machine learning-based heart disease prediction: an svr approach with selected interactions

A collection of various ailments that affect the heart and blood vessels is referred to as cardiovascular disease (cvd), also known as heart disease. in the world, heart disease is the main cause of fatality and morbidity, resulting in 18 million deaths per year. preventing premature death can be achieved by identifying those who are most vulnerable to heart diseases and providing them with the appropriate care. in the medical field, machine learning algorithms are becoming increasingly important, particularly when utilizing medical databases to diagnose diseases. efficient algorithms and data processing techniques are used to predict different diseases, and there is great potential for accurate prediction of heart disease. therefore, this study compares the support vector regression (svr) with selected interaction terms approach with other methods such as random forest, logistic regression, decision tree, k-nearest neighbor (knn) and support vector machine (svm). this test comes from two sets of data, both of which are 14 features and from the cleveland clinic heart disease datasets and are obtained from kaggle, the former with 303 instances and the latter containing 1025 cases. it was found that the method presented in this article obtained better results than other algorithms. so that for a data set with many samples, it will bring an acceptable accuracy of 100%. it was found that the method presented in this article obtained better results than other algorithms. so that for a data set with many samples, it will bring an acceptable accuracy of 100%. this result is achieved through rigorous cross-validation and feature interaction selection without signs of overfitting.