Researchers at the Los Alamos National Laboratory won the Centers for Disease Control and Prevention’s FluSight Challenge by providing the most accurate state, national, and regional flu forecasts in 2018.
The lab beat out 23 other teams with its probabilistic artificial intelligence computer model.
“Accurately forecasting diseases is similar to weather forecasting in that you need to feed computer models large amounts of data so they can ‘learn’ trends,” Dave Osthus, a statistician at Los Alamos and developer of the computer model, Dante, said. “But it’s very different because disease spread depends on daily choices humans make in their behavior—such as travel, hand-washing, riding public transportation, interacting with the healthcare system, among other things. Those are very difficult to predict.”
The FluSight Challenge challenges scientific institutions to develop predictive computer models to improve flu forecasting.
LANL’s Dante model proved more successful than the other models in predicting the timing, peak, and short-term intensity of the flu season. Dante is a multi-scale model, combining national, regional, and state flu data. The model averages the trends across those different geographies and uses information from individual states to improve other states’ forecasts. Dante proved particularly useful for forecasting at the local level.
“Flu forecasts this early in the season are marked by significant uncertainty,” Osthus said. “The flu season doesn’t usually start to reveal itself until after Thanksgiving. There is nothing, at this point, to suggest a highly unusual flu season, meaning it is likely to peak between mid-December and late March. As far as the intensity of the flu season, however, it’s just too early to tell.”