A Bayesian Multiscale Integrated Abundance Model for Estimating Latent Opioid Misuse Prevalence from Spatially Misaligned Data

2026-10-05

AI Summary

This study addresses the estimation bias in opioid misuse prevalence arising from misaligned geographic units in surveillance data by proposing a Bayesian multiscale integrated abundance model based on atomic spatial units. The method jointly analyzes indirect indicators across varying geographic scales, employing Fisher's noncentral hypergeometric distribution for modeling. To enable scalable inference, a two-stage composite Markov chain Monte Carlo algorithm combined with parallel computing techniques is developed. Empirical results demonstrate that this framework substantially reduces estimation bias and error, accurately identifying high-risk sub-county local areas within Ohio. Ultimately, this work provides robust methodological support for cross-scale public health surveillance.

Abstract

Estimating small area prevalence of opioid misuse is critical for targeting public health interventions, yet direct measures are unavailable and related surveillance data are often reported on misaligned areal units. We propose a Bayesian Multiscale Integrated Abundance (MIA) model for estimating latent opioid misuse prevalence by jointly analyzing multiple indirect surveillance indicators observed on different geographic supports. The model extends existing integrated abundance models by representing all source geographies through a common set of atomic spatial units formed by the intersections of observed areal supports. Latent prevalence at the atomic level is modeled using a Fisher noncentral hypergeometric distribution, which preserves county-level prevalence totals while respecting local population constraints. To enable scalable inference, we develop a two-stage compositional Markov chain Monte Carlo algorithm that combines customized sampling strategies and parallel computing. Simulation studies show the proposed approach reduces bias and root mean squared error relative to common downscaling methods. We apply the model to Ohio data from 2010-2023, integrating state-level survey estimates, county-level counts of opioid overdose deaths and treatment admissions, and ZIP code tabulation area-level counts of emergency medical services naloxone administrations. Results reveal substantial within-county heterogeneity and identify localized areas of elevated opioid misuse prevalence that would be missed by county-level analyses.

Problem

• opioid misuse prevalence
• small area estimation
• spatially misaligned data
• latent prevalence

Innovation

• Bayesian multiscale model
• spatially misaligned data
• Fisher noncentral hypergeometric distribution
• compositional MCMC
• latent prevalence estimation