A decision support system based on support vector machines for diagnosis of the heart valve diseases

In this paper, a decision support system that classifies the Doppler signals of the heart valve to two classes (normal and abnormal) is presented to support the cardiologist. The paper uses our previous paper where ANN is used as a classifier, as feature extractor from measured Doppler signal. To make this, it uses wavelet transforms and short time Fourier transform methods. Before it classifies these features, it applies Wavelet entropy to them. In this paper, our aim is to develop our previous work by using least-squares support vector machine (LS-SVM) classifier instead of ANN. We use LS-SVM and backpropagation artificial neural network (BP-ANN) to classify the extracted features. In addition, we use receiver operator characteristic (ROC) curves to compare sensitivities and specificities of these classifiers and compute the area under the curves. Finally, we evaluate two classifiers in all aspects.