Modeling of Heart Data using PSO and A-Priori Algorithm for Disease Prediction

Medical organizations such as hospitals include a lot of data and hidden Information. The medical field deals with a lot of data regularly. However, this data is not used correctly. Thus, this unused data can be converted into useful information by using various data extraction techniques. The main disease that causes sudden death of people is heart disease in medicine. It is imperative to predict this disease at an early stage. Large data processing by traditional means can affect results. Computer assisted systems help the doctor as a tool for prediction and analytic exploration of the heart disease. Advanced data mining algorithms and technique are used to discover the facts in the database and for medical research, especially in case of heart disease. This article has main purpose of understanding the datasets which are generally taken in medical field. The understanding of data within the attributes of disease is necessary for developing or modeling the proper algorithm for computing accuracy from the given data sets. The mining association is one of the most important data extraction techniques. Mining link rules can be used efficiently in any rule-building decisions based on decision-making wizard. In this article, we offer effective PSO optimization along with A-priori techniques to model data sets for prediction of heart diseases. Clustering provides the nearby occurrence and nature of datasets as considering the centroid of each cluster for disease. This paper presents the PSO, K-Mean clustering and the simple statistics which apply over the heart image data sets to provide the result for comparative analysis of proposed clustering technique.