The social business of flu

Whilst social media tools have primarily been used for commercial ends, there is a growing stream of evidence showing that it has scientific and social benefits as well. Nowhere is this more so than in the tracking and prevention of diseases.

For instance Google Flu Trends tracks search queries and applies its trending algorithm to gain an understanding of where flu outbreaks are occurring. A 21 month study by John Hopkins University found that the app was exceptionally good at predicting when hospitals would start to see people coming in with flu symptoms.

Primary investigator of the study, Dr. Richard Rothman, said that the results were promising for “eventually developing a standard regional or national early warning system for frontline health care workers.”

Social media context

It could be argued however that social media is a better method of tracking the spread of infection because it provides you with better context. Back in January the American Journal of Tropical Medicine and Hygiene reported that tweets and other public 'status updates' were a better way of determining the spread of cholera in post-earthquake Haiti than official channels. The research was conducted by scientists at Children’s Hospital Boston and Harvard Medical School and with over 6,000 people having died from the disease in Haiti, it has serious implications in terms of disaster prevention.

“When we analyzed news and Twitter feeds from the early days of the epidemic in 2010, we found they could be mined for valuable information on the cholera outbreak that was available up to two weeks ahead of surveillance reports issued by the government health ministry,” said Rumi Chunara, PhD, of the Informatics Program at Children’s Hospital Boston, Research Fellow at Harvard Medical School, and the lead author of the study. “The techniques we employed eventually could be used around the world as an affordable and efficient way to quickly detect the onset of an epidemic and then intervene with such things as vaccines and antibiotics.”

Companies such as SickWeather are already getting in on the act and are providing the first consumer facing service. The app scans the public domain for mentions of around 24 different symptoms and then uses semantic analysis to determine whether they are actual mentions of an illness and then locates the updates and plots it onto a map.

BioDiaspora are another service looking to help monitor the spread of disease. BioDiaspora use various data, including insect populations, human demographics, and airline routes, to map outbreaks. These maps are then used by health agencies to plan responses.

The role of government

Not surprisingly governments are very keen on utilising these technologies to both provide a strong early warning against potential epidemics and to subsequently control their spread. The U.S. Department of Homeland Security has recently announced a partnership with Accenture to scour publically available data on Facebook, Twitter and blogs for mentions of illness.

"Rapidly collecting and understanding what information is being shared will help OHA [Office of Health Affairs] meet its mission to detect and respond to potential threats to national health security,” said John Matchette, head of Accenture's Public Safety agency work.

The UK government also highlighted the value of social media monitoring, but also raised concerns about the challenges involved, both in ensuring what is collected is both valid and accurate, and of course having the technological grunt to perform the analysis in good time. In their recent report on Reducing the Risk of Disaster Provention (embedded below) they highlight the role social media can play in amongst the various other tools available in helping to stop the spread of infections.

What is clear however is that this is a strong growth area and when placed alongside the many other areas of networked science provides excellent examples of what can be done when organisations think. socially.