SoylentNews

Forecasting Future Infectious Disease Outbreaks.

posted by cmn32480 on Wednesday May 20 2015, @06:58AM   
from the does-a-bad-attitude-qualify dept.

AnonTechie writes:

Machine learning can pinpoint rodent species that harbor diseases andgeographic hotspots vulnerable to new parasites and pathogens. So reports a new study in the Proceedings of the National Academy of Sciences led by Barbara A. Han, a disease ecologist at the Cary Institute of EcosystemStudies.

Most emerging infectious diseases are transmitted from animals to humans, with more than a billion people suffering annually. Safeguarding public health requires effective surveillance tools.

With University of Georgia Odum School of Ecology colleagues John Paul Schmidt, Sarah E. Bowden, and John M. Drake, Han employed machine learning, a form of artificial intelligence, to reveal patterns in an extensive set of data on more than 2,000 rodent species, with variables describing species' life history, ecology, behavior, physiology, and geographic distribution.

The team developed a model that was able to predict known rodent reservoir species with 90% accuracy, and identified particular traits that distinguish reservoirs from non-reservoirs. They revealed over 150 new potential rodent reservoir species and more than 50 new hyper-reservoirs - animals that may carry multiple pathogens infectious to humans.

http://phys.org/news/2015-05-future-infectious-disease-outbreaks.html

[Abstract]: http://www.pnas.org/content/early/2015/05/14/1501598112

[Source]: http://www.caryinstitute.org/newsroom/forecasting-future-infectious-disease-outbreaks

• Re:More than a billion illnesses Re:More than a billion illnesses (Score: 1, Informative) by Anonymous Coward on Wednesday May 20 2015, @07:23PM

  by Anonymous Coward on Wednesday May 20 2015, @07:23PM (#185659)

  Nice catch on the implausible hype. I don't think it is influenza though. Maybe... to get to the origins of that claim we need to go down a citation hole. Starting with the OP paper:

  Han (2015):

  With over 1 billion cases of human illness attributable to zoonotic disease each year, identifying wild reservoirs of zoonotic pathogens is a perennial public health priority (4).
  4. Karesh WB, et al. (2012) Ecology of zoonoses: Natural and unnatural histories. Lancet
  380(9857):1936–1945.

  Karesh (2012):

  The greatest burden on human health and livelihoods, amounting to about 1 billion cases of illness and millions of deaths every year, is caused by endemic zoonoses that are persistent regional health problems around the world.2
  2 International Livestock Research Institute. Mapping of poverty
  and likely zoonoses hotspots. Zoonoses Project 4. Report to
  Department for International Development, UK. Nairobi, Kenya:
  International Livestock Research Institute, 2012.

  And in that report it shows a number of 2.333 billion annual cases of "Gastrointestinal (zoonotic)" (Table 2.1). They do not get any more specific than that (salmonella perhaps?) but cite five sources:

  International Livestock Research Institute (2012):

  1.4 Selection of zoonoses for prioritisation
  In order to select ‘important’ zoonoses for further study, we used information from five listings of
  priority zoonoses or priority diseases that included zoonoses and were relevant to developing
  countries:
  1) The World Health Organisation Global Burden of Disease
  2) The World Animal Health Organisation list of notifiable zoonoses
  3) Zoonoses important to poor people identified by expert consultation (Perry et al., 2002)
  4) The Rosetta listing of infectious causes of death
  5) A systematic review of zoonoses commissioned by DFID, which identified 373 zoonoses as
  important (Grace et al., 2011).
  Zoonoses that appeared in more than one list were considered (n=56).

  https://cgspace.cgiar.org/handle/10568/21161 [cgiar.org]

  At which point I just don't care about this claim any longer. Once it gets 3 deep without primary data we should no longer be surprised if the number is essentially made up. Now I have a bad feeling about this current paper.

  Parent

  Starting Score:	0		points
  Moderation		+1
  Informative=1, Total=1
  Extra 'Informative' Modifier		0
  Total Score:		1

• Re:More than a billion illnesses Re:More than a billion illnesses (Score: 2) by Joe on Wednesday May 20 2015, @10:56PM

  by Joe (2583) on Wednesday May 20 2015, @10:56PM (#185773)

  I only looked as far as the Lancet paper since they list some of the emerging zoonotic infections, including influenza and a quick search said ~15% of people get sick per year.
  I'll have to look into that ILRI report because the combined table is around 2.45 billion affected humans per year (a lot bigger than I expected) and that obviously doesn't match very well with the 1 billion number.

  - Joe

  Parent

  • Re:More than a billion illnesses (Score: 0) by Anonymous Coward on Thursday May 21 2015, @06:02AM

    by Anonymous Coward on Thursday May 21 2015, @06:02AM (#185910)

    If it really means something like 1/3 of people get diarrhea at least once each year it could make sense. We need the methodology from the primary data source to interpret that number. And also, it is odd to round down from over 2 billion to 1 billion.

    Parent