A Hierarchical Multilevel Inference Framework for Structural Cardiovascular Risk Modeling: County-Scale Analysis of Cardiovascular Mortality in Ohio and Pennsylvania (1999-2020)

Cardiovascular mortality is shaped by interacting demographic, environmental, and structural processes operating across multiple spatial scales. Conventional epidemiologic analyses often rely on aggregate summaries or single-model formulations that obscure hierarchical variation and contextual heterogeneity. We present a reproducible multilevel statistical inference framework integrating Normal (age-adjusted), Poisson (count-based), and population-offset Poisson models to quantify cardiovascular mortality across nested geographic units while separating demographic effects from structural variation. The framework was applied to county-level mortality data from Ohio and Pennsylvania (1999-2020) using MLwiN hierarchical models for seven cardiovascular disease (CVD) subtypes. Fixed effects included year, sex, race, PM2.5, and O3, while county-level random intercepts captured spatial heterogeneity. Complete model equations are provided in the Supplementary Material. The framework reveals complementary perspectives on cardiovascular risk unavailable from a single model. Age-adjusted mortality declined more rapidly in Pennsylvania than Ohio, whereas Poisson models identified post-2010 stagnation or reversal for several CVD subtypes. Black populations experienced elevated mortality risks, males exhibited higher mortality than females, and PM2.5 showed stronger associations with ischemic and hypertensive mortality in Pennsylvania. Population-offset models reduced unexplained variance while preserving county-level structural disparities. Beyond cardiovascular epidemiology, this work introduces a generalizable hierarchical statistical framework for structurally nested health systems. The methodology provides a scalable foundation for disease surveillance, environmental health assessment, health equity research, reproducible statistical analysis, and AI-assisted scientific inference.

Source: arXiv:2607.06916v1 - http://arxiv.org/abs/2607.06916v1 PDF: https://arxiv.org/pdf/2607.06916v1 Original Link: http://arxiv.org/abs/2607.06916v1