A Review on Prediction of Multiple Diseases and Performance Analysis using Data Mining and Visualization Techniques

Abstract

In the field of medical science a tremendous amount of data is generated, doctors need to test the patient physically to find out the injuries and disease of the patient. This paper outlines the idea of predicting a particular disease by performing operations on the digital data generated in the medical diagnosis. In this project an efficient genetic algorithm hybrid with the techniques like back propagation and Naive Bayes approach for disease prediction is proposed. Bad clinical decisions would cause death of a patient which cannot be aff orded by any hospital. To achieve a correct and cost eff ective treatment, computer technology Systems can be developed to make good decision. There is a lot of medical information unexplored, which gives rise to an important query of how to make useful information out of the data. The purpose of this project is to construct a basic prototype model which can determine and extract unknown knowledge (patterns, concepts and relations) related with multiple disease from a past database records of specified multiple diseases. It can solve complicated queries for detecting a particular disease and thus assist medical practitioners to make intelligent clinical decisions which traditional decision support systems were not able to. By providing efficient treatments, it can help to reduce costs of treatment. The medical organizations are "rich in data" but their "knowledge utilization is poor ". There is a lack of sufficiency of improved analysis techniques to find relations, concepts and patterns in the medical data. Data mining is science and engineering study of extracting previously undiscovered patterns from a huge set of data. In this paper, data mining methods namely, Decision tree, Naïve Bayes, and Back-Propagation(ANN) algorithms are implemented on medical data sets .The medical datasets will be represented graphically(graphs , charts , shapes)using diff erent visualization techniques. The algorithms are compared and evaluated on basis of their accuracy and time consumption factors. The algorithm which gives out high accuracy and less duration to give the output is analysed and implemented.

An Approach towards Crop Management using DM and Image Processing

“…Algorithms of Data Mining are used for performing analysis and pattern extraction from the selected data. Ajinkya Kunjir et.al in their survey paper in 2016 described the use of data analysis its approach to help us to provide a better exploration and understanding of large data, which are classifications and predictions [7]. Various predictive and descriptive data mining techniques are described below as follows:…”