Heart Disease Classification: A Case Study using Machine Learning and Data Mining

Abstract

The diagnostic of heart disease remains more or less the most difficult and tedious task in the medical field and it various factors and symptoms of prediction which is involved in several layered issue that could engender the negative presumptions and unpredictable effects. Wu et al proposed that the integration of clinical decision support with relation to the computer- based system of the patient record could reduce the rate of errors in medical predictions, low the unwanted practice variation, enhance safety for patients, and the improvement of patient outcome. This knowledge provides a useful environment which can help to significantly improve the quality of clinical decisions. Many of hospital information in recent days are designed to implement patient billing, patient data storing, inventory management and generation of simple statistics computation. Most of the hospitals use decision support systems but they are still in most cases bounded. The majority of doctors are predicting heart disease symptoms based on their learning and working experience. In this case, prediction system should be implemented so that to reduce the risk of Heart Disease.