Prediction of Myocardial Infarction Using Data Mining Techniques

Data Mining is a process that extracts knowledge from a large amount of data. Data Mining has the capability for classification, prediction, estimation and pattern recognition. The Healthcare industry is generally rich in information but somewhat poor in knowledge. Data Mining plays a vital role in predicting the heart disease using the datasets. Many kinds of information are accessible in the prevision of heart disease. The Heart disease diagnosis is a complicated task which requires more experience and knowledge. The aim of this work is to create a MLPT, to predict Myocardial Infraction. After getting the patient information this MLPT, forecast that the patient is caused by heart attack or not which is performed by using three Data mining techniques: Naive Bayes, Decision tree and WAC (Weighted Associative Classifiers). Using the medical prognosis such as chest pain type, thalassic, slope etc., it can predict the probabilities of patients getting a heart disease in the future. The prediction is performed from extracting the patient's diachronic data or data storage. The research is mainly developed to recover the hidden information from the database. The system has been implemented in JSP and checked using the datasets that is been collected from UCI machine learning repository.