Systemic lupus erythematosus prediction tool using optimal cluster based classification (OCBC) algorithm

Abstract

The key objective of the paper focuses on developing the Systemic Lupus Erythematosus prediction tool for the prediction of disease in the early stage using Optimal Cluster based Classification Algorithm (OCBC). Systemic Lupus Erythematosus is an autoimmune, chronic, multi-organ disorder which affects more or less all parts of the body with changing symptoms. There is no cure for the disease; the lifetime of the patients can be extended if diagnosed in the early stage. The death occurs due to various reasons like unawareness, late diagnosis, meeting the right specialist in the severe stage etc. The SLE dataset is tested and applied to various classification algorithms such as ID3, C4.5, J48 and OCBC using SLE prediction tool. As a result, statistics are generated based on all classification algorithms and comparison of all four classifiers is also done in order to predict the accuracy, specificity, sensitivity, precision, recall, F-measure, kappa statistics and to find the best performing classification algorithm among all. In this paper, the screenshots of the tool are also shown. This paper outlines the importance of classification and prediction based data mining algorithms in the healthcare field.