- Scientists are using a computer to make accurate predictions about which animals could harbor dangerous viruses, bacteria, and fungi and bring about the next pandemic.
- In a new study, the researchers used machine learning; teach computers to recognize patterns in large data sets.
- Better computer predictions could help experts improve how they prevent and respond to a pandemic.
Using a computer to predict a infectious disease outbreak before it starts or becomes a pandemic may sound like a bit of Philip K. Dick science fiction, but scientists are getting closer.
In a new study, researchers used the machine learning (teach computers to recognize patterns in large data sets) to make accurate predictions about which animals might harbor dangerous viruses, bacteria and fungi. Better predictions could help experts improve how they prevent and respond to disease outbreaks.
“I cannot stress enough how exciting this article is. I think it will really resonate with the scientific community,” says Lynn Martin, a disease ecologist at the University of South Florida, Tampa, who was not involved in the study.
Almost all new infectious disease outbreaks occur when a virus, bacteria, or fungus jumps from an animal to a human. Predicting with a precision computer when and where these infections, called zoonotic diseases, cross species could quell outbreaks before they become pandemics.. But maintaining active disease surveillance worldwide is costly and time-consuming.
A team of scientists built a computer program
To help narrow down the search, a team of scientists built a Computer program to analyze a massive database of mammal habits and habitats, including geographic range and reproductive strategies of hundreds of species. His program evaluated 86 different variables, such as body size, lifespan and population density, to look for common patterns among animals known to carry zoonotic diseases. “In fact, I was surprised that no one had. It seemed like a natural approach.” says team leader Barbara Han, a disease ecologist at the Cary Institute for Ecosystem Studies in Millbrook, N.Y.
To simplify the results, Han and his colleagues restricted their analysis to rodents, a group that carries a disproportionately high number of zoonotic diseases. Rodents carrying zoonotic infections tend to have “live fast, die young” lifestyles, Han says.
They have large geographic ranges, early reproductive maturity, large litters, and shorter gestation periods. Scientists aren’t sure why this lifestyle is common among rodents that carry zoonotic diseases., but they suggest that the accelerated reproductive cycle may allow animals to successfully pass on their genes before the disease kills them. “Even if it kills you in 6 months, you’ll be able to produce like 5 liters,” says Han.
WHAT HAS MADE THIS MODEL POSSIBLE
Han and his team first used their program to identify lifestyle patterns common to rodents harboring diseases such as the Black Death, rabies, and hantavirus, and found that their model had a 90% accuracy rate. After the telltale signals had been “learned” by the machine, the researchers
they looked for new rodents that fit the profile but were previously not thought to be carriers. Until now, the model has identified more than 150 new species of animals that could harbor zoonotic diseases researchers report online today at Proceedings of the National Academy of Sciences.
The computer program also predicted 58 new infections in rodents already known to carry a zoonotic disease.
Top 5 Laptops for Doctors in 2022
Researchers develop a ‘computer in the bone’
Computer vs patient. How to make the patient the protagonist?