Review on effective disease prediction through data mining techniques

Abstract

Hidden and unknown pattern are extracted from large data sets by performing several combinations of techniques from database and machine learning. Data mining plays a significant role for handling a huge amount of data. Data mining deals with heterogeneity, privacy and correctness of data. Moreover, medical data mining is tremendously important research area and significant attempts are made in this area in recent years because inaccuracy in medical data systems may cause seriously disingenuous medical treatments. Medical data sets should be analyzed using suitable mining algorithms. To perform related operations, techniques of data mining have been used in developing medical systems for prediction of diseases through a set of medical data set. This paper reviews state of the art data mining algorithms for predicting different diseases and to analyze the performance of classification techniques i.e. Naive Bayes (NB), J48, REF Tree, Sequential Minimal Optimization (SMO), Multi-Layer Perceptron and Vote on different data sets of different diseases i.e. chronic kidney disease (CKD), heart disease, liver and diabetes. The experimental setup for performance evaluation of various algorithms using disease data sets retrieved from UCI respiratory has been made in WEKA tool. Values of different parameters i.e. correctly classified instances, precision, recall and F-Measure, time taken are analyzed by applying different classification algorithms.