Google have used their gigantic databases of search terms to come up with something quite interesting: predicting levels of flu activity in the United States. By aggregating data on flu-related searches, the search giant was able to get accurate results up to two weeks faster than the Epidemiology and Prevention Branch of the Influenza Division at the U.S. Centers for Disease Control and Prevention (CDC).
By speeding up predictions, Google can provide an early warning system for influenza outbreaks. The CDC report that each year in America, 200,000 people are hospitalized from flu complications and about 36,000 people die from the disease – although these is some debate about these figures. In an early version of a paper that has been accepted for publication in the journal Nature, Google researchers state:
Up-to-date influenza estimates may enable public health officials and health professionals to better respond to seasonal epidemics. If a particular region experiences an early, sharp increase in ILI physician visits, it may be possible to focus additional resources on that region to identify the etiology of the outbreak, providing extra vaccine capacity or raising local media awareness as necessary.
Google is also keen to reiterate it’s company’s unofficial motto: Don’t be evil. Using search engine data in this way brings up questions about privacy issues, but Google assures its users that they can not be identified from the data used in Google Flu. Which is nice. Now if they could just invent Google Where In The Damn Hell Did I Leave My Keys…