Efficient Heart Disease Prediction Using Modified Hybrid Classifier

Cardiovascular diseases, popularly known as heart disease leading to heart attack, kill nearly 17.9 million humans. Heart disease is found in three out of five patients in critical care unit. The complexity of this disease lies in the fact that it suddenly fails the functioning of human and then Standard Operating Plan (SOP) is required; if not provided on time, patients’ life is in danger. Proper healthcare system takes time to detect the cause and effectively start the diagnosis, whereas our proposed system efficiently and accurately tells the client weather a patient has a heart disease or not. It also tells whether the patient will face such kind of disease in near future or not. The system is developed based on machine learning techniques such as Naive Bayes, XGBoost gradient classifier, support vector machine (SVM), and decision tree. Some external factors were also considered which may lead to heart disease in the future. Furthermore, integrated web application has been developed which alert and gives a user-friendly interface for the recognition and prediction. Thirteen diagnostic factors and five environmental factors are analyzed. The proposed diagnosis system attained a good precision as compared to previous methods recommended earlier. In addition, system can easily be implemented in public domain to spread awareness regarding heart disease, and it also talks about the possibility of the heart disease in near future.