Comparing Statistical Models to Predict Dengue Fever Notifications

Dengue fever (DF) is a serious public health problem in many parts of the world, and, in the absence of a vaccine, disease surveillance and mosquito vector eradication are important in controlling the spread of the disease. DF is primarily transmitted by the female Aedes aegypti mosquito. We compared two statistical models that can be used in the surveillance and forecast of notifiable infectious diseases, namely, the Autoregressive Integrated Moving Average (ARIMA) model and the Knorr-Held two-component (K-H) model. The Mean Absolute Percentage Error (MAPE) was used to compare models. We developed the models using used data on DF notifications in Singapore from January 2001 till December 2006 and then validated the models with data from January 2007 till June 2008. The K-H model resulted in a slightly lower MAPE value of 17.21 as compared to the ARIMA model. We conclude that the models' performances are similar, but we found that the K-H model was relatively more difficult to fit in terms of the specification of the prior parameters and the relatively longer time taken to run the models.

[1]  D. Chadee,et al.  Climate, mosquito indices and the epidemiology of dengue fever in Trinidad (2002–2004) , 2007, Annals of tropical medicine and parasitology.

[2]  Lee Ching Ng,et al.  The 2005 dengue epidemic in Singapore: epidemiology, prevention and control. , 2008, Annals of the Academy of Medicine, Singapore.

[3]  Philip D O'Neill,et al.  A tutorial introduction to Bayesian inference for stochastic epidemic models using Markov chain Monte Carlo methods. , 2002, Mathematical biosciences.

[4]  J. Heijne,et al.  Automated detection of infectious disease outbreaks: hierarchical time series models , 2006, Statistics in Medicine.

[5]  S I Hay,et al.  Etiology of interepidemic periods of mosquito-borne disease. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[6]  Alan L Rothman,et al.  Spatial and Temporal Clustering of Dengue Virus Transmission in Thai Villages , 2008, PLoS medicine.

[7]  A. Wilder-Smith,et al.  Meteorological factors and El Niño Southern Oscillation are independently associated with dengue infections , 2011, Epidemiology and Infection.

[8]  J. Hyman,et al.  Spatial and temporal dynamics of dengue fever in Peru: 1994–2006 , 2008, Epidemiology and Infection.

[9]  A. Mondini,et al.  Spatial correlation of incidence of dengue with socioeconomic, demographic and environmental variables in a Brazilian city. , 2008, The Science of the total environment.

[10]  D. Gubler,et al.  Dengue Prevention and 35 Years of Vector Control in Singapore , 2006, Emerging infectious diseases.

[11]  Muhammad Mamdani,et al.  Autoregression as a means of assessing the strength of seasonality in a time series , 2003, Population health metrics.

[12]  Kenneth D. Mandl,et al.  Time series modeling for syndromic surveillance , 2003, BMC Medical Informatics Decis. Mak..

[13]  Duane J. Gubler,et al.  Dengue and Dengue Hemorrhagic Fever , 1998, Clinical Microbiology Reviews.

[14]  A. Pettitt,et al.  Bayesian analysis of a time series of counts with covariates: an application to the control of an infectious disease. , 2001, Biostatistics.

[15]  Volker Schmid,et al.  A two-component model for counts of infectious diseases. , 2005, Biostatistics.

[16]  S. Rothenberg,et al.  Assessing the roles of temperature, precipitation, and ENSO in dengue re-emergence on the Texas-Mexico border region. , 2008, Salud publica de Mexico.

[17]  C. Depradine,et al.  Climatological variables and the incidence of Dengue fever in Barbados , 2004, International journal of environmental health research.

[18]  M. Pascual,et al.  Inapparent infections and cholera dynamics , 2008, Nature.

[19]  Edward L. Ionides,et al.  Plug-and-play inference for disease dynamics: measles in large and small populations as a case study , 2009, Journal of The Royal Society Interface.