"Fruitful Marriage of Mob Behavior and Medicine": Google Flu Trends
Posted Dec 23 2008 9:35pm
The New York Times called it the " fruitful marriage of mob behavior and medicine." Google announced today that "certain search terms are good indicators of flu activity. Flu Trends uses aggregated search data to estimate flu activity in your state up to two weeks faster than traditional systems."
So searches for flu and other like search terms, based on analysis over hundreds of billions of de-identified searches, may be a good indictor of flu outbreak - -with results 1 to 2 weeks faster than trailing indicators based on reporting to the Centers for Disease Control and Prevention (CDC). The graph below charts the correlation between Flu Trends and CDC data.
What's the flu activity in your state? Check out the Flu Trends map.
An early version of an upcoming article in Nature Magazine reports that "because the relative frequency of certain queries is highly correlated with the percentage of physician visits in which a patient presents with influenza-like symptoms, we can accurately estimate the current level of influenza activity in each region of the United States, with a reporting lag of about one day. This approach may make it possible to utilize search queries for influenza surveillance in areas with a large population of web search users."
In their press release, Google forsees a breakthrough in proactive management of disease outbreaks. "For epidemiologists, this is an exciting development, because early detection of a disease outbreak can reduce the number of people affected. If a new strain of influenza virus emerges under certain conditions, a pandemic could emerge and cause millions of deaths (as happened, for example, in 1918 ). Our up-to-date influenza estimates may enable public health officials and health professionals to better respond to seasonal epidemics and — though we hope never to find out — pandemics. We shared our preliminary results with the Epidemiology and Prevention Branch of the Influenza Division at CDC throughout the 2007-2008 flu season, and together we saw that our search-based flu estimates had a consistently strong correlation with real CDC surveillance data."