A real-time forecasting system can predict the peak of seasonal flu outbreaks with 63 to 70 percent accuracy, a new study shows.
A team of researchers created the system by adapting weather prediction methods and combining reports from the Centers for Disease Control on verified cases of flu in specific regions with data from Google Flu Trends, which tracks the number of flu-related searches to estimate outbreaks. The system produced weekly flu forecasts for 108 U.S. cities during the 2012-2013 influenza season, the team reports December 3 in Nature Communications.
While the forecaster performed better than past methods and did well with smaller cities' predictions, borough- or neighborhood-level data may need to be included for places such as New York City or Los Angeles to make more accurate outbreak calculations, the authors suggest.
Note: To comment, Science News subscribing members must now establish a separate login relationship with Disqus. Click the Disqus icon below, enter your e-mail and click “forgot password” to reset your password. You may also log into Disqus using Facebook, Twitter or Google.