DECISION SUPPORT SYSTEM FOR HEART DISEASE BASED ON SEQUENTIAL MINIMAL OPTIMIZATION IN SUPPORT VECTOR MACHINE

Computer based medical decision support system (MDSS) can be useful for the physicians with its fast and accurate decision making process. Predicting the existence of heart disease accurately, results in saving life of patients followed by proper treatment. The main objective of our paper is to present a MDSS for heart disease classification based on sequential minimal optimization (SMO) technique in support vector machine (SVM). In this we illustrated the UCI machine learning repository data of Cleveland heart disease database; we trained SVM by using SMO technique. Training a SVM requires the solution of a very large QP optimization problem..SMO algorithm breaks this large optimization problem into small sub-problems. Both the training and testing phases give the accuracy on each record. The results proved that the MDSS is able to carry out heart disease diagnosis accurately in fast way and on a large dataset it shown good ability of prediction.