News Feature | November 21, 2014

Can Wikipedia Forecast Diseases?

Katie Wike

By Katie Wike, contributing writer

Lab Reporting Disease Reports

Researchers claim Wikipedia page views can forecast the spread of influenza and dengue fever.

According to researchers at Los Alamos National Laboratory, evaluating trends in page views on Wikipedia can help experts predict disease outbreaks. BBC News reports this technique may be able to predict outbreaks of influenza and dengue fever nearly a month before official health advice.

“Even in developed countries, infectious disease has significant impact; for example, flu seasons in the United States take between 3,000 and 49,000 lives. Disease surveillance, traditionally based on patient visits to health providers and laboratory tests, can reduce these impacts,” write the study's authors.

The team at Los Alamos argues these traditional surveillance methods are time consuming. Fierce Health IT explains that instead, these researchers can use an algorithm to connect relevant Wikipedia searches with information from the Centers for Disease Control and Prevention for real-time disease prediction.

“We argue that these challenges can be overcome by using a freely available data source: aggregated access logs from the online encyclopedia Wikipedia. Using simple statistical techniques, our proof-of-concept experiments suggest that these data are effective for predicting the present, as well as forecasting up to the 28-day limit of our tests.”

Wikipedia can be used “as a broadly effective data source for disease information, and we outline a path to a reliable, scientifically sound, operational, and global disease surveillance system that overcomes key gaps in existing traditional and internet-based techniques.”

Another recent disease surveillance project is that of Google Flu Trends, which Health IT Outcomes reports has integrated CDC information into its program for better accuracy.  Google Flu Trends has been criticized in the past for predicting double the flu incidents than what actually occurred.