Forecasting system predicts peaks in flu outbreaks

A new forecast system has predicted peak outbreaks of influenza (virus shown) in 108 U.S. cities.

Cynthia Goldsmith/CDC

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.

Ashley Yeager is the associate news editor at Science News. She has worked at The Scientist, the Simons Foundation, Duke University and the W.M. Keck Observatory, and was the web producer for Science News from 2013 to 2015. She has a bachelor’s degree in journalism from the University of Tennessee, Knoxville, and a master’s degree in science writing from MIT.

More Stories from Science News on Health & Medicine

From the Nature Index

Paid Content