An ensemble prediction approach to weekly Dengue cases forecasting based on climatic and terrain conditions
Journal Title: Journal of Health and Social Sciences - Year 2017, Vol 2, Issue 3
Abstract
Introduction: Dengue fever has been one of the most concerning endemic diseases of recent times. Every year, 50-100 million people get infected by the dengue virus across the world. Historically, it has been most prevalent in Southeast Asia and the Pacific Islands. In recent years, frequent dengue epidemics have started occurring in Latin America as well. This study focused on assessing the impact of different short and long-term lagged climatic predictors on dengue cases. Additionally, it assessed the impact of building an ensemble model using multiple time series and regression models, in improving prediction accuracy. Materials and Methods: Experimental data were based on two Latin American cities, viz. San Juan (Puerto Rico) and Iquitos (Peru). Due to weather and geographic differences, San Juan recorded higher dengue incidences than Iquitos. Using lagged cross-correlations, this study confirmed the impact of temperature and vegetation on the number of dengue cases for both cities, though in varied degrees and time lags. An ensemble of multiple predictive models using an elaborate set of derived predictors was built and validated. Results: The proposed ensemble prediction achieved a mean absolute error of 21.55, 4.26 points lower than the 25.81 obtained by a standard negative binomial model. Changes in climatic conditions and urbanization were found to be strong predictors as established empirically in other researches. Some of the predictors were new and informative, which have not been explored in any other relevant studies yet. Discussion and Conclusions: Two original contributions were made in this research. Firstly, a focused and extensive feature engineering aligned with the mosquito lifecycle. Secondly, a novel covariate pattern-matching based prediction approach using past time series trend of the predictor variables. Increased accuracy of the proposed model over the benchmark model proved the appropriateness of the analytical approach for similar epidemic prediction research.
Authors and Affiliations
Sougata Deb, Cleta Milagros Libre Acedebo, Gomathypriya Dhanapal, Chua Matthew Chin Heng
Keywords
Related Articles
- EP ID EP232736
- DOI 10.19204/2017/nnsm3
- Views 121
- Downloads 0
Efficacy of education strategies concerning organ shortage: state-of-the-art and proposals
Introduction: Aim of this study was to review the underlying reasons for organ shortage and the efficacy of current education programs, in order to propose messages to modify socio-psychological feelings to donation. Di...
Case Reports: The core of practice-based evidence
A case report is a type of scientific paper that describes a patient-centred clinical pathway, which depends on medical doctor’s viewpoint, clinical insights and professional skills [1]. Case reports are particularly use...
Health inequalities, welfare state regimes and economic crisis: A comparative analysis in Sweden, Greece and Poland
Introduction: The aim of this paper is to explore individual-level determinants of health inequalities across three European countries (Sweden, Greece and Poland) with different welfare systems and differently affected b...
Spiritual well-being in the 21st century: It is time to review the current WHO’s health definition
Over the years, some critics argue that the dimension of spiritual well-being was missing from the World Health Organization’s (WHO) definition of health. Nevertheless, although the WHO’s definition has been criticized o...
“What’s that on your phone?” The aftermath of parents finding sexual and reproductive health messages on their children’s phone in coastal Kenya
Introduction: Digital health interventions allow young people to access information quickly and discreetly, but privacy remains a concern. This article explores what happens when a young user’s privately-access Sexual an...