Building a macrosystems ecology framework to identify links between environmental and human health: a random forest modelling approach.

Published online
29 Mar 2023
Content type
Journal article
Journal title
People and Nature
DOI
10.1002/pan3.10427

Author(s)
Walls, F. N. & McGarvey, D. J.
Contact email(s)
wallsfn@vcu.edu

Publication language
English
Location
USA

Abstract

Anthropogenic activities that degrade natural ecosystems may also impact human health. However, research on the links between human and environmental health has most often been conducted at small scales (e.g. individual cities) and cannot easily be extrapolated to larger scales. We created a macrosystems ecology framework to identify associations between human and environmental health by combining human mortality and socioeconomic data for the conterminous United States with spatially aligned data on the physicochemical characteristics of river basins. Principal component analysis was first used to reduce a list of 596 environmental variables to a subset of 64 environmental covariates, representing six main environmental themes (climate, geology, hydrology, land use, river basin morphology and pollution). Independent, spatially aligned information was then obtained for 12 socioeconomic covariates. Random forest modelling was used to predict age-adjusted mortality rate as a function of the environmental and socioeconomic covariates. An independent data subset (random 75:25 model building vs. testing split) was also used for model validation. The coefficient of determination between predicted and observed mortality rates was 0.76 for the validation data. Furthermore, model residuals (predicted - observed mortality) were centered near zero and normally distributed (1 SD = 62.26), suggesting high model accuracy and precision. Socioeconomic covariates were consistently the most influential predictors of mortality rate. Smoking, food insecurity, and lack of physical activity were particularly important. However, environmental covariates accounted for 5 of the 10 strongest predictors overall, with air temperature and precipitation being most influential among environmental variables. This proof-of-concept study demonstrates the utility of a modelling framework that combines environmental and human health data at macroscales. We suggest that further application of macrosystems ecology tools will improve the capacity to anticipate human health responses to ongoing environmental change. Read the free Plain Language Summary for this article on the Journal blog.

Key words