DEVELOPMENT OF EFFICIENT MODEL FOR THE ASSESSMENT OF HEART RISK STRATIFICATION

Abstract

The diagnosis of coronary disease at the early time is important to save the life of people as it is actually tedious process. It requires depth knowledge and rich experience. For this, Artificial Neural Network (ANN) techniques are contributing for highest prediction accuracy results over medical data. Recently, several software tools and various methods have been proposed by researchers for developing effective decision support systems. This paper presents the development of efficient model to predict the assessment of Heart risk strategies such as Normal person, first stroke, second stroke and end of life. Two models Learning Vector Quantization (LVQ), Support Vector Machine (SVM) are represented for the efficient prediction of coronary disease. Among them SVM leads 99% accuracy for the prediction of classes with Normal, first stroke, second stroke and end of life of patients.