Abstract: Most nations face high and expanding rates of heart diseases or cardiovascular disease. There are number of factors which increase risk of heart diseases, like family history of heart disease, smoking, cholesterol, high blood pressure, obesity, lack of physical exercise etc. Heart disease is a major health problem in today’s time. A major challenge facing healthcare organization is the provision of quality services at affordable costs. Thus, there arises a need to develop a decision support system for detecting heart disease of a patient. That is, to achieve a correct and cost effective computer-based treatment and support system that can be used to make good decision. Many hospitals use hospital information systems to manage their healthcare or patient data. These systems produce huge amounts of data in the form of images, text, charts and numbers. Sadly, this data is rarely used to support the medical decision making. There is a bulk of hidden information in this data that is not yet explored which give rise to an important query of how to make useful information out of the data. So there is necessity of creating a system which will help practitioners predict the heart disease before it occurs. By providing efficient predictions, it can help to reduce costs of treatment. A hybrid system of Back-Propagation algorithm for neural network and genetic algorithm is proposed. The characteristics of Back-Propagation algorithm are that it is adaptive and tolerant towards the noisy data or other outliers present in the medical data. Back propagation networks do not need the linear relationship between the data and the target output. But it has a disadvantage of getting stuck in the local minima and thus the data is first optimized using genetic algorithm and the concepts of crossover and mutation are applied and that is then again fed into the neural network for better results. In the case of heart diseases time is precious, proper diagnosis at the right time saves life of many patients. The system can be considered assisting the doctor to come to decision making.

Keywords: Neural Network, Genetic Algorithm, Crossover, Mutation, Back-Propogation.