Google Flu Trends Helps Hospitals Accurately Predict Influenza Cases
A new study from John Hopkins University shows that Google’s influenza oracle, Flu Trends, turns out to be a reliable way for hospitals to anticipate outbreaks or “seasons” of patients sick with the flu, possibly more reliable than using “outdated” government flu reports.
Conducted over the course of a 21-month period, the researchers found a “strong correlation between a rise in Internet searches for flu information, compiled by Google’s Flu Trends tool, and a subsequent rise in people coming into a busy urban hospital emergency room complaining of flu-like 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.” More from the press release:
Rothman and his team found the correlation between Internet searches and patient volume was most pronounced when researchers reviewed data showing a rise in search traffic for flu information and the number of children coming into the Hopkins pediatric emergency room with what doctors call influenza-like illness or ILI.
Although the science and medical community has generally accepted that a rise in flu search queries on Google Flu Trends corresponds with a rise in people reporting flu-like symptoms, the Johns Hopkins team is believed to be the first to show that the Flu Trends data strongly correlates with an upswing in emergency room activity.
Currently, emergency departments, hospitals and other health care providers rely on Centers for Disease Control and Prevention flu case reports provided during flu season, October to May, as a key way to track flu outbreaks.
Those CDC reports currently dictating the preparation of hospitals for influenza outbreaks, the researchers say, are simply too slow to reach health care providers in order to be of any use. In the Google era of search technology, there’s a reason that news and cultural trends are described as “viral” when they become popular: they catch on and they spread among people quickly. If videos of politicians doing idiotic things at state fairs can race across an entire country within the period of a few hours in the afternoon, there’s no reason the CDC shouldn’t be able to quickly assess influenza outbreaks in a timely fashion. As a result, Rothman concludes, “[the CDC reports] don’t provide frontline health care workers with a strong tool to prepare day-to-day for a surge in flu cases, even as the flu is spreading in real time. Google Flu Trends, on the other hand, collects and provides data on search traffic for flu information on a daily basis by detecting and analyzing certain flu-related search terms.”
Mark one more in the win column for Team Google, who’s now officially doing better at helping your community stave off flu outbreaks than the United States government agency charged with that same task.