Cardiovascular Disease Prediction using Enhanced Support Vector Machine Algorithm

Abstract

Cardiovascular syndrome is a distinct disorder which remains as the core cause of morbidity and mortality in people all over the world. It is a deadly disease that affects a significant portion of the world's population. When deaths and the proportion of persons affected by heart disease are considered, it dearly signifies the importance of early identification of cardiovascular illness. Traditional diagnostic methods are insufficient for this condition. Prediction of heart infection is one of the most important issues in clinical data analysis. In the healthcare business, there is a wealth of information. Developing a medical diagnosis system for heart disease diagnosis using machine learning models provides more precise test than the previous method. All the available Machine learning techniques (MLTs) have proved to be assistive in making decisions, predicting illness in the huge amounts of data that are available in healthcare data domains. Numerous studies purely graze the apparent using models to prognosticate cardiac syndrome. The proposed study offers a strategy for identifying key features using MLT, which augment the accuracy of predicting the diseases present in the heart. Different sets of methods and techniques with proficient machine learning algorithms are used to identify the diseases at the early stages itself. The proposed research study has obtained a higher degree of performance with high accuracy by using a composite process to produce a statistical method for heart disease.