Heart attack risk detection using Bagging classifier

Cardiovascular diseases in the world are the most common cause of death. Our study aims to predict the rate of heart attack risk for individuals using the Bagging Method, an ensemble Machine Learning classification algorithm. For this reason, a questionnaire has been prepared to collect the relevant data. After obtaining the official permissions, the questionnaires are applied to the patients who have had a heart attack. By this way a predefined dataset is created to be used in the classification algorithms. In the applications, heart attack risk can be detected for an individual by using powerful ensemble classifiers. Additionally, in cross validation process the proposed model shows a high-performance in regression. Therefore, this suggested Clinical Decision Support System (CDSS) enables to take some precautions before a heart attack.