Analysis of the Factors that Cause Dengue Hemorrhagic Fever (DHF) Using Chi-Square Automatic Interaction Detection (CHAID)

Abstract

The low level of public awareness of environmental cleanliness has led to the spread of dengue hemorrhagic fever (DHF). This study aims to identify and analyze the factors that cause dengue hemorrhagic fever (DHF) using the Chi-Square Automatic Interaction Detection (CHAID) method. This type of research is applied research, namely research conducted to apply, test, and evaluate the ability of a theory that is applied in solving practical problems. This research was conducted at the University of Kaltara by taking quantitative data on dengue hemorrhagic fever (DHF) patients recorded at the Bulungan District Health Office. The analytical method used is the Chi-Square Automatic Interaction Detection (CHAID) tree-structured classification method with the Statistical Package for the Social Sciences (SPSS) program. Based on the study results, it was found that five factors caused the occurrence of dengue hemorrhagic fever (DHF) in Bulungan Regency. They are Gender, Age, Work Status, Environment, and Household Income. Based on the CHAID analysis using the IBM SPSS Statistics computer program, a decision tree is formed, which consists of 5 nodes consisting of 1 main node (node 0), one decision node (node 1), and 3 terminal nodes (node 2, 3 and 4). The predictor variables that affect the formation of the decision tree are Age and Household Income. DHF patients can be classified into three different segments from the segmentation decision tree with an estimated risk of 0.273, which means the risk of the wrong classification for DHF status is 27.3%.