April 29, 2009

Tracking the flu on the Internet with Google Flu

Google Flu (what it is and how it works here: http://www.google.org/about/flutrends/how.html) can actually track flu outbreaks. Using the Internet. Wuh?

That's not the only surprising thing. It doesn't show any flu outbreak in the southern half of the Cabo peninsula right now, for example. I assume they weight their data by the geographic density of internet users, but I don't know for sure that they do (i.e. they're looking at % of searches not total number of searches). In any case, according to these data points, we're safer in Cabo than in California right now.

Flu in Mexico: http://www.google.org/flutrends/intl/en_mx/
Flu in the US: http://www.google.org/flutrends/

How the heck does Google, or by extension the Internet, know where there is a flu outbreak?

From the Google site: "Each week, millions of users around the world search for online health information. As you might expect, there are more flu-related searches during flu season, more allergy-related searches during allergy season, and more sunburn-related searches during the summer.


In the United States we have found a close relationship between how many people search for flu-related topics and how many people actually have flu symptoms. Of course, not every person who searches for "flu" is actually sick, but a pattern emerges when selected flu-related search queries from each state and region are added together. For the United States, we compared our query counts with data from a surveillance system managed by the U.S. Centers for Disease Control and Prevention (CDC) and found that some search queries tend to be popular exactly when flu season is happening. By counting how often we see these search queries, we can estimate how much flu is circulating in various regions of the United States."

This is probably one of the most surprisingly useful features of the Internet I've seen. How long before Skynet becomes sentient? Wowzers.

Posted by rick at April 29, 2009 08:20 PM