WASHINGTON - Intricate tracking models have become a huge asset in forecasting the weather. Now, scientists are using similar technology to try to predict flu outbreaks.
The aim is to predict the peak of an outbreak weeks before it occurs.
Google Flu Trends estimates outbreaks based on the number of flu-related searches in different parts of the country.
The researchers from Columbia University's Mailman School of Public Health and the National Center for Atmospheric Research created a model that processed data using the 2003-2008 flu seasons in New York City.
Authors of the study, published in the Proceedings of the National Academy of Sciences of the United States of America, say this is just a first step, one that shows a lot of potential.
The findings indicated the peak timing could be predicted more than seven weeks in advance.
The flu kills about 35,000 Americans each year.
WTOP's Thomas Warren contributed to this report. Follow @WTOP on Twitter.
(Copyright 2012 by WTOP. All Rights Reserved.)