How Your Location Relates to Health: Variable Importance and Interpretable Machine Learning for Environmental and Sociodemographic Data

2025-01-03

AI Summary

This study investigates the spatiotemporal heterogeneity of residential environmental and sociodemographic determinants on multiple health outcomes—asthma, hypertension, and anxiety—particularly during the COVID-19 pandemic. Leveraging fine-grained spatiotemporal data from the UK MEDSAT cohort, we develop a novel integrative framework combining interpretable machine learning with spatial statistics: specifically, robust variable importance assessment (via permutation tests and SHAP), generalized additive models (GAMs), and multiscale geographically weighted regression (MGWR). This enables simultaneous identification of global associations and modeling of local spatial heterogeneity. Results reveal NO₂ as a significant global risk factor across all three conditions; occupational status, marital status, and vegetation cover exhibit outcome-specific effects; and the health impacts of air pollution and solar radiation display pronounced regional variation—systematically shifting during the pandemic. The framework establishes a new, interpretable, and generalizable paradigm for spatiotemporal causal inference in environmental epidemiology.

Technology Category

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

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Health outcomes depend on complex environmental and sociodemographic factors whose effects change over location and time. Only recently has fine-grained spatial and temporal data become available to study these effects, namely the MEDSAT dataset of English health, environmental, and sociodemographic information. Leveraging this new resource, we use a variety of variable importance techniques to robustly identify the most informative predictors across multiple health outcomes. We then develop an interpretable machine learning framework based on Generalized Additive Models (GAMs) and Multiscale Geographically Weighted Regression (MGWR) to analyze both local and global spatial dependencies of each variable on various health outcomes. Our findings identify NO2 as a global predictor for asthma, hypertension, and anxiety, alongside other outcome-specific predictors related to occupation, marriage, and vegetation. Regional analyses reveal local variations with air pollution and solar radiation, with notable shifts during COVID. This comprehensive approach provides actionable insights for addressing health disparities, and advocates for the integration of interpretable machine learning in public health.

Problem

• Residential Environment
• Population Characteristics
• Health Impact

Innovation

• Interpretable Machine Learning
• Environmental and Demographic Factors
• Health Impact Analysis