A review paper on: Heart disease data set analysis using data mining classification techniques

Health care industry is one of the fastest growing industries in 21st century. This is the era of increasing health problems and chronic diseases. The major chronic diseases faced world over are cardio vascular diseases such as stroke and heart attacks. Heart disease is one of the common causes of death worldwide. According to WHO as many as, 17.9 Million people die of Cardio Vascular Diseases each year, 31% of all the deaths worldwide. Diagnosis of the disease is one of the most important task of medical science. Medical professionals need a decision support system for early prediction of heart diseases with good accuracy rate which can be achieved with the help of data mining techniques. The healthcare industry produces large amount of data each day. Data mining helps in extracting hidden information and patterns from a large and complex database which is helpful in making decisions. The main objective of this research is to develop a heart disease prediction system by using data mining techniques with a good accuracy rate. Here we have a pre processed data set consisting of 303 records and 14 predictors such as Gender, blood pressure, chest pain type etc. as input for BPN and Decision Tree. In this research we will compare two data mining algorithms: Decision tree and Back propagation network Algorithm and predict the presence or absence of heart disease in a patient. The algorithm with highest accuracy rate will be considered good for heart disease prediction in hospitals.