Application of log-linear models to dengue virus infection patients in Thailand

Abstract

Dengue is an infectious mosquito-borne viral disease. Dengue or dengue-like epidemics ranks highly among new and newly emerging infectious diseases in public health significance and may affect persons of all ages in dengue endemic area. Dengue virus infections may lead to dengue fever (DF), dengue haemorrhagic fever (DHF) and may lead to hypovolaemic shock (dengue shock syndrome, DSS). The purpose of this study is to identify the associated factors between personal, clinical variables of dengue patients by using log-linear models. Test of independence are used (chi-square and Cramer's V value tests) to find out the association between any two variables. In addition two- and three-dimensional log-linear models are used to obtain estimated parameters and expected frequencies for these models. Amongst the models fitted, the best are chosen based on the analysis of deviance. The results show that most paired variables of personal and clinical variables are significantly related at p-value less than 0.05. For dengue fever (DF), dengue hemorrhagic fever (DHF) and dengue shock syndrome (DSS) patients, the type of clinic has a strong association with gender, occupation and place of treatment that gave the highest Cramer's V value. In addition, the type of clinic has an association with the status of the last contact. To reduce the outbreak of dengue there should be a control of mosquitoes and for treatment of patients in hospital.© 2013 - IOS Press and the authors. All rights reserved.