Google Flu Trends

November 12, 2008 / Can you really predict flu activity by aggregating search data?

Google Flu Trends looks like an excellent example of the wisdom of crowds principle. Many individuals use Google Search when they experience flu symptoms. Google pairs this data with information from the Centers for Disease Control to predict flu activity across the country:

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 all the flu-related search queries from each state and region are added together. We compared our query counts with data from a surveillance system managed by the U.S. Centers for Disease Control and Prevention (CDC) and discovered 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.

They claim that this gives results two weeks earlier than existing methods. I wonder if you could predict an election with data like that…

Edited to add: What a difference a day makes. This screenshot shows that several states have moved from “low” to “moderate” flu activity based on data from the past 24 hours:

Compare this to Lydia’s screenshot which shows how the map looked yesterday. “Moderate” now includes Vermont, West Virginia, Alabama, Georgia and South Carolina, and Nevada has moved from “minimal” to “low.” Here comes that spike.