyperparameters, evaluating predictor variable importance, and evaluating operating characteristics. We close by calling for machine-learning research into suicide-related behaviors to move beyond merely demonstrating significant prediction-this is by now well-established-and to focus instead on using such models to target specific preventive interventions and to develop individualized treatment rules that can be used to help guide clinical decisions to address the growing problems of suicide attempts, suicide deaths, and other injuries and deaths in the same spectrum.

Causes of death among U.S. Veterans with a prior nonfatal opioid overdose.

BACKGROUND: For over a decade, there has been a surge in opioid-related morbidity and mortality among Veterans. To better understand the impact of the growing epidemic, it is important to identify the cause-specific mortality rates among Veterans with a prior nonfatal opioid overdose. METHODS: We followed 8370 Veterans who received medical care for a nonfatal opioid overdose between 2011 through 2015.Mortality records were linked to clinical records from the Veterans Health Administration (VHA). We compared the mortality rates among those with a nonfatal opioid overdose to a 5 % stratified random sample of patients accessing services during the same time period. SMRs were calculated using age-adjusted cause-specific mortality rates for the l U.S. population obtained from the Centers for Disease Control and Prevention's Wide-Ranging Online Data for Epidemiologic Research (CDC WONDER). RESULTS: The crude mortality for Veterans with a history of a nonfatal overdose was 370.6 per 10,000 person years. Those with a prior nonfatal overdose had a higher risk of substance-related mortality (aHR [adjusted Hazard Ratio] 5.0), including a higher risk of death from drugs (aHR 6.9) and alcohol (aHR 2.7). Similarly, cause-specific mortalities assessed between Veterans and the U.S. population, SMRs were also highest for deaths associated with substances (114.0). CONCLUSION: Veterans with a prior nonfatal overdose experienced substantially higher mortality rates compared to other Veterans or the general U.S. POPULATION: Causes of death related to substance use and mental health were significantly higher than other causes of death, highlighting the importance of integrated treatment and substance use services.

Response Variations to Survey Items About Firearms in the 2004 and 2017 Behavioral Risk Factor Surveillance System.

PURPOSE: The aim of this investigation was to document the prevalence and correlates of refusing to answer a US federal health survey item about firearms in the household. DESIGN: The cross-sectional analysis was conducted with 2004 and 2017 Behavioral Risk Factor Surveillance System (BRFSS) survey data from Texas, Oregon, Idaho, California, Kansas, and Utah states whose surveys included items about firearms in the household. PARTICIPANTS: Probability-based samples of adults over the age of 18 (n = 34 488 in 2017 BRFSS; n = 33 136 in 2004 BRFSS). MEASURES: Dichotomized measure of whether respondents answered versus refused to answer "Are any firearms now kept in or around your home?" ANALYSIS: Weighted multiple logistic regression was used to assess how sociodemographic and health-related characteristics were associated with item refusal. RESULTS: Approximately 1.8% (95% CI: 1.6-2.1) of respondents in 2004 and 3.9% (95% CI: 3.4-4.5) of respondents in 2017 sample refused the firearms item (P < .01). Men were more likely than women (2004: adjusted odds ratio [aOR] = 1.81, 95% CI: 1.24-2.62; 2017: aOR = 1.60, 95% CI = 1.17-2.18) and Latino/a respondents were less likely than white respondents (2004: aOR = 0.24, 95% CI: 0.10-0.60; 2017: aOR = 0.21, 95% CI: 0.13-0.34) to refuse the firearms question. In 2004, refusal was more likely among older than younger respondents, but in 2017, age was not associated with refusal. CONCLUSIONS: Refusal to firearm-related survey items along sociodemographic characteristics warrants further research. Community-informed strategies (eg, focus groups, cognitive testing, in-depth interviews) could improve the context and wording of firearm-related items to maximize response to these items in public health surveys.

The next wave? Mental health comorbidities and patients with substance use disorders in under-resourced and rural areas.

The rapid spread of the coronavirus disease (COVID-19) has impacted the lives of millions around the globe. The COVID-19 pandemic has caused increasing concern among treatment professionals about mental health and risky substance use, especially among those who are struggling with a substance use disorder (SUD). The pandemic's impact on those with an SUD may be heightened in vulnerable communities, such as those living in under-resourced and rural areas. Despite policies loosening restrictions on treatment requirements, unintended mental health consequences may arise among this population. We discuss challenges that under-resourced areas face and propose strategies that may improve outcomes for those seeking treatment for SUDs in these areas.