Assessment of land use factors associated with dengue cases in Malaysia using Boosted Regression Trees

Yoon Ling Cheong,Pedro J Leitão,Tobia Lakes

doi:10.1016/j.sste.2014.05.002

Yoon Ling Cheong, Pedro J Leitão + Show 1 more

Open Access

https://doi.org/10.1016/j.sste.2014.05.002

Copy DOI

Abstract

The transmission of dengue disease is influenced by complex interactions among vector, host and virus. Land use such as water bodies or certain agricultural practices have been identified as likely risk factors for dengue because of the provision of suitable habitats for the vector. Many studies have focused on the land use factors of dengue vector abundance in small areas but have not yet studied the relationship between land use factors and dengue cases for large regions. This study aims to clarify if land use factors other than human settlements, e.g. different types of agricultural land use, water bodies and forest are associated with reported dengue cases from 2008 to 2010 in the state of Selangor, Malaysia. From the correlative relationship, we aim to generate a prediction risk map. We used Boosted Regression Trees (BRT) to account for nonlinearities and interactions between the factors with high predictive accuracies. Our model with a cross-validated performance score (Area Under the Receiver Operator Characteristic Curve, ROC AUC) of 0.81 showed that the most important land use factors are human settlements (model importance of 39.2%), followed by water bodies (16.1%), mixed horticulture (8.7%), open land (7.5%) and neglected grassland (6.7%). A risk map after 100 model runs with a cross-validated ROC AUC mean of 0.81 (±0.001 s.d.) is presented. Our findings may be an important asset for improving surveillance and control interventions for dengue.

Highlights

IntroductionDengue fever (DF) and dengue haemorrhagic fever (DHF) are the most important vector-borne diseases⇑ Corresponding author at: Geography Department, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany
Dengue fever (DF) and dengue haemorrhagic fever (DHF) are the most important vector-borne diseasesAbbreviations: DF, dengue fever; DHF, dengue haemorrhagic fever; VBD, vector-borne diseases; BRT, Boosted Regression Trees; ELISA, IgM capture enzyme-linked immunosorbent assay; API, Application Programming Interface; GLM, generalized linear model; GAM, generalized addictive model; DV, dengue virus; lr, learning rate; tc, tree complexity; ROC AUC, Receiver Operating Characteristic Area Under the Curve; IVM, Integrated Vector Management.⇑ Corresponding author at: Geography Department, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany
From the correlation analysis we found no high rank correlations between any pair of predictor variables so that we continued with a model that included all land use variables

Summary

Introduction

Dengue fever (DF) and dengue haemorrhagic fever (DHF) are the most important vector-borne diseases⇑ Corresponding author at: Geography Department, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany. Dengue fever (DF) and dengue haemorrhagic fever (DHF) are the most important vector-borne diseases. In recent decades the risk of dengue infection has increased dramatically in tropical, and in sub-tropical regions (World Health Organization, 2012). There are between 50 and 100 million dengue infections every year, and more than 500,000 cases are hospitalized (Gubler, 2006). Dengue transmission is influenced by a complex set of factors including the environment, climate and weather, human behavior and dengue virus serotype-specific herd immunity among the human population (Cheong et al, 2013; Halstead, 2008; Hay et al, 2000). Understanding the association between environmental factors and VBD is essential for better preventing and controlling disease transmission (Armien et al, 2008; Dambach et al, 2009)

Objectives

Results

Conclusion