NPR logo Disease Sleuths Analyze Google Searches To Stop Infections

Public Health

Disease Sleuths Analyze Google Searches To Stop Infections

Google has allowed some researchers to sift through Google data searches to identify disease trends.

Google has allowed some researchers to sift through Google data searches to identify disease trends. Meredith Rizzo/NPR hide caption

toggle caption Meredith Rizzo/NPR

With sexually transmitted diseases on the rise, researchers at the University of Illinois at Chicago think they might have a powerful new weapon to fight their spread: Google searches.

The company behind the Web's leading search engine has quietly begun giving researchers access to its data troves to develop analytical models for tracking infectious diseases in real time or close to it. UIC is one of at least four academic institutions that have received access so far, along with the Centers for Disease Control and Prevention, Google said.

Researchers can mine Google data to identify search terms that spiked during previous upticks in a particular disease. Then, researchers can measure the frequency of those searches in real time to estimate the number of emerging cases. For instance, a jump in gonorrhea might coincide with more people searching "painful urination" or other symptoms.

"If this works, it could revolutionize STD surveillance," said Supriya Mehta, an associate professor of epidemiology at the UIC School of Public Health.

Search trends can be broken down by city and state, weighted by significance and combined with other data to produce a snapshot of where disease is spreading well before public health agencies report the number of verified cases.

"We're hoping for a bit of creativity to flourish around this," said Christian Stefansen, a senior engineer working on disease trends at Google, during a visit to UIC in November. He spoke to about 100 people about lessons Google has learned in its attempts to mine data for public health. "There's no shortage of communicable diseases, sadly," he said.

Sexually transmitted diseases are a growing problem that is being worsened by the progress of antibiotic-resistant strains of microbes, according to the CDC. The agency reported in November that STDs — including chlamydia, gonorrhea and syphilis — all increased in 2014.

Chlamydia set a record of more than 1.4 million new cases. STD diagnoses are highest among 15- to 24-year-olds, a group that also happens to be full of heavy users of technology, including Google search.

Public health researchers have long wanted to use Internet searches to track infectious diseases. But they were limited to the publicly available Google Trends tool. It has drawbacks, including a restriction on the number of phrases that can be tracked and an omission of searches that fall below certain undisclosed volume thresholds.

Google invited researchers to apply for unrestricted access to search data in August, as the company discontinued its own real-time tracking tool, Flu Trends. Launched in 2008, Flu Trends broke ground but consistently overpredicted cases.

Google came under fire from some researchers for not disclosing its methodology. According to a paper published in Science by some independent researchers, Flu Trends stumbled because it used search terms that correlated with flu season but not actual cases of the flu. The tracking tool failed to adjust after Google introduced "search suggest" and other features to guide users to information, the critics said.

Google is the most commonly used search engine in the U.S., with a 63.9 percent market share of desktop searches in October, according to comScore, a Reston, Va.-based analytics company.

Google searches can be tracked by city, providing more refined data than the national and multistate data reported by the CDC. "It's a phenomenal data feed to work with, and there's a lot that can be done with it from a research standpoint," said Jeffrey Shaman, an associate professor in environmental health sciences at Columbia University's Mailman School of Public Health, which was given access to the data.

But no matter how great Google's search data may be, some researchers say they can't rely on the company alone.

Take flu, which is the farthest along of any real-time disease-tracking effort, with at least nine teams working with the CDC on 12 forecasting models for the current season. Boston Children's Hospital and Harvard Medical School are launching HealthMap FluCast, a tool that gives one- and two-week predictions by incorporating Google searches with the CDC's weekly surveillance reports, electronic medical records from athenahealth; and Flu Near You, a website of patient-reported data.

In a recent paper, FluCast's developers say multiple data sources will allow them to produce "more accurate and robust real-time flu predictions than any other existing system." FluCast co-founder John Brownstein said in an interview that the tool will eventually include information from Twitter, though it's "taking time to get the data in order." On Monday, HealthMap expects to roll out the more sophisticated tracking tool for flu, called FluTrends.

Amy Johnson, a PhD candidate in public health at the University of Illinois-Chicago, is working on a model to use Google searches to track the spread of sexually transmitted diseases in real time. i

Amy Johnson, a PhD candidate in public health at the University of Illinois-Chicago, is working on a model to use Google searches to track the spread of sexually transmitted diseases in real time. /Mary Chris Jaklevic for NPR hide caption

toggle caption /Mary Chris Jaklevic for NPR
Amy Johnson, a PhD candidate in public health at the University of Illinois-Chicago, is working on a model to use Google searches to track the spread of sexually transmitted diseases in real time.

Amy Johnson, a PhD candidate in public health at the University of Illinois-Chicago, is working on a model to use Google searches to track the spread of sexually transmitted diseases in real time.

/Mary Chris Jaklevic for NPR

While flu patients may find it therapeutic to tweet about their high fevers, pounding headaches and extreme exhaustion, people who suspect they have a sexually transmitted illness are unlikely to vent about their symptoms via social media.

"In no way shape or form is someone going to tweet, 'I have bumps on my vulva. Do you think it's an STI?' " said Amy Johnson, a UIC doctoral candidate who's been studying the feasibility of using search data for tracking sexually transmitted infections.

Mehta, her thesis adviser, agreed: "Because STDs are so stigmatized and personal, Twitter is not going to work for that."

Robust STD tracking systems might incorporate additional search services, such as Yahoo and Bing, as well as weekly surveillance reports from local health departments, Johnson said.

Reliance on one data source is risky if it's a private company, such as Google, which could halt access at any time.

Even the CDC is hedging its bets. Matthew Biggerstaff, an epidemiologist who leads flu tracking efforts there, said the national health agency is exploring whether it can measure visits to its own website as a reliable disease indicator "so we have something that's more of a public data set."

And it remains to be seen just how real-time data could be used by public health agencies and providers. In coming months, the CDC will be asking state and local health departments what type of flu data they want — real-time versus three-month forecasting, for example — and how they would use it, Biggerstaff said.

"Producing it and showing that it works is different than operationalizing it," Biggerstaff said. "It's still new in terms of incorporating it into a public health data stream."

Then, there's the issue of public trust. Researchers emphasize that no one's privacy will be violated. Even with their unprecedented data access, researchers won't be able to identify who performs queries, what their sex or ethnicity is, or even what neighborhoods people live in, Johnson said.

"I'm not going to knock on their door and tell their wife or their husband they have a sexually transmitted infection," Johnson said. "It's important for people on the individual level to know it's about community health."

Updated Dec. 11, 2:30 p.m.: This story was updated to reflect HealthMap's expected launch of Flu Trends, a more sophisticated flu tool, on Monday.

Mary Chris Jaklevic is a freelance health and environment writer based in Chicago. She is on Twitter: @mcjaklevic.

Comments

 

Please keep your community civil. All comments must follow the NPR.org Community rules and terms of use, and will be moderated prior to posting. NPR reserves the right to use the comments we receive, in whole or in part, and to use the commenter's name and location, in any medium. See also the Terms of Use, Privacy Policy and Community FAQ.