Heart Disease Detection Model Using Support Vector Machine with Feature Selection
Ayodeji Olalekan Salau, Tsehay Admassu Assegie, Gunjan Chhabra, Keshav Kaushik, Sepiribo Lucky Braide
Abstract
Heart disease has recently risen to prominence as one of the leading killers and most pervasive diseases in the globe. Detection of heart disease in an early stage using heart disease symptoms is an exciting task. In developing nations such as Ethiopia where the number of cardiologists is limited and most of the population lives in rural and remote areas, an effective decision support system is crucial to saving a life by detecting heart disease at an early stage. Many studies exist in scientific literature which focus on the design and implementation of an intelligent automated system for solving the challenges in heart disease detection. However, the existing work in the literature has larger scope for improvement and the performance of the medical decision support system is required to have higher precision to detect heart disease accurately. Thus, this study extends the existing work by proposing a more efficient model for heart disease detection. Overall, we have proposed a state-of-the-art heart disease detection model with a predictive accuracy of 98.60 % using support vector machine and sequential feature selection.