Disease Outbreaks Revealed By Analysis of Aggregate Internet Searches - Technologist
Technologist - The FindLaw Legal Technology Blog

Disease Outbreaks Revealed By Analysis of Aggregate Internet Searches

FindLaw columnist Eric Sinrod writes regularly in this section about legal developments surrounding technology and the internet.

Last week I told you about how the Internet can provide valuable information to help people learn about and deal with disease outbreaks like the recent swine flu.  I am here to tell you now that the Internet goes even farther - as early analysis of aggregate Internet searches can be the first indicator of a disease outbreak.

Google has found that certain search terms correspond as indicators of flu activity within the United States.  As a result, Google Flu Trends has been set up to aggregate Google search data to estimate possible flu activity at a state level practically in real-time.
How does this work?  Millions of Google users search for health information online.  Not surprisingly, there are more searches for flu-related information during flu season, just like there are increased searches for allergy-related information during allergy season.

Google has established a strong relationship between the number of people who search for flu-related information and the number of people who are experiencing flu symptoms.  The results have been published in Nature.

During the 2007-2008 flu season, an earlier version of Google Flu Trends was used to share results weekly with the Epidemiology and Prevention Branch of the Influenza Division of the U.S. Centers for Disease Control and Prevention (CDC).  Amazingly, Google Flu Trends was able to accurately estimate current flu levels one to two weeks faster than published CDC reports. 

Of course, a jump of a week or two can be very valuable in terms of marshalling resources and getting governments, businesses and individuals to respond proactively to a disease outbreak just as it unfolds.

Google Flu Trends potentially can come up with results quicker than the CDC because the CDC in part relies upon data provided by doctors that they have obtained from their evaluation of patients.  This can take a bit of time, whereas Google search queries can be counted quickly and made available daily, providing a possible early-warning system for outbreaks.

One concern is that as news coverage saturates the public with reports of a given disease, it is possible that searches relating to that disease in a specific geographical area may not match what people actually are experiencing in that region.  For example, if people in one state constantly are barraged with reports of swine flu in another state, they may conduct online searches relating to swine flu, even if the disease and its symptoms are not present in the state of the searchers.

Perhaps the real value of tools like Google Flu Trends will become the revelation of early spikes in aggregate searches from a region relating to a given disease and its associated symptoms before that region has been peppered with news information from other geographic areas.

Eric Sinrod is a partner in the San Francisco office of Duane Morris LLP (http://www.duanemorris.com) where he focuses on litigation matters of various types, including information technology and intellectual property disputes.  His Web site is http://www.sinrodlaw.com and he can be reached at ejsinrod@duanemorris.com.  To receive a weekly email link to Mr. Sinrod's columns, please send an email to him with Subscribe in the Subject line.

This column is prepared and published for informational purposes only and should not be construed as legal advice.  The views expressed in this column are those of the author and do not necessarily reflect the views of the author's law firm or its individual partners.