An AI Hunts the Wild Animals Carrying Ebola

the_newsbeagle writes: Outbreaks of infectious diseases like Ebola follow a depressing pattern: People start to get sick, public health authorities get wind of the situation, and an all-out scramble begins to determine where the disease started and how it's spreading. Barbara Han, a code-writing ecologist, hopes her algorithms will put an end to that reactive model. She wants to predict outbreaks and enable authorities to prevent the next pandemic. Han takes a big-data approach, using a machine-learning AI to identify the wild animal species that carry zoonotic diseases and transmit them to humans.

Comments

Re:Vaporware

[Anonymous Coward]

FTFA:

When we tested our rodent-sorting algorithm on the 20 percent of rodents that hadn’t been included in the training data set, it predicted species’ reservoir status with about 90 percent accuracy.
[...]
As the algorithm sorted through the 2,200 rodent species, it provided a list of new suspects. Some species that had previously been given a “0” for unknown reservoir status fit more neatly in the “1” category of known disease carriers. We didn’t have to wait long for validation. While we were getting our results to press, two of those suspect species were indeed recognized as novel reservoirs for human diseases. One species, a red backed vole (Myodes gapperi) native to Canada and the northern United States, was found to carry the parasite that causes echinococcosis, a nasty ailment in which cysts grow in multiple organs. And researchers identified a vole (Microtus guentheri) native to Asia Minor as a newfound reservoir for leishmaniasis, which causes skin ulcers.

Yeah, nothing to indicate this approach might work in identifying likely reservoir hosts, and also tracking conditions where a disease outbreak is more likely.

Perhaps you should have read the WHOLE article, and not just the first paragraph or two?

Re:easy to prevent

[SuricouRaven]

Ebola gets a lot of attention because it's high-mortality, spreads fast in the right conditions, and is a wonderfully messy way to die - and that means lots of newspaper sales and TV ratings.

It's the influenzas you have to look out for. People don't pay attention any more after the bird flu and swine flu fizzled out without producing the pandemic everyone was fearing - and perhaps the next one will do likewise. Eventually, though, we'll get another really nasty strain and it'll be 1918 all over again. Fifty million dead last time - people forgot quickly.

Ask most people today about the 1918 pandemic and most wouldn't know about it - and of those that do know, half of it only know it from a passing mention in Twilight.