Modeling the environmental suitability of anthrax in Ghana and estimating populations at risk: Implications for vaccination and control

Abstract

Anthrax is hyper-endemic in West Africa. Despite the effectiveness of livestock vaccines in controlling anthrax, underreporting, logistics, and limited resources makes implementing vaccination campaigns difficult. To better understand the geographic limits of anthrax, elucidate environmental factors related to its occurrence, and identify human and livestock populations at risk, we developed predictive models of the environmental suitability of anthrax in Ghana. We obtained data on the location and date of livestock anthrax from veterinary and outbreak response records in Ghana during 2005–2016, as well as livestock vaccination registers and population estimates of characteristically high-risk groups. To predict the environmental suitability of anthrax, we used an ensemble of random forest (RF) models built using a combination of climatic and environmental factors. From 2005 through the first six months of 2016, there were 67 anthrax outbreaks (851 cases) in livestock; outbreaks showed a seasonal peak during February through April and primarily involved cattle. There was a median of 19,709 vaccine doses [range: 0–175 thousand] administered annually. Results from the RF model suggest a marked ecological divide separating the broad areas of environmental suitability in northern Ghana from the southern part of the country. Increasing alkaline soil pH was associated with a higher probability of anthrax occurrence. We estimated 2.2 (95% CI: 2.0, 2.5) million livestock and 805 (95% CI: 519, 890) thousand low income rural livestock keepers were located in anthrax risk areas. Based on our estimates, the current anthrax vaccination efforts in Ghana cover a fraction of the livestock potentially at risk, thus control efforts should be focused on improving vaccine coverage among high risk groups.

Author summary

Anthrax is a soil-borne zoonotic disease found worldwide. In the West African nation of Ghana, anthrax outbreaks occur annually with a high burden to livestock keepers and their animals. To control anthrax in both humans and animals, annual livestock vaccination is recommended in endemic regions. However, in resource poor areas distributing and administering vaccine is difficult, in part, due to underreporting, logistical issues, limited resources, and an under appreciation of the geographic extent of anthrax risk zones. Our objective was to model high spatial resolution anthrax outbreak data, collected in Ghana, using a machine learning algorithm (random forest). To achieve this, we used a combination of climatic and environmental characteristics to predict the potential environmental suitability of anthrax, map its distribution, and identify livestock and human populations at risk. Results indicate a marked ecological divide separating the broad areas of environmental suitability in northern Ghana from the southern part of the country, which closely mirrors the ecotone transitions from southern tropical and deciduous forests to the northern Sudanian and Guinea Savanna. Based on our model prediction, we estimated >3 million combined ruminant livestock and low income livestock keepers are situated in anthrax risk zones. These findings suggest a low level of annual livestock vaccination coverage among high risk groups. Thus, integrating control strategies from both the veterinary and human health sectors are needed to improve surveillance and increase vaccine dissemination and adoption by rural livestock keepers in Ghana and the surrounding region.