MedML: Fusing medical knowledge and machine learning models for early pediatric COVID-19 hospitalization and severity prediction.

The COVID-19 pandemic has caused devastating economic and social disruption. This has led to a nationwide call for models to predict hospitalization and severe illness in patients with COVID-19 to inform the distribution of limited healthcare resources. To address this challenge, we propose a machine learning model, MedML, to conduct the hospitalization and severity prediction for the pediatric population using electronic health records. MedML extracts the most predictive features based on medical knowledge and propensity scores from over 6 million medical concepts and incorporates the inter-feature relationships in medical knowledge graphs via graph neural networks. We evaluate MedML on the National Cohort Collaborative (N3C) dataset. MedML achieves up to a 7% higher AUROC and 14% higher AUPRC compared to the best baseline machine learning models. MedML is a new machine learnig framework to incorporate clinical domain knowledge and is more predictive and explainable than current data-driven methods.

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.

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.

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.

A randomized controlled trial of public messaging to promote safe firearm storage among U.S. military veterans.

BACKGROUND: The objectives of this study were to determine whether short-term exposure to firearm safety messaging significantly improved (1) firearm storage practices, and (2) attitudes of safe firearm storage behaviors among U.S. veterans, a group at elevated risk for firearm suicide. DESIGN: A three-arm, parallel-group RCT was conducted online in the U.S. nationwide from December 2015 to January 2016. SETTING: A national random sample of U.S. veterans (N = 358) was recruited from the GfK KnowledgePanel, a probability-based internet panel representative of U.S. adults. All study activities were administered online over a three-week study period. INTERVENTION: Participants were randomized and exposed three times (once per week) to either (a) firearm safety message only (n = 115); (b) firearm safety and mental health promotion messages (n = 133); or (c) active control group exposed to mental health promotion message only (n = 110). Each message was less than two minutes long. MEASURES: Assessments were completed at baseline (pre-randomization) and at end-of-trial. Changes in awareness of risk for injuries, attitudes/beliefs related to safe storage practices, behavioral intentions, and storage practices were measured using self-reported surveys. Linear mixed effect models with weighted generalized estimating equations were used to test for exposure effects. Analyses were conducted February 2018. RESULTS: Analyses restricted to those with baseline firearm access (n = 195) identified no significant changes for intentions or safe storage practices across exposure groups. At baseline, participants' attitudes and beliefs were generally supportive of safe firearm storage. The Firearm Safety message yielded small increases in agreement with the concept that secure storage is "important during emotional or stressful times" (0.36; 95% CI = 0.08, 0.64). Other significant changes in awareness and beliefs were found, but across all study conditions. CONCLUSION: Results reinforce the critical need for considerable research and testing prior to the widespread implementation of public messages to increase the likelihood for desired exposure effects.

Opioid-Related Outcomes in West Virginia, 2008-2016.

OBJECTIVES: To examine opioid-related outcomes by using hospitalization and mortality data as an indicator of the current opioid crisis in West Virginia. METHODS: We used data from the West Virginia University Medicine health care system to examine the trend in opioid overdoses and percentage of patients with a repeat overdose from 2008 to 2016. We obtained the opioid overdose death rate for the state from Centers for Disease Control and Prevention WONDER (Wide-ranging ONline Data for Epidemiologic Research) mortality data for 2008 to 2016. RESULTS: The hospitalization rate for opioid overdoses increased (13%) on average each year in a similar fashion to the opioid overdose death rate for the state (12%) between 2008 and 2016. During the same time, the percentage of patients with a repeat opioid overdose increased annually by 13% on average. CONCLUSIONS: There continues to be a surge of opioid overdoses in West Virginia. These findings suggest a need to amplify comprehensive prevention and treatment efforts throughout the state. Public health initiatives to reduce the morbidity and mortality associated with overdoses should consider how the changes in potency may be influencing these outcomes.

The Use of Theory-Based Formative Research to Design Suicide Prevention Messaging for U.S. Veterans in Midlife.

BACKGROUND: Communication campaigns offer a viable mechanism to promote suicide prevention and reinforce mental health for U.S. veterans in midlife, a group with a high suicide burden. However, little empirical investigation of this type of messaging has been conducted, with formative campaign research conspicuously missing from the limited literature. AIMS: Using the theory of planned behavior as a guide, formative research was conducted to inform the design of suicide prevention messaging by (a) describing and measuring several theoretical constructs among our audience and (b) modeling associations between constructs and intentions to seek help for suicidal behaviors and mental health more broadly. METHODS: Telephone-based cross-sectional surveys were collected between 2014 and 2016 from a nationally representative sample of veterans with analyses restricted to those aged between 44 and 65 years ( n = 809). Multiple logistic regression was used to identify significant factors associated with intentions to seek help for either suicidal behaviors or mental health. RESULTS: Perceived behavioral control was one of the largest predictors of intentions to seek help for both suicidal behaviors and mental health concerns. Descriptive norms were also significantly associated with suicide-related intentions. Data further suggest several types of attitudes (i.e., discordant beliefs, stereotypes) to consider when designing messages for this group. DISCUSSION: This study represents one of the first efforts to document and describe theoretical constructs and their influence on intentions among veterans in midlife to contribute to the development of evidence-based messaging for veterans informed by a conceptual framework. CONCLUSION: Findings have important implications as the use of communication strategies for suicide prevention grows increasingly popular.