Efficient disease diagnosis system using data mining techniques

Abstract

Recently data mining and machine learning techniques have found widespread applications in the field of healthcare The objective of this study is to develop an automated technique for diagnosing disease Here three different approaches namely Efficient hybrid approach association rule based approach and hybrid fuzzy decision making tree approach are proposed for detection of diseases using data mining techniques In the first approach an efficient hybrid method to reduce the number of outliers is proposed Detection of outlier is an active area of research in data mining If clustering methods are used the elements that are lying outside the clusters are focused and detected as outliers But there is a possibility of inclusion of few unknown elements as a part of the cluster So in order to eliminate the irrelevant data completely from the dataset it becomes necessary to identify and eliminate such data merged with the clusters Two algorithms namely Multilayer Neural Networks MLN and density based K means adopted for datamining are employed in the proposed approach to identify outliers in a data group. newline