Document text
Principal Investigator: Jennifer R Fonda
Organization: VA BOSTON HEALTH CARE SYSTEM
Fiscal Year: 2024
Funding agency: Veterans Affairs
The overall aim of this proposed study is to use machine learning prediction models to evaluate the
multifaceted, additive and multiplicative interactions of known and novel risk factors for opioid use disorder
(OUD) and overdose in Post-9/11 Veterans. The proposed study will also investigate the short- and long-term
impact of the coronavirus disease 2019 (COVID-19) pandemic on the risk of OUD and overdose.
TRAINING PLAN: The CDA-2 training plan will facilitate the applicant’s primary career goal of becoming a
fully funded, independent epidemiologic researcher at the Department of Veterans Affairs (VA), with a focus on
addiction and suicidal behavior. The CDA-2 will provide additional training necessary to lead an independent
program of research investigating the multifaceted sociodemographic, physical, psychological, and behavioral
factors mediating and moderating the risk of addiction and suicidal behavior. The first step of achieving this
goal is to complete the following training aims: 1) gaining expertise in the biological and behavioral basis of
addiction; 2) gaining expertise in the assessment of the problems of TBI and blast exposure, psychiatric
disorders, and suicidal behavior, which is pervasive in this generation of Veterans; 3) gaining expertise in
advanced analytic techniques employed in health data science, including machine learning algorithms; and 4)
professional development to achieve career independence as a VA funded epidemiologic researcher.
RESEARCH DESIGN & METHODS: The proposed study will use Veterans Health Administration (VHA)
electronic medical records to develop models predicting OUD and overdose risk. The sample will include Post-
9/11 Veterans who are aged 18-65, receive care in the VHA, and will have completed the VA primary TBI
screen between October 2007 and February 2020 (n~1,267,000). We will assess the risk of incident and
recurrent OUD and overdose events, as separate outcomes, using machine learning algorithmic models. We
will examine whether overdose was 1) fatal and non-fatal and 2) intentional and unintentional. For Aims 1 and
2, we will examine the risk of OUD and overdose events between October 1, 2007 and February 29, 2020. For
Exploratory Aim 3, we will examine the risk of OUD and overdose events between March 1, 2020 and
September 30, 2025. We will use several machine learning classification-tree modeling approaches, including
classification and regression trees, random forest, and gradient boosting, to develop predictor profiles of OUD
and overdose incorporating important risk factors and interactions. The validity (sensitivity and specificity) and
prediction accuracy (area under the curve) will be assessed for all prediction profile models. OBJECTIVES:
Aim 1: Develop and evaluate the performance of predictor profiles incorporating known and novel risk factors
and interactions for OUD and overdose over proximal (30, 60, and 90 days) and distal (180, 365, 730, 1095
and >1460 days) prediction intervals using machine learning classification algorithms. Hypothesis 1a: The
machine learning algorithms will have high validity and prediction accuracy (e.g., sensitivity and specificity and
area under the curve) >0.8. Hypothesis 1b: Accuracy and predictive ability will be higher in the proximal vs.
distal prediction intervals. Aim 2: Examine gender, race/ethnicity, deployment-related trauma (e.g., TBI and
prevalent psychiatric and substance disorders), and close-blast exposure as moderators of the risk of OUD
and overdose. Hypothesis 2: There will be novel risk factors and differential variable importance impacting the
risk of OUD and overdose within the subgroup-specific predictor profiles. Exploratory Aim 3: Investigate the
short- and long-term impact of the COVID-19 pandemic on the risk of OUD and overdose using machine
learning classification algorithms to develop predictor profiles of known and novel risk factors and interactions.
Hypothesis 3: The COVID-19 pandemic will have both a direct effect on the risk for OUD and overdose and an
indirect effect through the onset or exacerbation of mental health symptoms and psychiatric conditions.
Terms: <Access to Care><Adverse Experience><Adverse event><Afghanistan><Amalgam><Anxiety><Area Under Curve><Behavioral><Biological><Brain Trauma><COVID crisis><COVID epidemic><COVID pandemic><COVID-19 crisis><COVID-19 epidemic><COVID-19 era><COVID-19 global health crisis><COVID-19 global pandemic><COVID-19 health crisis><COVID-19 pandemic><COVID-19 pandemic affected><COVID-19 pandemic consequence><COVID-19 pandemic effects><COVID-19 pandemic impact><COVID-19 pandemic impacted><COVID-19 period><COVID-19 public health crisis><COVID-19 years><Caring><Complex><Computerized Medical Record><Data><Data Bases><Data Science><Databases><Development><Disease><Disorder><Distal><Domestic Violence><Early Intervention><Electronic Medical Record><Epidemiologic Research><Epidemiologic Studies><Epidemiological Studies><Epidemiology><Epidemiology Research><Ethnic Origin><Ethnicity><Event><Funding><Gender><General Population><General Public><Generations><Goals><Health Services Accessibility><High Prevalence><History><Individual><Intervention><Intervention Strategies><Investigators><Iraq><Lead><Machine Learning><Measures><Mediating><Mental Depression><Mental Health><Mental Hygiene><Mental disorders><Mental health disorders><Modeling><Opiates><Opioid><Outcome><Overdose><PTSD><Pb element><Performance><Physical distancing><Population><Post-Traumatic Neuroses><Post-Traumatic Stress Disorders><Posttraumatic Neuroses><Predisposition><Psychiatric Disease><Psychiatric Disorder><Psychological Health><Public Health><Race><Races><Recording of previous events><Recurrence><Recurrent><Research><Research Design><Research Methodology><Research Methods><Research Personnel><Researchers><Risk><Risk Assessment><Risk Factors><SARS-CoV-2 epidemic><SARS-CoV-2 global health crisis><SARS-CoV-2 global pandemic><SARS-CoV-2 pandemic><SARS-coronavirus-2 epidemic><SARS-coronavirus-2 pandemic><Sampling><Sensitivity and Specificity><Severe Acute Respiratory Syndrome CoV 2 epidemic><Severe Acute Respiratory Syndrome CoV 2 pandemic><Severe acute respiratory syndrome coronavirus 2 epidemic><Severe acute respiratory syndrome coronavirus 2 pandemic><Social Distance><Study Type><Subgroup><Substance Use Disorder><Susceptibility><Symptoms><Techniques><Testing><Training><Trauma><Traumatic Brain Injury><United States><United States Department of Veterans Affairs><United States Veterans Administration><Veterans><Veterans Administration><Veterans Affairs><Veterans Health Administration><Veterans Health Affairs><Work><access to health services><access to services><access to treatment><accessibility to health services><addiction><addictive disorder><advanced analytics><aged><availability of services><biologic><blast exposure><care access><career><chronic pain><classification algorithm><classification trees><cohort><computer based prediction><coronavirus disease 2019 crisis><coronavirus disease 2019 epidemic><coronavirus disease 2019 global health crisis><coronavirus disease 2019 global pandemic><coronavirus disease 2019 health crisis><coronavirus disease 2019 pandemic><coronavirus disease 2019 pandemic consequence><coronavirus disease 2019 pandemic impact><coronavirus disease 2019 public health crisis><coronavirus disease crisis><coronavirus disease epidemic><coronavirus disease pandemic><coronavirus disease-19 global pandemic><coronavirus disease-19 pandemic><data base><depression><developmental><disease risk><disorder risk><effects following the COVID-19 pandemic><epidemiologic><epidemiologic investigation><epidemiological><epidemiology study><exposure to trauma><gradient boosting><health data><health service access><health services availability><heavy metal Pb><heavy metal lead><high risk><high risk group><high risk individual><high risk people><high risk population><histories><impact of the SARS-CoV-2 pandemic><improved><interventional strategy><long term COVID-19 pandemic consequences><long term COVID-19 pandemic effects><long term COVID-19 pandemic impacts><longer term COVID-19 pandemic consequences><longer term COVID-19 pandemic effects><longer term COVID-19 pandemic impacts><machine based learning><machine learned algorithm><machine learning algorithm><machine learning based algorithm><machine learning based classification><machine learning based method><machine learning based prediction model><machine learning based predictive model><machine learning classification><machine learning method><machine learning methodologies><machine learning prediction><machine learning prediction model><mental illness><military veteran><non-medical opioid use><nonmedical opioid use><novel><opiate crisis><opiate misuse><opiate use disorder><opioid crisis><opioid epidemic><opioid misuse><opioid use disorder><overdose risk><pandemic><pandemic disease><post 9/11><post-trauma stress disorder><posttrauma stress disorder><precision medicine><precision-based medicine><predictive modeling><programs><psychiatric co-morbidity><psychiatric comorbidity><psychiatric illness><psychologic><psychological><psychological disorder><racial><racial background><racial origin><random forest><regression trees><research and methods><service availability><severe acute respiratory syndrome coronavirus 2 global health crisis><severe acute respiratory syndrome coronavirus 2 global pandemic><socio-demographics><sociodemographics><study design><study population><substance use and disorder><suicidal behavior><suicide behavior><targeted drug therapy><targeted drug treatments><targeted therapeutic><targeted therapeutic agents><targeted therapy><targeted treatment><trauma exposure><traumatic brain damage><traumatic neurosis><treatment access><veteran population>