Can Wikipedia help predict virus outbreaks?

By Efrosini Costa

Can Wikipedia help predict virus outbreaks?
Scientists say Wikipedia can help them predict virus outbreaks nearly a month before health officials.

It may sound slightly out of this world, but scientists used the online encyclopaedia to forecast influenza and tuberculosis outbreaks four weeks before they became apparent to health officials.

The Los Alamos National Laboratory team said tracking page view has helped them spot emerging outbreaks.

This is because people are searching the internet or consulting online advice before seeking medical care from their health care practitioners.

“A global disease-forecasting system will change the way we respond to epidemics,” said Lead researcher Dr Sara Del Valle.

“In the same way we check the weather each morning, individuals and public health officials can monitor disease incidence and plan for the future based on today’s forecast.

Traditional disease surveillance relies on data collected from laboratory tests, as well as frequency in communication with health practitioners and facilities.

Published in the journal PLoS Computational Biology, the study found while these methods were accurate they are slow and more expensive.

Instead the researchers turned to Wikipedia to track disease-related page views from 2010 to 2013.

By doing this they were able to map the languages the information was viewed in, using this as a guide to the approximate location of the page viewers.

The data collected was then compared to the disease outbreak information provided by national health surveillance teams.

In eight out of 14 cases there was a marked increase in page views four weeks before health officials declared an outbreak.

The statistical technique allowed them to predict emerging influenza outbreaks in the United States, Poland, Japan and Thailand, dengue fever spikes in Brazil and Thailand, and a rise in tuberculosis cases in Thailand.

“The goal of this research is to build an operational disease monitoring and forecasting system with open data and open source code,” Dr Valle explained.

“This paper shows we can achieve that goal.”

Previous attempts using the Internet to predict disease outbreaks include Google Flu Trends.’

SHARE THIS ARTICLE

Print Recipe

BECOME A MiNDFOOD SUBSCRIBER TODAY

Let us keep you up to date with our weekly MiNDFOOD e-newsletters which include the weekly menu plan, health and news updates or tempt your taste buds with the MiNDFOOD Daily Recipe. 

Member Login