Detection of heart disease using binary particle swarm optimization

This article introduces a computer-aided diagnosis system of the heart valve disease using binary particle swarm optimization and support vector machine, in conjunction with K-nearest neighbor and with leave-one-out cross-validation. The system was applied in a representative heart dataset of 198 heart sound signals, which come both from healthy medical cases and from cases suffering from the four most usual heart valve diseases: aortic stenosis (AS), aortic regurgitation (AR), mitral stenosis (MS) and mitral regurgitation (MR). The introduced approach starts with an algorithm based on binary particle swarm optimization to select the most weighted features. This is followed by performing support vector machine to classify the heart signals into two outcome: healthy or having a heart valve disease, then its classified the having a heart valve disease into four outcomes: aortic stenosis (AS), aortic regurgitation (AR), mitral stenosis (MS) and mitral regurgitation (MR). The experimental results obtained, show that the overall accuracy offered by the employed approach is high compared with other techniques.