Medical Domain Knowledge and Associative Classification Rules in Diagnosis

Abstract

Hospital information systems have been frustrated by problems that include congestion, long wait time, and delayed patient care over decades. To solve these problems, data mining techniques have been used in medical research for many years and are known to be effective. Therefore, this study examines building a hybrid data mining methodology, combining medical domain knowledge and associative classification rules. Real world emergency data are collected from a hospital and the methodology is evaluated by comparing it with other techniques. The methodology is expected to help physicians to make rapid and accurate diagnosis of chest diseases.