×

zbMATH — the first resource for mathematics

Tracking epidemics with google flu trends data and a state-space SEIR model. (English) Zbl 1258.62102
Summary: We use Google Flu Trends data together with a sequential surveillance model based on state-space methodology to track the evolution of an epidemic process over time. We embed a classical mathematical epidemiology model (a susceptible-exposed-infected-recovered (SEIR) model) within the state-space framework, thereby extending the SEIR dynamics to allow changes through time. The implementation of this model is based on a particle filtering algorithm, which learns about the epidemic process sequentially through time and provides updated estimated odds of a pandemic with each new surveillance data point. We show how our approach, in combination with sequential Bayes factors, can serve as an online diagnostic tool for influenza pandemic. We take a close look at the Google Flu Trends data describing the spread of flu in the United States during 2003–2009 and in nine separate U.S. states chosen to represent a wide range of health care and emergency system strengths and weaknesses. This article has online supplementary materials.

MSC:
62P10 Applications of statistics to biology and medical sciences; meta analysis
92D30 Epidemiology
62L99 Sequential statistical methods
62D05 Sampling theory, sample surveys
65C60 Computational problems in statistics (MSC2010)
PDF BibTeX XML Cite
Full Text: DOI
References:
[1] American College of Emergency Physicians, The National Report Card on the State of Emergency Medicine (2009)
[2] Anderson R. M., Infectious Diseases of Humans: Dynamics and Control (1991)
[3] DOI: 10.1109/78.978374 · doi:10.1109/78.978374
[4] Atkinson K. E., Introduction to Numerical Analysis (1978) · Zbl 0402.65001
[5] DOI: 10.1109/JPROC.2007.893250 · doi:10.1109/JPROC.2007.893250
[6] DOI: 10.1214/10-STS325 · Zbl 1328.62541 · doi:10.1214/10-STS325
[7] DOI: 10.1098/rsif.2007.1292 · doi:10.1098/rsif.2007.1292
[8] DOI: 10.1016/j.jtbi.2005.11.026 · doi:10.1016/j.jtbi.2005.11.026
[9] DOI: 10.1098/rsif.2006.0161 · doi:10.1098/rsif.2006.0161
[10] DOI: 10.3934/mbe.2009.6.261 · Zbl 1166.62080 · doi:10.3934/mbe.2009.6.261
[11] Doucet A., Handbook of Nonlinear Filtering (2009)
[12] DOI: 10.1073/pnas.0600816103 · doi:10.1073/pnas.0600816103
[13] DOI: 10.1038/nature02541 · doi:10.1038/nature02541
[14] DOI: 10.1198/106186002835 · doi:10.1198/106186002835
[15] DOI: 10.1038/nature02007 · doi:10.1038/nature02007
[16] DOI: 10.1126/science.1176062 · doi:10.1126/science.1176062
[17] DOI: 10.3201/eid1209.041344 · doi:10.3201/eid1209.041344
[18] DOI: 10.1038/414748a · doi:10.1038/414748a
[19] DOI: 10.1111/1467-9868.00280 · Zbl 0976.62021 · doi:10.1111/1467-9868.00280
[20] DOI: 10.1038/nature07634 · doi:10.1038/nature07634
[21] DOI: 10.1098/rsif.2009.0151 · doi:10.1098/rsif.2009.0151
[22] DOI: 10.1137/S0036144500371907 · Zbl 0993.92033 · doi:10.1137/S0036144500371907
[23] Hindmarsh A., Scientific Computing pp 55– (1983)
[24] DOI: 10.1007/978-1-4020-6448-7_2 · doi:10.1007/978-1-4020-6448-7_2
[25] DOI: 10.1214/09-BA417 · Zbl 1330.62395 · doi:10.1214/09-BA417
[26] DOI: 10.3182/20090706-3-FR-2004.00129 · doi:10.3182/20090706-3-FR-2004.00129
[27] DOI: 10.1073/pnas.162282799 · doi:10.1073/pnas.162282799
[28] DOI: 10.1098/rspa.1927.0118 · JFM 53.0517.01 · doi:10.1098/rspa.1927.0118
[29] DOI: 10.1038/nature07084 · doi:10.1038/nature07084
[30] Kitagawa G., Journal of the American Statistical Association 93 pp 1203– (1998)
[31] DOI: 10.1080/01621459.1994.10476469 · doi:10.1080/01621459.1994.10476469
[32] DOI: 10.1198/jasa.2009.tm08047 · Zbl 1388.60133 · doi:10.1198/jasa.2009.tm08047
[33] DOI: 10.1007/978-1-4757-3437-9_10 · doi:10.1007/978-1-4757-3437-9_10
[34] DOI: 10.1093/aje/kwh092 · doi:10.1093/aje/kwh092
[35] Lopes H. F., Particle Learning for Sequential Bayesian Computation,” in Bayesian Statistics 9 (2011)
[36] DOI: 10.1002/for.1195 · Zbl 1217.91146 · doi:10.1002/for.1195
[37] DOI: 10.2202/1948-4690.1020 · doi:10.2202/1948-4690.1020
[38] DOI: 10.1111/j.1467-9868.2004.05561.x · Zbl 1046.62100 · doi:10.1111/j.1467-9868.2004.05561.x
[39] DOI: 10.1038/nature03063 · doi:10.1038/nature03063
[40] DOI: 10.1093/biostatistics/5.2.249 · Zbl 1096.62123 · doi:10.1093/biostatistics/5.2.249
[41] DOI: 10.1186/1742-4682-4-20 · doi:10.1186/1742-4682-4-20
[42] DOI: 10.1111/1467-985X.00125 · Zbl 04549851 · doi:10.1111/1467-985X.00125
[43] DOI: 10.1137/0904010 · Zbl 0518.65051 · doi:10.1137/0904010
[44] DOI: 10.1080/01621459.1999.10474153 · doi:10.1080/01621459.1999.10474153
[45] DOI: 10.1111/j.1467-9868.2007.00642.x · Zbl 1351.62177 · doi:10.1111/j.1467-9868.2007.00642.x
[46] Ristic B., Beyond the Kalman Filter: Particle Filters for Tracking Applications (2004) · Zbl 1092.93041
[47] DOI: 10.1177/0962280206071640 · Zbl 1122.62372 · doi:10.1177/0962280206071640
[48] DOI: 10.1109/78.978383 · doi:10.1109/78.978383
[49] DOI: 10.1503/cmaj.091807 · doi:10.1503/cmaj.091807
[50] U.S. Census Bureau., Annual Estimates of the Resident Population for the United States, Regions, States, and Puerto Rico: April 1, 2000 to July 1, 2009 (2009)
[51] Vaillant L., Eurosurveillance 14 pp 1– (2009)
[52] DOI: 10.1017/S0950268807008369 · doi:10.1017/S0950268807008369
[53] DOI: 10.1126/science.1090350 · doi:10.1126/science.1090350
[54] West M., Bayesian Forecasting and Dynamic Models (2nd ed.) (1997) · Zbl 0871.62026
[55] Yang Y., Science Express pp 729– (2009)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.