Google Flu Botched Predictions, Overestimated Flu Amid Record Season
February 18, 2013 11:44 AM
comment(s) - last by
Typically accurate algorithm may need tweaking to deal with new trends
Launched in 2008
Google Flu Trends
is one of Google Inc.'s (
) most intriguing internet services. Leveraging Google's mastery of data mining and industry-leading search engine position, the system injects data on health-related searches into a complex model which spits out an estimation of the number of people in each region that are infected with the flu virus.
I. Flu Trends' Bad Forecast
The system performs extraordinarily well, typically matching up closely with data from the
Centers for Disease Control
(CDC). The system typically is several days ahead of CDC predictions in 29 countries and today also tracks a second disease -- dengue.
But this flu season was
a rough one
for the Google service. Google badly over predicted the Christmas peak of flu season, estimating that over 10 percent of the U.S. population had flu, versus the CDC's data, which showed only around 6 percent had it.
Google Flu overpredicted, while Flu Near You underpredicted. [Image Source: Nature]
So what happened?
Experts believe part of the problem was public fear influencing search behavior in an unusual way. The flu season got off to its earliest seasonal start in nearly a decade, starting in November and peaking in December. Of the three major flu virus strains, the most virulent strain -- H3N2n -- dominated, as in the severe 2003 outbreak.
There were multiple deaths, particularly among the elderly from the outbreak. As a result, the mass media latched onto the story and focus a great deal of coverage on the flu -- more so than usual. Experts say that may have led people to increase searches for flu terms, even if they didn't have flu.
It was also a bad season for norovirus outbreaks, which may have led to people searching for flu terms. Norovirus is a separate pathogen that manifests itself via intestinal symptoms. However, many in the public mistake norovirus infections for flu.
II. Self-Tracking Efforts Also Miss
Professor John Brownstein
that the miss by Google shows the difficulty in adapting algorithms to new variables. He comments, "You need to be constantly adapting these models, they don’t work in a vacuum. You need to recalibrate them every year."
Professor Brownstein helps maintain "
Flu Near You
Boston Children's Hospital
project which tracks flu in the U.S. via volunteer self-reporting. The 2011 program tracks a sample set of 70,000 people and has 46,000 participants (who report on their own health and health of family members).
Tracking the flu-virus in real time is a daunting challenge. [Image Source: Navco]
To Google's credit, Flu Near You missed nearly as badly, underestimating the peak infection rate. It peaked around a little over 4 percent. It's unclear why that underestimation happened.
Digital tracking of influenza-like illness (ILI) -- symptoms such as fever and sinus issues -- first began in 1985 in France with the creation of the Sentinelles network. Today France's GrippeNet.fr continues that tradition. Similar to Flu Near You, GrippeNet uses self-reporting from volunteers and has 5,500 participants.
The CDC's tracking comes directly from a network of 2,700 health institutions, which cover 30 million patients.
III. What About Twitter Tracking?
The misses of Flu Near You and Google Flu Trends open the door to new analysis projects. A pair of new efforts --
-- look to track Twitter posts to determine flu rates. Johns Hopkins University Professor Michael Paul argues that Twitter monitoring may offer less noise than search term monitoring, while offering big sample sets than self-monitoring.
He comments, "I suspect that passive monitoring of social media will always yield more data than systems that rely on people to actively respond to surveys, like Flu Near You."
Some are turning to Twitter for flu tracking.
But some are skeptical of Twitter-mining.
, head of the CDC’s Influenza Surveillance and Outbreak Response Team, argues that Twitter crowdsourcing is less effect that search-term efforts, because Twitter's userbase tends to be younger, less reliable users. She comments, "The Twitter analyses have much less promise."
The 2012 miss was the
worst since 2009
for Google, which led to some major algorithmic adjustments. In 2009 Google under predicted the H1N1 swine flu outbreak. That mistake was the subject of a
paper entitled "
Assessing Google Flu Trends Performance in the United States during the 2009 Influenza Virus A (H1N1) Pandemic
This article is over a month old, voting and posting comments is disabled
RE: for Profit Healthcare, so much for the Hypocratic Oath
2/19/2013 5:49:27 PM
Don't believe colds are life-threatening. The flu can be life-threatening for many, especially the elderly and the very young.
"Nowadays you can buy a CPU cheaper than the CPU fan." -- Unnamed AMD executive
Google Helps to Track Swine Flu, Twitter Catches Criticism
April 28, 2009, 11:29 AM
Google Predicts the Flu
November 12, 2008, 10:10 AM
Nail Polish May Soon be Able to Detect Date Rape Drugs
August 26, 2014, 7:57 AM
SpaceX Falcon 9-R Rocket Suffers Malfunction, Self-Destructs During Test Flight
August 23, 2014, 9:36 AM
Texas Chosen as Site for SpaceX's First Commercial Launchpad
August 5, 2014, 1:44 PM
South Carolina Prison Finds Crashed Drone Carrying Drugs, Phones
August 1, 2014, 2:49 PM
NASA's Mars 2020 Rover Gains Seven New Instruments for Exploration
August 1, 2014, 1:30 PM
NASA Opportunity Rover Breaks Record for Most Miles Traveled on Another Planet
July 29, 2014, 1:38 PM
Most Popular Articles
Numerous Leaks Detail 4.7" iPhone 6 Processor, RAM, Cellular and NFC Capabilities
August 29, 2014, 10:37 PM
Windows 9: "Upgrade Now" Button Coming for Enterprise Updates, ARM Preview in H1 2015
August 26, 2014, 8:00 PM
L.A. Unified School District’s Apple iPad Contract Canceled Following Heavy Criticism
August 26, 2014, 12:37 PM
Apple Builds Not-So-Secret Secret 3-Story Tower for iPhone 6/iWatch Unveil
August 28, 2014, 3:41 PM
Netflix Accuses Comcast of Ripping Off Customers, Files to Block Merger
August 26, 2014, 5:49 PM
Latest Blog Posts
Space Terrorism is a Looming Threat For the United States
Apr 23, 2014, 7:47 PM
Facebook Aims to Provide Internet to "Every Person in the World" with Drones, Satellites
Apr 1, 2014, 10:20 AM
Retail Mobile Sites Experience Outages in Light of Simplexity's Bankruptcy
Mar 14, 2014, 8:48 AM
Tesla vs. BMW: Who Has the Safer EV?
Feb 1, 2014, 2:56 PM
Justice Leaks Details of Next HTC One Two Flagship Phone
Dec 5, 2013, 4:04 PM
More Blog Posts
Copyright 2014 DailyTech LLC. -
Terms, Conditions & Privacy Information