Cluster based effective prediction approach for improving the curable rate of lymphatic filariasis affected patients

Abstract

The objective for global elimination of human lymphatic filariasis is by 2020. Public health department major problem is to predict the severity of the lymphatic filariasis disease grade levels and its control measures in patients. The grades are classified as Grade-I, Grade-II, Grade-III and Grade-IV which are categorized based on their symptom of the disease in the patients. The study is based on the attributes of lymphatic filariasis grades. In this research paper data mining techniques such as K-means Classification algorithms and Bayesian prediction are used to categorize the grade levels of lymphatic filariasis and to predict the curable rate of the lymphatic filariasis control measures. The control measures of the existing affected patients are to be considered to increase the curable rate in the future, with the help of Bayesian prediction mechanism. With regard to these findings and emphasis on prediction of severity of the lymphatic filariasis disease incidence to reduce complications, disabilities and healthcare costs, this study was aimed to investigate lymphoedema stages and grades for lymphatic filariasis. Therefore accurate prediction of severity of lymphatic filariasis at different period of time in patient is important for good clinical decision making and morbidity management in public health strategies.