Creating Compact Regions of Social Determinants of Health

TL;DR

This paper compares multiple regionalization algorithms on large-scale social determinant of health data, evaluating their scalability, geographic metrics, and performance in real-world applications.

Contribution

It provides a comprehensive comparison of state-of-the-art regionalization methods on large datasets, including new geographic metrics and memory analysis.

Findings

Agglomerative Clustering and SKATER perform well on large data.

Regionalization methods differ significantly in scalability and geographic accuracy.

Unconstrained K-Means is less effective than constrained methods for health data segmentation.

Abstract

Regionalization is the act of breaking a dataset into contiguous homogeneous regions that are heterogeneous from each other. Many different algorithms exist for performing regionalization; however, using these algorithms on large real world data sets have only become feasible in terms of compute power in recent years. Very few studies have been done comparing different regionalization methods, and those that do lack analysis in memory, scalability, geographic metrics, and large-scale real-world applications. This study compares state-of-the-art regionalization methods, namely, Agglomerative Clustering, SKATER, REDCAP, AZP, and Max-P-Regions using real world social determinant of health (SDOH) data. The scale of real world SDOH data, up to 1 million data points in this study, not only compares the algorithms over different data sets but provides a stress test for each individual regionalization algorithm, most of which have never been run on such scales previously. We use several new geographic metrics to compare algorithms as well as perform a comparative memory analysis. The prevailing regionalization method is then compared with unconstrained K-Means clustering on their ability to separate real health data in Virginia and Washington DC.