Environmental determinants predicting population vulnerability to high yellow fever incidence

Abstract

Yellow fever (YF) is an endemic mosquito-borne disease in Brazil, though many locations have not observed cases in recent decades. Some locations with low disease burden may resemble locations with higher disease burden through environmental and ecohydrological characteristics, which are known to impact YF burden, motivating increased or continued prevention measures such as vaccination, mosquito control or surveillance. This study aimed to use environmental characteristics to estimate vulnerability to observing high YF burden among all Brazilian municipalities. Vulnerability was defined in three categories based on yearly incidence between 2000 and 2017: minimal, low and high vulnerability. A cumulative logit model was fit to these categories using environmental and ecohydrological predictors, selecting those that provided the most accurate model fit. Per cent of days with precipitation, mean temperature, biome, population density, elevation, vegetation and nearby disease occurrence were included in best-fitting models. Model results were applied to estimate vulnerability nationwide. Municipalities with highest probability of observing high vulnerability was found in the North and Central-West (2000-2016) as well as the Southeast (2017) regions. Results of this study serve to identify specific locations to prioritize new or ongoing surveillance and prevention of YF based on underlying ecohydrological conditions.

Keywords: cumulative logit model; environment; vulnerability; yellow fever.

Figure 1.

Time series of total YF cases in Brazil: (a) yearly cases, 2000–2017; (b) monthly cases, 2000–2016; (c) monthly cases, 2017.

Figure 2.

Municipalities of Brazil where any YF cases or dengue cases were seen between January 2000 and March 2018. The highlighted municipalities' vulnerability and environmental data were used in model fitting for both time periods.

Figure 3.

Estimated probabilities associated with vulnerability categories for YF burden in Brazil. Estimates for 2000–2016: (a) minimal, (b) low and (c) high vulnerability as well as 2017: (d) minimal, (e) low and (f) high vulnerability categories were predicted with a cumulative logit model using environmental predictors. Scales across graphs are inconsistent to show spatial heterogeneity within predictions for each category; maps using the same colour scale are found in the electronic supplementary material, figure S3.

Figure 4.

First- and second-order Sobol indices for model predictors for the models fit using 2000–2016 (left column) and 2017 (right column) data. Higher values of Sobol indices represent greater relative influence in model prediction as a function of their independent variability and joint variability for first- and second-order index, respectively.