An Illustration of Rheumatoid Arthritis Disease Using Decision Tree Algorithm

Abstract

Data Mining domain integrates several partitions of the computer science and analytics field. Data mining focuses on mine data from a repository of datasets, to identify patterns, discover knowledge, additionally to predict probable outcomes. One of the inflammatory diseases is the Rheumatoid Arthritis (RA) caused by specific autoantibodies with the destruction of synovial joint autoantibodies. Most RA patients experience abhor pain on the joints of the hands, legs, hip, spine, and shoulder. ID3 is the general significant algorithm to construct a decision tree. Information gain determined to find the dominant attributes from the dataset to build the decision tree for the ID3 algorithm. C4.5 is another algorithm to construct the decision tree. It is the successor of ID3 that handles dataset contains different numerical attributes. C4.5 algorithm builds the decision tree evaluated by the gain ratio. Decision tree belongs to classification techniques is a well-known method appropriate for medical diagnosis. Decision tree algorithms such as ID3 and C4.5 are popular and efficiently used classifiers for Rheumatoid Arthritis (RA) prediction from a RA dataset. The objective of this paper is to display the prominent features to predict RA from the RA dataset.