Your tweets could help track the spread of seasonal flu in real time, say scientists who have developed a new model that uses Twitter posts to predict how the infection may affect a population.
Researchers from Northeastern University in the US gathered tweets along with parameters of each season’s epidemic, such as the incubation period of the disease, the immunisation rate, how many people an individual with the virus can infect, and the viral strains present.
They applied forecasting and other algorithms to the key parameters informed by the Twitter data.
Researchers then matched the resulting simulations with the surveillance data generated by the US Centre for Disease Control (CDC) and clinical and personal reports of influenza-like illnesses from the three countries. They analysed the evolving dynamics revealed in the past data, and were able to select the model that would most likely forecast the future.
Researchers then tested the model against official influenza surveillance systems. They found that it accurately forecast the disease’s evolution up to six weeks in advance significantly earlier than other models.
“It will enable public health agencies to plan ahead in allocating medical resources and launching campaigns that encourage individuals to take preventative measures such as vaccination and increased hand washing,” said Alessandro Vespignani, from Northeastern University.
“In the past, we had no knowledge of initial conditions for the flu,” Vespignani said. “The initial conditions — which show where and when an epidemic began as well as the extent of infection — function as a launching pad for forecasting the spread of any disease,” he said.
The explicit modelling of the disease’s parameters — information about the dynamics of the disease itself — sets the model apart from others in the challenge, researchers said.
For example, researchers could identify the week when the epidemic would reach its peak and the magnitude of that peak with an accuracy of 70 to 90 per cent six weeks in advance of the event.
“By capturing the key parameters, we could track how serious the flu was each year compared with every other year and see what was driving the spread,” said Qian Zhang from Northeastern University.