Influenza Forecasting with Google Flu Trends

Dugas, Andrea Freyer; Jalalpour, Mehdi; Gel, Yulia; Levin, Scott; Torcaso, Fred; Igusa, Takeru; Rothman, Richard E.
February 2013
PLoS ONE;Feb2013, Vol. 8 Issue 2, p1
Academic Journal
Background: We developed a practical influenza forecast model based on real-time, geographically focused, and easy to access data, designed to provide individual medical centers with advanced warning of the expected number of influenza cases, thus allowing for sufficient time to implement interventions. Secondly, we evaluated the effects of incorporating a real-time influenza surveillance system, Google Flu Trends, and meteorological and temporal information on forecast accuracy. Methods: Forecast models designed to predict one week in advance were developed from weekly counts of confirmed influenza cases over seven seasons (2004–2011) divided into seven training and out-of-sample verification sets. Forecasting procedures using classical Box-Jenkins, generalized linear models (GLM), and generalized linear autoregressive moving average (GARMA) methods were employed to develop the final model and assess the relative contribution of external variables such as, Google Flu Trends, meteorological data, and temporal information. Results: A GARMA(3,0) forecast model with Negative Binomial distribution integrating Google Flu Trends information provided the most accurate influenza case predictions. The model, on the average, predicts weekly influenza cases during 7 out-of-sample outbreaks within 7 cases for 83% of estimates. Google Flu Trend data was the only source of external information to provide statistically significant forecast improvements over the base model in four of the seven out-of-sample verification sets. Overall, the p-value of adding this external information to the model is 0.0005. The other exogenous variables did not yield a statistically significant improvement in any of the verification sets. Conclusions: Integer-valued autoregression of influenza cases provides a strong base forecast model, which is enhanced by the addition of Google Flu Trends confirming the predictive capabilities of search query based syndromic surveillance. This accessible and flexible forecast model can be used by individual medical centers to provide advanced warning of future influenza cases.


Related Articles

  • Geographic and Temporal Trends in Influenzalike Illness, Japan. 1992-1999. Sakai, Takatsugu; Suzuki, Hiroshi; Sasaki, Asami; Saito, Reiko; Tanabe, Naohito; Taniguchi, Kiyosu // Emerging Infectious Diseases;Oct2004, Vol. 10 Issue 10, p1822 

    From 1992 to 1999, we analyzed >2.5 million cases of influenzalike illness (ILI). Nationwide influenza epidemics generally lasted 3-4 months in winter. Kriging analysis, which illustrates geographic movement, showed that the starting areas of peak ILI activity were mostly found in western Japan....

  • Circulation of HRSV in Belgium: From Multiple Genotype Circulation to Prolonged Circulation of Predominant Genotypes. Houspie, Lieselot; Lemey, Philippe; Keyaerts, Els; Reijmen, Eva; Vergote, Valentijn; Vankeerberghen, Anne; Vaeyens, Freya; De Beenhouwer, Hans; Van Ranst, Marc // PLoS ONE;Apr2013, Vol. 8 Issue 4, p1 

    Molecular surveillance of HRSV in Belgium for 15 consecutive seasons (1996–2011) revealed a shift from a regular 3-yearly cyclic pattern, into a yearly alternating periodicity where HRSV-B is replaced by HRSV-A. Phylogenetic analysis for HRSV-A demonstrated the stable circulation of GA2...

  • President's Message. Frye, Joyce // American Journal of Homeopathic Medicine;Winter2004/2005, Vol. 97 Issue 4, p242 

    Focuses on the global pandemic of Spanish influenza virus and A(H5N1) strain of influenza viruses. Advisory of the World Health Organization regarding the influenza strain; Physical signs and symptoms of the disease; Annual death rate of influenza.

  • Pandemic prevention schemes threaten diversity, experts warn. Waltz, Emily // Nature Medicine;Jun2006, Vol. 12 Issue 6, p598 

    The article reports that the fear of a bird flu pandemic is threatening the survival of many rare avian species. The H5N1 virus has struck at least 84 percent of known avian species by the order of governments to cull millions of both healthy and infected birds. The culling is affecting the...

  • Alarms ring over bird flu mutations. Butler, Declan // Nature;1/19/2006, Vol. 439 Issue 7074, p248 

    The article reports on the discovery of three mutations from the virus samples of the human outbreak of avian influenza in Turkey. The scientists say that at least two of these mutations look likely to make the virus better adapted to humans. Both samples from the Turkish teenagers show a...

  • FEARS SPREAD FASTER THAN AVIAN FLU. Howlett, Doug // Outdoor Life;Dec2005/Jan2006, Vol. 213 Issue 1, p23 

    The article reports on the public fear concerning the spread of avian flu worldwide. It includes information on how the disease spread and efforts being taken to address the worldwide pandemic.

  • Update: Influenza Activity -- United States, January 8-14, 2006.  // MMWR: Morbidity & Mortality Weekly Report;1/27/2006, Vol. 55 Issue 3, p74 

    This article offers update on influenza cases in the U.S. for the week ending January 14, 2006. During this period, the number of states reporting influenza activity increased. Overall, the percentage of specimens testing positive for influenza also increased. The percentage of deaths caused by...

  • Age- and Influenza Activity-Stratified Case Definitions of Influenza-Like Illness: Experience from Hospital-Based Influenza Surveillance in South Korea. Yang, Tae Un; Cheong, Hee Jin; Song, Joon Young; Lee, Jin Soo; Wie, Seong-Heon; Kim, Young Keun; Choi, Won Suk; Lee, Jacob; Jeong, Hye Won; Kim, Woo Joo // PLoS ONE;Jan2014, Vol. 9 Issue 1, p1 

    Objectives: This study aims to identify clinical case definitions of influenza with higher accuracy in patients stratified by age group and influenza activity using hospital-based surveillance system. Methods: In seven tertiary hospitals across South Korea during 2011–2012 influenza...

  • The Economic Impact of Pandemic Influenza in the United States: Priorities for Intervention. Meltzer, Martin I.; Cox, Nancy J. // Emerging Infectious Diseases;Sep/Oct99, Vol. 5 Issue 5, p659 

    We estimated the possible effects of the next influenza pandemic in the United States and analyzed the economic impact of vaccine-based interventions. Using death rates, hospitalization data, and outpatient visits, we estimated 89,000 to 207,000 deaths; 314,000 to 734,000 hospitalizations; 18 to...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics