Research
My research agenda is grounded in a commitment to health equity and the recognition that biological, social, spatial, political, economic, and environmental forces are core to the production and distribution of health outcomes. I view health geography as not merely the study of disease patterns but as a critical framework to interrogate structural inequalities. My work spans three intersecting themes. First, population data enrichment: I combine various datasets using spatial joins, fuzzy matching, microsimulation, and table linkage. These techniques support the construction of rich population cohorts that can be used to explore spatial and temporal health trends over the life course. Second, statistical and spatial analysis (of big data): I apply cross-sectional and longitudinal analyses to characterise patterns of disease distribution, environmental exposures, and health service utilisation. My recent projects use multi-level modelling and geographically weighted regression to investigate the effects of place-based attributes on multimorbidity and chronic conditions. Third, machine learning for health research: I implement various supervised and unsupervised machine learning approaches to discover non-linear interactions and subtle patterns in large datasets. These methods augment theory-building and inform predictive modelling approaches. I code primarily in R and Python to ensure replicability and efficiency.