Become a fan of Slashdot on Facebook

 



Forgot your password?
typodupeerror
Check out the new SourceForge HTML5 internet speed test! No Flash necessary and runs on all devices. ×
AI Earth Medicine Stats

An AI Hunts the Wild Animals Carrying Ebola 45

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.
This discussion has been archived. No new comments can be posted.

An AI Hunts the Wild Animals Carrying Ebola

Comments Filter:
  • FTFA:

    If we can predict which species may carry infections capable of jumping to humans, we can monitor the potential hot spots where people interact with these creatures. One day, I hope that biologists will forecast disease outbreaks in the same way meteorologists forecast the weather.

    That's a noble goal. But there was nothing in the article indicating it actually works.

    • Re: (Score:1, Insightful)

      by 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 f

    • Re:Vaporware (Score:4, Informative)

      by gstoddart ( 321705 ) on Thursday September 24, 2015 @01:16PM (#50590529) Homepage

      Well, did you keep scrolling?

      Our study yielded more than scientific insights: It also provided actionable intelligence. 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.

      Sure sounds to me that, for the North American populations they tested this one they actually did demonstrate it actually works.

      I'm sure it's not perfect or complete, but it sure sounds like it actually created some testable results.

      • by tomhath ( 637240 )

        Sure sounds to me that, for the North American populations they tested this one they actually did demonstrate it actually works.

        Not really. While they were crunching numbers, other scientists not connected in any way with this project identified a couple of rodents that are disease vectors. It turned out that those two rodents were in her "maybe a vector" bucket. All that demonstrates is that those two are not false positives.

  • A new strain of ebola causes animal to start bleeding as if they'd been shot...

    • (For the humor impaired, the "hunt" is identifying species likely to harbor ebola based on matching various traits such as number of litters per year).

  • She wants to predict outbreaks and enable authorities to prevent the next pandemic.

    it's easy to prevent, you just need good sanitation laws. the problem we face is corrupt governments who don't give a flying fuck about their people. there is a reason that outbreaks start in poor areas with bad/no sanitation practices.

    • Re:easy to prevent (Score:5, Insightful)

      by SuricouRaven ( 1897204 ) on Thursday September 24, 2015 @03:16PM (#50591375)

      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.

  • by nickweller ( 4108905 ) on Thursday September 24, 2015 @05:09PM (#50592253)
    "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"

    I though Ebola spread because of the traditional burial practices of the indigenous peoples. Namely some traditional healer traveling from the next village over, performing a 'purification' ritual, consisting of a crude form of embalming and 'sitting in' with the deceased. The healer goes back to her home village and dies from Ebola. People from miles around attend the funeral and go back home and spread Ebola. Over three hundred cases from the one funeral ref [who.int].
  • Anyone else imagine Arnold calling up wild animals from a pay phone?

"There... I've run rings 'round you logically" -- Monty Python's Flying Circus

Working...