What if Google knew before anyone else that a flu outbreak was
putting you at heightened risk of getting sick? And what if it could
alert you, your doctor and your local public health officials before
the muscle aches and chills kicked in?
That, in essence, is the promise of Google Flu Trends, a Web tool
that Google.org, the company's philanthropic unit, announced
Tuesday, just as the flu season was starting.
Google Flu Trends is based on the idea that people feeling sick
are likely to turn to the Web for information, searching on Google
for phrases like "flu symptoms" or "muscle aches." Google Flu Trends
tracks such queries and charts their ebb and flow, broken down by
regions across the United States.
Google.org said this first version of Google Flu Trends "is just
a start" and it hoped to "explore other countries, languages, and
diseases in the future."
Early tests suggest that the service might be able to detect
regional outbreaks of the flu between a week and 10 days before they
are reported by the U.S. Centers for Disease Control and Prevention.
Some public health experts say that 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.
It could also offer a dose of comfort to stricken individuals in
knowing that a bug is going around.
"This could conceivably provide as early a warning of an outbreak
as any system," said Lyn Finelli of the influenza division of the
Centers for Disease Control and Prevention.
"The earlier the warning, the earlier prevention and control
measures can be put in place, and this could prevent cases of
influenza," Finelli said.
Between 5 percent and 20 percent of the population of the United
States contracts the flu each year, Finelli said, leading to an
average of 36,000 deaths.
Google Flu Trends is the latest indication that the words typed
into search engines like Google can be used to track the collective
interests and concerns of millions of people, and even to forecast
the future.
"This is an example where Google can use the incredible systems
that we have to come up with an interesting, predictive result,"
said Eric Schmidt, the Google chief executive. "From a technological
perspective, it is the beginning."
The premise behind Google Flu Trends 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. The study, by the University of Iowa College
of Medicine, suggested that the technique could be applied to the
surveillance of other diseases in the future.
Still, some public health officials note that many health
departments already use other techniques, like gathering data from
visits to emergency rooms, to keep 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 Farzad Mostashari, assistant commissioner
of the New York City Department of Health.
If Google could provide health officials with more details of how
its system works, the data could be an additional way to detect
influenza that may prove quite valuable, said Mostashari, who is
also chairman of the International Society for Disease Surveillance.
Researchers have long said that the data sprinkled throughout the
Web could be used to make predictions. There are commercial Web
sites that mine that information to predict airfares and home
prices.
But the data collected by search engines is particularly
powerful, because the keywords and phrases that people type into
search engines represent their most immediate intentions. People may
search for "Kauai hotel" when they are planning a vacation and for
"foreclosure" when they get in trouble with their mortgage. Those
queries express the world's collective desires and needs, its wants
and likes.
Research at Yahoo suggests that increases in searches for certain
terms can help predict events. Yahoo has begun using search traffic
to make decisions about ranking news articles on its site.
Two years ago, Google began opening up its search data through
Google Trends, a tool that allows anyone to track the popularity of
search terms. It also offers more sophisticated search traffic tools
that marketers can use to test advertising campaigns.
Google Flu Trends is based on the same idea. Google's engineers
created 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 the data onto the Centers
for Disease Control and Prevention's reports of "influenza-like
illness," which the agency collects from laboratories, health care
providers and other sources. Google found an almost perfect
correlation between its data and the center's reports.
"We know it matches very, very well in the way flu developed in
the last year," said Larry Brilliant, executive director of
Google.org.
Finelli and Brilliant cautioned that the data needed to be
monitored to ensure that the correlation with flu trends remained
valid.
Other projects have tried to use information collected from
Internet users for public health purposes. A Web site called
whoissick.org, for instance, invites people to post information
about what ails them and superimposes the results on a map. But the
site has received little traffic, so its usefulness is limited.
HealthMap, a project affiliated with the Children's Hospital in
Boston, scours the Web for news articles, blog posts and electronic
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 disease as one of its main goals.
But Google Flu Trends appears to be the first public project that
uses the powerful database of a search engine to track the emergence
of a disease. The approach has the potential to detect other
diseases.
"In theory, we could use this stream of information to learn
about other disease trends as well," said Philip Polgreen, assistant
professor of medicine and epidemiology at the University of Iowa.
Polgreen is a co-author of the study that used Yahoo's search data
to detect influenza, which will be published next month.
(C) 2008 International Herald Tribune. via ProQuest Information and Learning Company; All Rights Reserved