A team of researchers from Los Alamos National Laboratory's (LANL) Defense Systems and Analysis Division has developed a method for forecasting the course of upcoming flu seasons and other infectious disease outbreaks by analyzing the views of Wikipedia articles.
According to the U.S. Centers for Disease Control (CDC) and Prevention, the seasonal flu affects a fifth of the U.S. population, and the resulting hospitalization and absenteeism causes major economic impacts, making the ability to forecast the course of the disease ahead of time a major boon.
To create their weekly forecasts, the Los Alamos researchers used modern data assimilation methods in conjunction with Wikipedia access logs and the influenza-like illness (ILI) reports from the CDC. "We used techniques often seen in weather forecasting to iteratively tune a model of influenza dynamics based on Wikipedia observations so that our forecast agrees with the most current ILI data," says LANL researcher Kyle Hickmann.
The team applied its method to the 2013-2014 influenza season and says it was able to project the actual outcome with a high probability.
"Disease forecasting is still in its infancy and there is much more to learn in this field," says LANL's Sara Del Valle. "We are continuing to refine our approach so our forecasts can be used for actionable decision-making."
From Los Alamos National Laboratory News
View Full Article
Abstracts Copyright © 2015 Information Inc., Bethesda, Maryland, USA
No entries found