CITATION.cff

cff-version: 1.2.0
message: "If you use this software, please cite it as described below."
authors:
  - family-names: "O'Dea"
    given-names: "Ryan"
    orcid: "0009-0000-0103-9546"
    affiliation: "Boston Medical Center, Department of Infectious Diseases"
  - family-names: "Linas"
    given-names: "Benjamin"
    affiliation: "Boston Medical Center, Department of Infectious Diseases; Boston University School of Public Health"
  - family-names: "Wang"
    given-names: "Jianing (Jenny)"
    affiliation: "Massachusetts General Hospital; Harvard Medical School"
  - family-names: "Barocas"
    given-names: "Josh"
    affiliation: "University of Colorado School of Medicine-Divisions of General Internal Medicine and Infectious Diseases"
  - family-names: "White"
    given-names: "Laura"
    affiliation: "Boston University School of Public Health"
title: "Estimation of Opioid Use Disorder Prevalence Under Unique Data Scenarios: A Simulation Study"
version: 1.0.0
date-published: 2024-10-08
keywords:
  - "Opioid Use Disorder"
  - "Prevalence Estimation"
  - "Simulation Study"
  - "Capture Recapture"
  - "CRC"
  - "Public Health"
abstract: "To effectively tackle the overdose crisis, a nuanced understanding of Opioid Use Disorder (OUD) 
          prevalence is crucial, both broadly and within targeted cohorts. Healthcare interactions provide 
          estimates but may overlook those outside the healthcare system, leading to underestimation. 
          Capture-recapture (CRC) analysis is valuable in estimating prevalence by addressing underreporting in 
          surveillance. Conventionally, a stepwise model selection process (MSP) is employed to identify the
          model that best fits the data. However, the MSP in estimating group-stratified prevalence is less explored, 
          especially with sparse data. This study uses simulations to investigate different MSPs for selecting 
          conventional log-linear CRC models, with a focus on their ability to precisely estimate strata prevalence.
          Using data from the Massachusetts Public Health Data Warehouse, we generated synthetic populations stratified by 
          multiple data sources and demographic groups: age, sex, and race. We simulated observation patterns 
          across multiple data sources, accounting for scenarios with small observed counts. Data were tabulated to 
          reflect varying source and strata combinations. We examined Poisson and Negative Binomial distributions within 
          log-linear models, incorporating interaction terms to adjust for source dependency. Model selection efficacy was 
          benchmarked by comparing stepwise, global AIC-based, and threshold-specific interaction methods 
          against the simulated truth.
          As more demographic information was added, Poisson log-linear models selected through forward-stepwise 
          processes generally outperformed their Negative Binomial counterparts, estimating prevalence within <0.001% 
          discrepancy from true prevalence. In scenarios with data suppression, Poisson models selected through a 
          forward-stepwise approach proved most accurate, within 0.78% discrepancy. CRC is a valuable method for 
          estimating the hidden prevalence of OUD, but its effectiveness depends on selecting 
          appropriate models based on available data. Through contrasting different approaches, 
          we highlight the estimation process for strata-specific prevalence and interpret strengths 
          and limitations of common model selection strategies, enhancing the precision of OUD prevalence 
          assessments for uniquely stratified data."
license: "MIT"