This article is more than 5 years old. Information may no longer be current.
Artificial intelligence identifies bat species that could harbor Ebola
Click Here to Manage Email Alerts
Artificial intelligence helped researchers identify more bat species that may be carriers of Ebola and other filoviruses, which could aid future surveillance and help fight outbreaks, they said.
“Using machine learning methods developed for artificial intelligence, we were able to bring together data from ecology, biogeography, and public health to identify bat species with a high probability of harboring Ebola and other filoviruses,” Barbara A. Han, PhD, disease ecologist at the Cary Institute of Ecosystem Studies, said in a news release.
“Understanding which species carry these viruses, and where they are located, is essential to preventing future spillovers.”
Finding the bats
According to a study by Han and colleagues that was published in PLoS Neglected Tropical Diseases, preventing future outbreaks of filoviruses such as Ebola depends on identifying wildlife reservoirs, a task that is complicated by the number of potential reservoirs and the dynamic environments of areas such as equatorial Africa.
Evidence, including the presence of filovirus antibodies and asymptomatic responses to filovirus infection, points to bats as a natural reservoir for ebolaviruses. As such, Han and colleagues collected life history, physiological and ecological traits of the 21 species known to harbor filoviruses, more than half of them fruit bats.
Caption: Of the world's 1116 bat species, only a small percentage have been flagged as potential hosts of filoviruses. Knowing where these bats live can help guide targeted surveillance and virus discovery. Credit: David Hayman
What they discovered were bats that matured early, reproduced more often, had larger offspring and tended to live in large groups. These bats also covered a broader geographic range, bringing them in contact with a more diverse range of mammals per square kilometer.
Using 57 variables such as diet, reproductive behavior and migratory patterns, an algorithm was able to distinguish bats that have tested positive for filoviruses from other bat species with 87% accuracy, according to the researchers.
“This model allows us to move beyond our own biases and find patterns in the data that only a machine can,” David T.S. Hayman, PhD, MSc, academic group leader at Massey University, said in the release. “Instead of predicting where Ebola and other filovirus outbreaks will occur by looking at the last spillover event, it forecasts risk based on the intrinsic traits of filovirus-positive bat species.”
Mapping hot spots
Armed with the trait profile, the researchers scanned a database of mammals, including the 1,116 known species of bats. They found that the species predicted to harbor filoviruses occurred over a larger area than expected, including Central and South America and Southeast Asia.
Notable hotspots, where up to 26 of the species overlap, included regions of Thailand, Burma, Malaysia, Vietnam and northeast India.
Despite this, there are “comparatively few reports” of human filovirus outbreaks in Asia, a disparity that warrants further study, Han and colleagues said.
“One outstanding question for future work is to investigate why there are so few spillover events reported for human and wildlife populations in Southeast Asia compared to equatorial Africa,” they wrote. “Whether outbreaks are indeed occurring but on a smaller or less easily detectable scale … or whether filovirus strains in this region are fundamentally less virulent to their host species, sorting the competing hypotheses about why filovirus infection dynamics in Africa differ from those in Asia will begin with more targeted surveillance of candidate reservoir species.” – by Gerard Gallagher
Click Here to Manage Email Alerts