BehindTheMedspeak: Google Flu Tracker is nothing to sniff[le] at

Just unveiled yesterday, Google's latest offering — google.org/flutrends — takes the results of millions of searches with phrases like "flu symptoms," mixes them with Google's special proprietary algorithm sauce and produces a real-time map (above) showing where in the U.S. it's hitting.

Miguel Helft's front page story in today's New York Times on the new new thing in infectious disease tracking follows.

Google Uses Searches to Track Flu’s Spread

There is a new common symptom of the flu, in addition to the usual aches, coughs, fevers and sore throats. Turns out a lot of ailing Americans enter phrases like “flu symptoms” into Google and other search engines before they call their doctors.

That simple act, multiplied across millions of keyboards in homes around the country, has given rise to a new early warning system for fast-spreading flu outbreaks, called Google Flu Trends.

Tests of the new Web tool from Google.org, the company’s philanthropic unit, suggest that it may be able to detect regional outbreaks of the flu a week to 10 days before they are reported by the Centers for Disease Control and Prevention.

In early February, for example, the C.D.C. reported that the flu cases had recently spiked in the mid-Atlantic states. But Google says its search data show a spike in queries about flu symptoms two weeks before that report was released. Its new service at google.org/flutrends analyzes those searches as they come in, creating graphs and maps of the country that, ideally, will show where the flu is spreading.

The C.D.C. reports are slower because they rely on data collected and compiled from thousands of health care providers, labs and other sources. Some public health experts say the Google data could help accelerate the response of doctors, hospitals and public health officials to a nasty flu season, reducing the spread of the disease and, potentially, saving lives.

“The earlier the warning, the earlier prevention and control measures can be put in place, and this could prevent cases of influenza,” said Dr. Lyn Finelli, lead for surveillance at the influenza division of the C.D.C. From 5 to 20 percent of the nation’s population contracts the flu each year, she said, leading to roughly 36,000 deaths on average.

The service covers only the United States, but Google is hoping to eventually use the same technique to help track influenza and other diseases worldwide.

“From a technological perspective, it is the beginning,” said Eric E. Schmidt, Google’s chief executive.

The premise behind Google Flu Trends — what appears to be a fruitful marriage of mob behavior and medicine — has been validated by an unrelated study indicating that the data collected by Yahoo, Google’s main rival in Internet search, can also help with early detection of the flu.

“In theory, we could use this stream of information to learn about other disease trends as well,” said Dr. Philip M. Polgreen, assistant professor of medicine and epidemiology at the University of Iowa and an author of the study based on Yahoo’s data.

Still, some public health officials note that many health departments already use other approaches, like gathering data from visits to emergency rooms, to keeping daily tabs on disease trends in their communities.

“We don’t have any evidence that this is more timely than our emergency room data,” said Dr. Farzad Mostashari, assistant commissioner of the Department of Health and Mental Hygiene in New York City.

If Google provided health officials with details of the system’s workings so that it could be validated scientifically, the data could serve as an additional, free way to detect influenza, said Dr. Mostashari, who is also chairman of the International Society for Disease Surveillance.

A paper on the methodology of Google Flu Trends is expected to be published in the journal Nature.

Researchers have long said that the material published on the Web amounts to a form of “collective intelligence” that can be used to spot trends and make predictions.

But the data collected by search engines is particularly powerful, because the keywords and phrases that people type into them represent their most immediate intentions. People may search for “Kauai hotel” when they are planning a vacation and for “foreclosure” when they have trouble with their mortgage. Those queries express the world’s collective desires and needs, its wants and likes.

Internal research at Yahoo suggests that increases in searches for certain terms can help forecast what technology products will be hits, for instance. Yahoo has begun using search traffic to help it decide what material to feature on its site.

Two years ago, Google began opening its search data trove through Google Trends, a tool that allows anyone to track the relative popularity of search terms. Google also offers more sophisticated search traffic tools that marketers can use to fine-tune ad campaigns. And internally, the company has tested the use of search data to reach conclusions about economic, marketing and entertainment trends.

“Most forecasting is basically trend extrapolation,” said Hal Varian, Google’s chief economist. “This works remarkably well, but tends to miss turning points, times when the data changes direction. Our hope is that Google data might help with this problem.”

Prabhakar Raghavan, who is in charge of Yahoo Labs and the company’s search strategy, also said search data could be valuable for forecasters and scientists, but privacy concerns had generally stopped it from sharing it with outside academics.

Google Flu Trends avoids privacy pitfalls by relying only on aggregated data that cannot be traced to individual searchers. To develop the service, Google’s engineers devised a basket of keywords and phrases related to the flu, including thermometer, flu symptoms, muscle aches, chest congestion and many others.

Google then dug into its database, extracted five years of data on those queries and mapped it onto the C.D.C.’s reports of influenzalike illness. Google found a strong correlation between its data and the reports from the agency, which advised it on the development of the new service.

“We know it matches very, very well in the way flu developed in the last year,” said Dr. Larry Brilliant, executive director of Google.org. Dr. Finelli of the C.D.C. and Dr. Brilliant both cautioned that the data needed to be monitored to ensure that the correlation with flu activity remained valid.

Google also says it believes the tool may help people take precautions if a disease is in their area.

Others have tried to use information collected from Internet users for public health purposes. A Web site called whoissick.org, for instance, invites people to report what ails them and superimposes the results on a map. But the site has received relatively little traffic.

HealthMap, a project affiliated with the Children’s Hospital Boston, scours the Web for articles, blog posts and newsletters to create a map that tracks emerging infectious diseases around the world. It is backed by Google.org, which counts the detection and prevention of diseases as one of its main philanthropic objectives.

But Google Flu Trends appears to be the first public project that uses the powerful database of a search engine to track a disease.

“This seems like a really clever way of using data that is created unintentionally by the users of Google to see patterns in the world that would otherwise be invisible,” said Thomas W. Malone, a professor at the Sloan School of Management at M.I.T. “I think we are just scratching the surface of what’s possible with collective intelligence.”

...................

Robert A. Guth's report in this morning's Wall Street Journal follows.

Sniffly Surfing: Google Unveils Flu-Bug Tracker




You can Google to get a hotel, find a flight and buy a book. Now you may be able to use Google to avoid the flu.

One month into flu season, Google Inc. on Tuesday opened a free Web service that the Internet company says can show if the number of influenza cases is increasing in areas around the U.S., earlier than many existing methods.

The service, called Flu Trends (www.google.org/flutrends), uses computers to crunch millions of Internet searches people make for keywords that might be related to the flu — for instance "cough," or "fever." It displays the results on a map of the U.S. and shows a chart of changes in flu activity around the country. The data is meaningful because the Google arm that created Flu Trends found a strong correlation between the number of Internet searches related to the flu and the number of people reporting flu symptoms.

Google built the service with the guidance of the Centers for Disease Control and Prevention, the U.S. government's public-health watchdog that runs a range of flu-surveillance systems. Flu Trends can be a complement to those tools, health officials say.

Flu Trends "maps very closely to the influenza-like trends that we see in the U.S.," says Lyn Finelli, lead of the influenza surveillance team at CDC's headquarters in Atlanta.

The service adds Google to a growing number of Web sites that are trolling, culling and crunching Internet data in ways to better pinpoint and predict where diseases are hitting around the world. The sites use varying degrees of human and computer methods for detecting outbreaks and many have historically been aimed at doctors and health-care professionals. Google executives say their service could also appeal to consumers.

In any given year, between 5% and 20% of Americans can catch the flu, depending upon the strength of a particular flu virus and other factors, the CDC says. Around 145 million doses of flu vaccines will be available this flu season, which generally runs from October to May and typically peaks in February.

Finding a new tool to stave off infection is important to Maureen Rinehart, a 28-year-old kindergarten teacher in San Francisco. Ms. Rinehart says daily contact with her kids means she gets sick about once a month. She got a flu shot about two weeks ago and is armed with hand sanitizer in the classroom.

"They're really snotty and they want to hold hands with you; you know how it is with the little guys," says Ms. Rinehart. So if the Google service shows flu cases are rising, she says, "you could bulk up on vitamins and wash your hands more — all the necessary things you should do."

The Google service is the brainchild of Google.org, a three-year-old group at the Mountain View, Calif., company that works on areas for the public good — such as renewable energy — that may or may not have a direct financial benefit to Google. The company won't use advertising on the Flu Trends site.

The Google group examined flu-related keywords over five years, noting times when searches of those terms surged. It then compared those times to CDC records and found a strong correlation between when people searched flu keywords and when people have had flu-like symptoms. It spent the past year testing new search results against data from the CDC, tweaking its software to make its results more accurate, Google executives said.

The Flu Trends site displays results of its analysis in a five-tier scale of flu activity ranging from "minimal" to "intense," with a middle point of "moderate." The site includes CDC flu prevention messages, a flu vaccination locator and links to flu-related news items.

"It's still quite experimental," says Jeremy Ginsberg, Google's lead engineer on Flu Trends. "We feel it's an interesting, unique way to track disease outbreaks."

In 2003, the Canadian government and other organizations used versions of these data-collection and health sites to detect early signs of the SARS virus in China. The Canadian service — the Global Public Health Intelligence Network — automatically scans Web sites and news sources in seven languages for information on disease outbreaks, contaminated food and water, natural disasters and other health risks around the world. It charges a fee based on the type of organization that accesses it and its usage.

At Harvard Medical School's Children's Hospital Boston, a site called HealthMap crawls through 24,000 Web sites looking for disease-related terms. Results appear on a world map, which has colored markers for dengue fever, avian flu and other diseases.

Google.org last month started funding HealthMap to find ways to collaborate with ProMED, a site that uses people to gather clues about diseases from the Web and from other sources.

The Web-based services have shortcomings. The most accurate way to measure a disease outbreak is by the number of actual cases confirmed by a laboratory. By tracking keywords in news stories and search results, the Web sites can't guarantee that they are finding actual outbreaks.

But what they lose in accuracy, the sites may make up in speed. Getting accurate data on real disease cases requires people to be tested for a disease and that data to be collected by public-health organizations. While the CDC and other organizations do this kind of research, it takes time.

Reducing that time is crucial for combating influenza, which can manifest itself one to three days after a person comes into contact with the virus. "If you get data that's not very timely one or two weeks old it's possible that the outbreak has already peaked," the CDC's Ms. Finelli says.

Still, some consumers question how helpful the new Google health service will be for them. Tony Deen, a 22-year-old recent college grad in San Francisco, says he hasn't had the flu since he was a kid and uses health Web sites only when he has a medical problem. "It's not like I can flee the city if the flu is coming," Mr. Deen says. But "it might convince me to get a flu shot if people are getting sick."