Data Mining of Dengue Infection Using Decision Tree

Dengue infection is an epidemic disease typically found in tropical region. Nowadays, the experts need to know the set of features on dengue infection in order to correctly classify the patients since these classes require different treatment. Our temporal dataset consists of clinical data and laboratory data. The data was collected from the first visit of patient until the date of discharge. We obtained 2 sources of datasets from different regions of Thailand which are Srinagarindra Hospital and Songklanagarind Hospital. Each dataset consists of more than 400 attributes. To accomplish the knowledge discovery task, we consider to employ decision tree as a data mining tool. We propose a set of meaningful attributes from the temporal data. Our experiments are divided into 4 parts. The first two experimental results show the useful knowledge to classify dengue infection from Srinagarindra Hospital’s dataset and Songklanagarind Hospital’s dataset, respectively. Each set of knowledge is tested by different dataset to make sure that the test data was a real unseen data. The third experimental results show the useful knowledge when we integrated 2 datasets. Another objective of this research is to detect the day of defervescence of fever which is called day0. The day0 date is the critical date of dengue patients that some patients face the fatal condition. Therefore the physicians need to predict day0 in order to treat the patients. They expect to have an intelligent system that can trigger the day0 date of each patient. Key-Words: Data Mining, Dengue infection, the day of defervescence.