A rough sets approach for diagnostic M-mode evaluation in newborn with congenital heart diseases

This paper presents a methodology based on rough set theory that can be used to identify those newborn with congenital heart diseases for which performing the test is redundant or superfluous. Pawlak introduced rough set theory in the early 1980s as a tool for representing and reasoning about imprecise or uncertain information. Our method depends on cardiac morphologic measurement algorithms for diagnosis template for neonatal congenital heart diseases accuracy. In this study, relationship between cardiac morphologic measurement and diagnosis of neonatal congenital heart diseases is analysed. Examples of echocardiographic M-mode values application for prediction of diagnosis for newborn infant with congenital heart diseases are given. Furthermore, the methodology enables one to automatically construct a set of descriptive and minimal if-then rules that model the patient group in need of the test. A reanalysis of a previously published real-world dataset of patients with normal cardiovascular system is used as this study. This may be helpful in supporting decisions concerning diagnosis of congenital heart diseases in newborn babies using rough set techniques. In addition, medical rough set techniques can discover novel diagnostic facility and associations that are useful to paediatric cardiologists.