Modeling Spatial Heterogeneity in Exposure Buffers and Risk: A Hierarchical Bayesian Approach

2025-09-29

AI Summary

Traditional epidemiological exposure definitions based on fixed-radius circular buffers ignore spatial heterogeneity, leading to biased risk estimates. To address this, we propose the Spatially Varying Buffer Radius (SVBR) method, which—uniquely—models the buffer radius as an unknown spatially varying parameter jointly estimated with the exposure effect. Implemented via a hierarchical Bayesian spatial changepoint model, SVBR enables simultaneous, spatially adaptive estimation of both radius and effect. Inference is conducted using Markov Chain Monte Carlo (MCMC) sampling and integrated into the R package *EpiBuffer*. Simulation studies demonstrate that SVBR significantly outperforms conventional fixed-radius approaches in both parameter estimation accuracy and spatial cluster identification. Applied to prenatal care data from Madagascar, SVBR reveals a positive yet highly spatially heterogeneous association between proximity to health facilities and service utilization. This work breaks the fixed-radius paradigm, establishing a novel, data-driven, spatially explicit framework for exposure modeling.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Place-based epidemiology studies often rely on circular buffers to define "exposure" to spatially distributed risk factors, where the buffer radius represents a threshold beyond which exposure does not influence the outcome of interest. This approach is popular due to its simplicity and alignment with public health policies. However, buffer radii are often chosen relatively arbitrarily and assumed constant across the spatial domain. This may result in suboptimal statistical inference if these modeling choices are incorrect. To address this, we develop SVBR (Spatially-Varying Buffer Radii), a flexible hierarchical Bayesian spatial change points approach that treats buffer radii as unknown parameters and allows both radii and exposure effects to vary spatially. Through simulations, we find that SVBR improves estimation and inference for key model parameters compared to traditional methods. We also apply SVBR to study healthcare access in Madagascar, finding that proximity to healthcare facilities generally increases antenatal care usage, with clear spatial variation in this relationship. By relaxing rigid assumptions about buffer characteristics, our method offers a flexible, data-driven approach to accurately defining exposure and quantifying its impact. The newly developed methods are available in the R package EpiBuffer.

Problem

• Modeling spatial heterogeneity in exposure buffers and risk
• Addressing arbitrary constant buffer radii assumptions
• Allowing spatially varying buffer radii and exposure effects

Innovation

• Hierarchical Bayesian approach models spatially-varying buffer radii
• Treats buffer radii as unknown parameters for flexibility
• Allows both radii and exposure effects to vary spatially