Abstract
Heart disease is one of the major causes of death worldwide and the early prediction of heart disease is important. The computer-based heart disease prediction system helps the physician as a tool for heart disease diagnosis. Hence, the early diagnosis of heart diseases can aid in making decisions on lifestyle changes in high-risk patients and in turn reduce the complications, which can be a great milestone in the field of medicine. Machine learning techniques used to develop an appropriate computer-based system and decision support that can aid to early detection or prediction of heart disease, in this project we have developed a model which classifies if patient will have heart disease or not based on various features. The data collection, data preprocessing, feature selection and classification algorithms placed a vital role in heart disease prediction. In this proposed work data include 70000 records of patients with 13 attributes such as age, gender, weight, height, blood pressure types, glucose, smoke, alcohol, etc. In addition, many classification algorithms are used such as KNN, Random Forest, Logistic Regression, SVM, Decision Tree. Feature selection is of three types: Filter Method, Wrapper Method, and Embedded Method. Here, we used Filter based method for feature selection, Filter Based feature selection techniques such as chi-square, mutual information, correlation it will select relevant feature for model creation among all 13 attributes only 10 features are selected. It will reduce the computational cost of modeling and, in some cases, used to improve the performance of the model. Finally, we will compare all algorithms for accuracy, and conclude which algorithm gives accurate results. By using this GUI application, user can sit at their convenience and have a health check-up. The GUI is designed in such a way that anyone can easily operate it and have a check-up that will enable to predicts a patient will have heart disease or not.