Graphical User Interface Developed for Diseases Prediction by Mean of Clustering and Apriori Algorithm

Abstract

Disease prediction is one of the most important issues that we are facing today. A large number of patients struggling for their check up even for predictive disease like heart attack possibilities, kidney damage change and possibilities of lung problem. All these lies in predictive disease categories. They need not require very vast analysis if we can predict. This Research motivate to develop a console(GUI) on the basis of data mining which is used to analyze large volumes of data and extracts information that can be converted to useful knowledge. And overall predict a patient for their chances of disease. These techniques can be applied on predictive medical disease. This research papers which mainly concentrated on predicting kidney failure, heart disease. Experimental results will show that many of the rules help in the best prediction of heart disease and kidney failure which even helps doctors in their diagnosis decisions by using Aprior and k-mean algorithm. By the help of this algorithm it provide easy and efficient way in which we can find the stage of the kidney failure and heart disease. To swamp this problem the healthcare industry gathers enormous amounts of heart disease data which, grievously, are not "mined" to discover hidden information for effective decision making. However, there is a lack of effective analysis tools to discover hidden relationships and trends in data. So due to these condition even doctors not able to predict disease accurately. So there is need to develop a efficient decision making system which can predict the correct diseases with available data. So in this paper we are introducing the automated console to predict the diseases by mean of clustering & a-priori algorithm. This is web based convenient tool it can be used even in absence to doctors to predict diseases. Here, we consider almost 200 persons data to develop this automated console. Preliminary conclusions shows that it very effective tool to predict diseases.