Volume 42, August 2022, 100522Highlights•

Determinants of neighborhood-level cancer risks are less well-understood.

•

We developed a new large-scale neighborhood dataset for all US census tracts.

•

We used a novel machine learning approach to select correlates of cancer prevalence.

•

We investigated correlates from four major domains of the neighborhood environment.

•

We found key demographic, healthcare access, and environmental predictors of cancer prevalence.

Abstract

Preventive measures, health behaviors, environmental exposures, and sociodemographic characteristics affect individual-level cancer risks. It is unclear how they influence neighborhood-level cancer risks. We developed a large-scale neighborhood health dataset for 72,337 census tracts in the United States by combining data from three publicly available sources. We used Bayesian additive regression trees to identify the most important predictors of tract-level cancer prevalence among adults (age ≥18 years), and examined their impact on cancer prevalence using partial dependence plots. The five most important census tract-level correlates of cancer prevalence were the proportion of population who were aged 65 years and older, had routine checkup and were non-Hispanic White, the proportion of houses built before 1960, and the proportion of population living below the poverty line. The identified predictors of neighborhood-level cancer prevalence may inform public health practitioners and policymakers to prioritize the improvement of environmental and neighborhood factors in reducing the cancer burden.

Keywords

Cancer prevalence

Neighborhood

Machine learning

Variable selection

AbbreviationsCenters for Disease Control and Prevention

(CDC)

Environmental Protection Agency

(EPA)

Population Level Analysis and Community Estimates

(PLACES)

Behavioral Risk Factor Surveillance System

(BRFSS)

Bayesian additive regression trees

(BART)

variable inclusion proportions

(VIP)

View full text

© 2022 Elsevier Ltd. All rights reserved.