Effects of Features Selection and Classification on Various Chronic Diseases Detection
Now days chronic disease highly imperative taking place progressively and extents at serious stage if it not diagnosis at early stage. Many researchers have been developed prediction system which process large medical datasets using data mining and machine learning approach for chronic diseases. Building highly measurable and accurate system depend on processing of data during training phase which effects over all like accuracy, computation time, superiority and lessor error rate. The performance of classification algorithm without feature selection techniques is. This paper focuses on effects of feature selection and classification process or methods on accuracy of chronic disease prediction model. The proposed work investigate effect of feature selection for medical dataset specially chronic disease dataset where it found appropriate feature selection method which removes redundant and irrelevant data which in turn reduces computation time and as result improve accuracy rate of classification method. In the same direction variety of feature selection algorithm are investigated and observe its effects on classification algorithm are evaluated for chronic disease. Our work find out that classiﬁcation is an important tool for diagnosing chronic diseases and Feature selection is one of the essential techniques for classification. The proposed paper helps researcher develop chronic disease prediction model which gives higher rate of accuracy for rigorous diagnosis of patient.