Latent Spatial Heterogeneity in U.S. Cancer Mortality: A Multi-Site Clustering and Spatial Autocorrelation Analysis

TL;DR

This study analyzes spatial patterns and clusters of cancer mortality across U.S. states from 1999 to 2021, identifying regional disparities and hotspots to inform targeted prevention strategies.

Contribution

It introduces a comprehensive spatial analysis framework combining clustering and autocorrelation methods to characterize regional cancer mortality patterns in the U.S.

Findings

Identification of distinct regional cancer mortality clusters

Detection of significant spatial autocorrelation in cancer death rates

Mapping of cancer-specific hotspots and cold spots

Abstract

This research set out to explore and delineate spatial patterns and mortality distributions for various cancer types across U.S. states between 1999 and 2021. The aim was to uncover region-specific cancer burdens and inform geographically targeted prevention efforts. We analyzed state-level cancer mortality records sourced from the CDC WONDER platform, concentrating on cancer sites consistently reported across the 48 contiguous states and Washington, D.C., excluding Hawaii, Alaska, and Puerto Rico. Multivariate clustering using Mahalanobis distance grouped states according to similarities in mortality profiles. Spatial autocorrelation was examined for each cancer type using both Global Moran's I and Local Indicators of Spatial Association (LISA). Additionally, the Getis-Ord statistic was applied to detect cancer-specific hotspots and cold spots.