Rough Set Technique to Predict Symptoms for Malaria

The combination of insufficient knowledge and the vague nature of symptoms, that characterize malaria, exponentially increases the morbidity and mortality rates of malaria. The task of getting an accurate medical diagnosis becomes complicated and unwieldy. The challenge, therefore, for physicians who have limited experience in investigating, diagnosing, and managing such conditions is how to make sense of these confusing symptoms to facilitate accurate diagnosis timely. In this paper, a study is conducted on a working hypothesis of Rough Set Theory (RST) to retrieve hidden information from a set of vague data. We focus to search out correct symptoms (conditional attributes) for malaria. RST is a useful tool to deal with vague data. It has been proved to be slightly better than the other soft computing technique but with non-noteworthy statistical difference in performance.