Google Flu Trends collaborates with CDC for more accurate predictions

Google Flu Trends, a data program aimed at predicting flu outbreaks in the United States and 29 other countries, has been reconfigured to include data from the Centers for Disease Control and Prevention (CDC) to better forecast the flu season.

Google initially launched the program to rival CDC’s weekly flu activity and surveillance reports called FluView, and predict flu outbreaks weeks before the CDC. Since launching the Flu Trends website in 2008, Google has made several changes to the way it collects data. Flu Trends uses aggregated search information from millions of Google searches to “indicate when and where influenza was striking in real time,” says Christian Stefansen, senior software engineer for Google, on the company’s research blog.

In March, an article in Science magazine titled The Parable of Google Flu: Traps in Big Data Analysis exposed Flu Trends’ use of faulty data collection methods for the 2012-2013 flu season. The article called the program “big data hubris,” for  overestimating doctor visits for the flu compared with CDC reports.

“Quantity of data does not mean that one can ignore foundational issues of measurement and construct validity and reliability and dependencies among data. The core challenge is that most big data that have received popular attention are not the output of instruments designed to produce valid and reliable data amenable for scientific analysis,” the authors of the Science magazine wrote, which led to dozens of media reports questioning the relevancy of Flu Trends.

Stefansen says that Google soon will issue a technical paper detailing how the CDC data integrate with Google’s data. “As we’ve said since 2009, ‘This system is not designed to be a replacement for traditional surveillance networks or supplant the need for laboratory-based diagnoses and surveillance,’” Stefansen said, citing a paper about Flu Trends published in Nature magazine. “But we do hope it can help alert health professionals to outbreaks early, and in areas without traditional monitoring, and give us all better odds against the flu.”

Strengthening the Google Flu Trends model is another example of how Google continues to show interest in the healthcare field. In June, the company introduced GoogleFit, a health and fitness data tracker for Android mobile apps. Google Glass also has been used by physicians during surgeries and by medical schools, but has yet to see a wide release