SSH — Structure risk minimization based support vector machine for heart disease prediction

摘要

The prediction of heart disease problem is a crucial task in the fields of medical sciences. It emerges a requirement of accurate system to detect heart disease of a patient. To achieve a accurate, cost effective computer-based model should be developed to make good decision. In this paper, we propose efficient Structure risk minimization based Support vector machine for Heart disease prediction (SSH model). The proposed SRM SSH model achieves highest sensitivity, specificity and accuracy compared with existing SVM based heart disease prediction model. The SSH model produces highest accuracy by minimizing a bound on the VC-dimension and the number of training errors at the same time. As recognition of minimizing structural risk rule, SSH proves that its classification performance is high in a given large datasets.