Improve early detection of seasonal illnesses through monitoring health-seeking behavior through online web search queries

Improve early detection of seasonal illnesses through monitoring health-seeking behavior through online web search queries.

Google Inc has launched flu Trend analysis for several countries around the world.

Google together with Centers for Disease Control and Prevention has developed a method of analyzing large numbers of Google search queries to track influenza-like illness in a population.

Jeremy Ginsberg and Matthew H. Mohebb, both employed at Google Inc conceived, designed, and implemented the system

The relative frequency of certain queries is highly correlated with the percentage of physician visits in which a patient presents with influenza-like symptoms. It is possible to accurately estimate the current level of weekly influenza activity in countries, with a reporting lag of about one or more days.

This approach may make it possible to utilize search queries to detect influenza epidemics in areas with a large population of web search users.

Traditional surveillance systems, including those employed by the U.S. Centers for Disease Control and Prevention (CDC) and the European Influenza Surveillance Scheme (EISS), rely on both virologic and clinical data, including influenza-like illness (ILI) physician visits. CDC publishes national and regional data from these surveillance systems on a weekly basis, typically with a 1-2 week reporting lag.

In an attempt to provide faster detection, innovative surveillance systems have been created to monitor indirect signals of influenza activity.

Previous attempts at using online activity for influenza surveillance have counted search queries. 

• Attempts were made to submit to a Swedish medical website, outlined in 2009 by Hulth, A., Rydevik, G. & Linde, A. in an article called Web Queries as a Source for Syndromic Surveillance.
• Visitors to certain pages on a U.S. health website, detailed in an article from 2004 by Johnson, H. et al. called Analysis of Web access logs for surveillance of influenza.
• User clicks on a search keyword advertisement in Canada described in an article by Eysenbach, G. Infodemiology called tracking flu-related searches on the web for syndromic surveillance in 2006.
• A set of Yahoo search queries containing the words “flu” or “influenza” were found to correlate with virologic and mortality surveillance data over multiple years was documented in 2008 by Polgreen, P. M., Chen, Y., Pennock, D. M. & Forrest, N. D. in an article called Using internet searches for influenza surveillance.

Google web search queries can be used to accurately estimate influenza-like illness percentages regions and countries. Because search queries can be processed quickly, the resulting ILI estimates were consistently 1-2 weeks ahead of CDC ILI surveillance reports. The early detection provided by this approach may become an important line of defense against future influenza epidemics globally.

Up-to-date influenza estimates may enable public health officials and health professionals to better respond to seasonal epidemics. If a 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.

The search queries in Google model are not, of course, exclusively submitted by users who are experiencing influenza-like symptoms, and the correlations observed are only meaningful across large populations. Despite strong historical correlations, their system remains susceptible to false alerts caused by a sudden increase in ILI-related queries. An unusual event, such as a drug recall for a popular cold or flu remedy, could cause such a false alert.

Harnessing the collective intelligence of millions of users, Google web search logs can provide one of the most timely, broad reaching influenza monitoring systems available today. While traditional systems require 1-2 weeks to gather and process surveillance data, Google estimates are current each day. As with other syndromic surveillance systems, the data are most useful as a means to spur further investigation and collection of direct measures of disease activity.

Google database of queries contains 50 million of the most common search queries on all possible topics, without pre-filtering. Billions of queries occurred infrequently and are excluded. Using the internet protocol (IP) address associated with each search query, the general physical location from which the query originated can often be identified.

Countries at the moment in the Google.com Flu trend analysis are:

Australia,
Austria,
Belgium,
Bulgaria,
Canada,
France,
Germany,
Hungary,
Japan,
Mexico,
Netherlands,
New Zealand,
Norway,
Poland,
Russia,
Spain,
Sweden,
Switzerland,
Ukraine,
United States.

You can find the FREE Flu Trend analytics by Google on the below mentioned web site;

http://www.google.org/flutrends

At the moment it looks like Norway and Belgium, both have abnormal trends as a peak is observed well ahead of the normal historical trends seen in these countries. The other countries seem to have a peak as seen through history. This could serve as a pre-cursor warning for other countries that the H1N1 virus could attack earlier than the normal flu season in their countries, especially in the northern hemisphere. This should put them in a position to prepare their health care system, either by vaccination or by setting up their systems to be able to take care of a greater influx of sick people, either over a longer period or in two rounds, the H1N1 flu peak and later the normal seasonal flu peak.

Supplementary information can be found at;

http://www.nature.com/nature/journal/v457/n7232/suppinfo/nature07634.html