Key Points:
- Wildlife-linked pathogen outbreaks are increasing.
- A new machine learning method can forecast when and where disease outbreaks are likely.
- The new approach will help direct infectious disease surveillance and field efforts, providing a cost-effective strategy to better determine where to invest limited disease resources.
The rate that emerging wildlife diseases infect humans has steadily increased over the last three decades—SARS-CoV-2 is a case in point. The global pandemic only heightened the urgent need for disease ecology tools to forecast when and where disease outbreaks are likely.
An international team of researchers has now developed a machine learning-based methodology that can accurately predict disease transmission from wildlife to humans, from one wildlife species to another, and determine who is at risk of infection.
To test the accuracy of the methodology, the researchers used three host-pathogen systems—avian malaria, birds with West Nile virus and bats with coronavirus. They found that for each system, the species most frequently infected was not necessarily the most susceptible to the disease. But, to better pinpoint hosts with higher risk of infection, the researchers had to identify relevant factors.
They accomplished this by integrating geographic, environmental and evolutionary development variables. From there, the researchers identified host species that have previously not been recorded as infected by the parasite under study, providing a way to identify susceptible species and eventually mitigate pathogen risk.
“Our main goal is to develop this tool for preventive measures,” said co-principal investigator Diego Santiago-Alarcon, a University of South Florida professor of integrative biology. “It’s difficult to have an all-purpose methodology that can be used to predict infections across all the diverse parasite systems, but with this research, we contribute to achieving that goal.”
The methodology was confirmed accurate even when using small amounts of information. The team plans to continue their research to further test the methodology on additional host-pathogen systems and extend the study of disease transmission to predict future outbreaks. The goal is to make the tool easily accessible through an app for the scientific community by the end of 2022.
“Humanity, and indeed biodiversity in general, are experiencing more and more infectious disease challenges as a result of our incursion and destruction of the natural order worldwide through things like deforestation, global trade and climate change,” said Andrés Lira-Noriega, research fellow at the Instituto de Ecologia. “This imposes the need of having tools like the one we are publishing to help us predict where new threats in terms of new pathogens and their reservoirs may occur or arise.”
Information courtesy of University of South Florida.