How Twitter can predict flu outbreaks faster than the CDC infographic showcases the growing influence of social networks in tracking public health trends.
This year has been declared the worse flu season in over a decade by the CDC with 29 states including New York City reporting high levels of influenza-like-illness (ILI), and another nine states reporting moderate levels of ILI. The mayor of Boston has declared a public health emergency on Wednesday as the reported flu infections is already 10 times higher than last season and has killed more than a dozen people. Hospitals throughout the country have felt the strain in treating the flu outbreak turning away patients in some places with tents set up to handle less serious cases.
Traditional flu tracking performed by the Centers for Disease Control and Prevention (CDC) relies on outpatient reporting and virological test results supplied by laboratories nationwide that confirms an outbreak within 2 weeks after they begin; however, the CDC does not track all cases. So, what if social networks such as Twitter can track the outbreak of the flu 8 days in advance with 90 percent accuracy?
Researchers at the University Of Rochester in New York have used Twitter to track the outbreak of flu through New York utilizing a learning model to determine when healthy people would get sick with the flu. The study, performed by Adam Sadilek and his team, analyzed 4.4 million tweets that contained GPS location data from some 630,000 users in New York City over one month in 2010, using an algorithm that learned the difference between actual reports of illness and other, non-relative uses of words such as “sick”. The results were then plotted on a heatmap used to predict with people in a certain area were at risk of contagion up to eight days in advance.
Social media website, Sickweather declared that the flu season began October 18th, six weeks before the CDC’s official announcement. Sickweather utilized tracking and analysis via social media to predict the start of the flu season after seeing a 77 percent increase in social media reports mentioning flu between August and September. The CDC has even collaborated with Google using their Google Flu Trends tool as a potential source for early outbreak warnings. Other social media tools such as Flunearyou.org have 20,000 volunteers who are tracking their symptoms, narrowing the spread of flu down to your ZIP code.
MPHProgramsList, an advocate for public health student education has created the infographic visuliazation shown below that highlights the growing influence of social media’s ability to monitor and accurately track public health trends. Key highlights of the infographic include:
CLICK IMAGE TO E ENLARGE