A Crossbreed Framework for Heart Disease Prediction Using svm and Rough set Techniques

Today's innovations in health-care technology are progressively assisting in the management of patients with various ailments. The most lethal of them is heart illness, which cannot be seen with the unaided eye and strikes when a person's vital indicators, such as heart rates, temperature, and blood pressure, exceed the authorized range. The fundamental difficulty is to identify patients with more precision and in a timely way, then prescribe suitable therapies while minimizing medication inaccuracies. Furthermore, there are several ambiguities in the information system when it comes to disease prediction. We provide a comprehensive approach for diagnosing cardiac disease in this work. The suggested model combines support vector machines and a rough set (SVMRS) for inferencing decision rules to predict the heart disease. In addition, a comparison analysis is given. The practicality of the suggested paradigm is demonstrated by the comparative analysis. The SVMRS model has executed with the accuracy of 93.8%.