Intelligent diagnosis system for acute respiratory infection in infants

Acute Respiratory Infections (ARI) became the main cause of morbidity and mortality of infectious diseases in the world. Recent studies have focused on the use of data mining techniques to build predictive models that are able to diagnose the ARI. The objective of this research is to develop a diagnosis system to predict ARI in infants using C4.5 algorithm. The algorithm used to build a decision tree. This research is a collaboration authors with the hospitals and doctors. The dataset was obtained from medical records of patients with respiratory disease from a hospital. The data are used as training data and test data. Symptoms that are used as input systems are the danger sign, fever, cough, shortness of breath and fast breathing. The first step is to pre-process subsequent data algorithm classification to form a decision tree. After the decision tree was formed, continued set the rules. That decision rules are implemented to establish the diagnosis system. Validation is done by comparing the results of diagnosis system with the doctor diagnosis. The comparison showed that the results of diagnosis system approaching the diagnosis of doctor. From these results, it can be concluded that the C4.5 algorithm could help to diagnose ARI. However, further investigation with the larger dataset is still needed.