Forecast infectious disease outbreaks with Social media and Internet data

Updated On : 21 Jan , 2017 , 02:53 PM
Social media and internet data to forecast infectious disease outbreaks
Social media and internet data to forecast infectious disease outbreaks
New Delhi:

According to a new study, it has been found that with the help of social media and Internet reports one can forecast the outbreak of infectious disease, especially when the information is scarce

"Our study offers proof of concept that publicly available online reports released in real-time by ministries of health, local surveillance systems, the World Health Organisation(WHO) and authoritative media outlets are useful to identify key information on exposure and transmission patterns during epidemic emergencies," researchers said.

"Our Internet-based findings on exposure patterns are in good agreement with those derived from traditional epidemiological surveillance data, which can be available after considerable delays," they said.

Mathematical models forecasting disease transmission can be difficult to formulate during the early stage of an outbreak as it is often used to guide public health control strategies when the accurate data is scarce, according to theresearchers from the Georgia State University in the US.

"In the absence of detailed epidemiological informationrapidly available from traditional surveillance systems,alternative data streams are worth exploring to gain areliable understanding of disease dynamics in the early stagesof an outbreak," they said.

To test the reliability of alternative data streams, researchers tracked and analysed reports from public healthauthorities and reputable media outlets posted via socialmedia or their websites during the 2014-2015 Ebola epidemic inWest Africa and the 2015 Middle East Respiratory Syndrome outbreak in South Korea.

 Data on the viruses' exposure patterns and transmission chains was collected by the Researchers. It was also noted the West African Ebola outbreak was particularly interesting case study because early data were limited to basic weekly case counts at the country level.

They were able to use internet reports describing Ebolacases in the three hardest hit countries - Guinea, SierraLeone and Liberia - to glean detailed stories about casesarising in clusters within families or through funerals orhospital exposure.

"Our analysis of the temporal variation in exposurepatterns provides useful information to assess the impact ofcontrol measures and behaviour changes during epidemics," theysaid. The findings are published in the Journal of Infectious Diseases. 

(With PTI Inputs)

First Published : Saturday, January 21, 2017 01:53 PM
Download the News Nation Mobile App and stay connected with top stories from India and around the world. Available on Android and iOS.