A team of scientists led by the Cary Institute of Ecosystem Studies are using machine learning and big data to develop a model that can predict which bat species are most likely to carry the Ebola virus and other filoviruses.
The study published in the journal PLoS Neglected Tropical Diseases, focused on bats – primary suspects for spreading the disease. The findings provide information that could be used to target surveillance more efficiently by focusing on the likeliest filovirus carriers, many of which have never been tested.
“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 harbouring Ebola and other filoviruses,” said the paper’s Lead Author and Disease Ecologist at Cary, Dr Barbara Han.
“Understanding which species carry these viruses and where they are located is essential to preventing future spill overs,” continued Dr Han.
The researchers created profiles of bat species that are likely to carry filoviruses, based on the biological characteristics of 21 bat species known to carry diseases using machine learning. They analysed 57 variables ranging from diet and reproductive behaviour to migratory patterns and population size. The algorithm was able to predict which bats act as potential carriers with 87% accuracy.
When data on the world’s 1116 bat species were searched using this filovirus-positive bat profile, machine learning identified new potential hosts based on their traits and the predicted bat species were then plotted onto a world map.
The researchers predicted new bat species that could carry filoviruses were widely distributed outside of Africa; potential Ebola hotspots included Thailand, Burma, Malaysia, Vietnam and north-east India.
Bat species that were more likely to harbour filoviruses had the tendency to live in large groups, reached sexual maturity at an earlier age, had larger offspring and gave birth to more than one pup.
“The model allows us to move beyond our own biases and find patterns in the data that only a machine can,” said Co-Author of the study and Researcher at the Institute of Vet, Animal & Biomedical Sciences at Massey University, Dr David Hayman.
“Maps generated by the algorithm can help guide targeted surveillance and virus discovery projects. We suspect there may be other filoviruses waiting to be found,” said Co-Author of the study and Researcher at the School of Ecology at the University of Georgia, Dr John Drake.
“An outstanding question for future work is to investigate why there are so few filovirus spill over events reported for humans and wildlife in Southeast Asia compared to equatorial Africa,” concluded Dr Drake.