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.

[1]  Shigeo Abe,et al.  Fuzzy least squares support vector machines for multiclass problems , 2003, Neural Networks.

[2]  Suresh R. Devasahayam,et al.  Signals and systems in biomedical engineering , 2000 .

[3]  Fernando S. Schlindwein,et al.  Application of wavelets in Doppler ultrasound , 1997 .

[4]  Ronald R. Coifman,et al.  Entropy-based algorithms for best basis selection , 1992, IEEE Trans. Inf. Theory.

[5]  José A. Romagnoli,et al.  Process data de-noising using wavelet transform , 1999, Intell. Data Anal..

[6]  Metin Akay,et al.  Wavelet applications in medicine , 1997 .

[7]  Ahmet Arslan,et al.  An expert system for diagnosis of the heart valve diseases , 2002, Expert Syst. Appl..

[8]  I Güler,et al.  Application of autoregressive analysis to 20 MHz pulsed Doppler data in real time. , 1992, International journal of bio-medical computing.

[9]  Liu Wei,et al.  Noninvasive acoustical analysis system of coronary heart disease , 1997, Proceedings of the 1997 16 Southern Biomedical Engineering Conference.

[10]  M. Graça Ruano,et al.  Real-time implementation of a Doppler signal spectral estimator using sequential and parallel processing techniques , 2000, Microprocess. Microsystems.

[11]  E. Karabetsos,et al.  Design and development of a new ultrasonic doppler technique for estimation of the aggregation of red blood cells , 1998 .

[12]  S. Gunn.  Support Vector Machines for Classification and Regression , 1998 .

[13]  Edward Y. Chang,et al.  SVM binary classifier ensembles for image classification , 2001, CIKM '01.

[14]  F. K. Lam,et al.  Fast detection of venous air embolism in Doppler heart sound using the wavelet transform , 1997, IEEE Transactions on Biomedical Engineering.

[15]  R. Centor.  Signal Detectability , 1991, Medical decision making : an international journal of the Society for Medical Decision Making.

[16]  C. Burrus,et al.  Introduction to Wavelets and Wavelet Transforms: A Primer , 1997 .

[17]  R Quian Quiroga,et al.  Wavelet entropy: a measure of order in evoked potentials. , 1999, Electroencephalography and clinical neurophysiology. Supplement.

[18]  N A Gough,et al.  Neural network analysis of Doppler ultrasound blood flow signals: a pilot study. , 1997, Ultrasound in medicine & biology.

[19]  Majid Mirmehdi,et al.  Comparative Exudate Classification Using Support Vector Machines and Neural Networks , 2002, MICCAI.

[20]  Bf Buxton,et al.  An introduction to support vector machines for data mining , 2001 .

[21]  Hyun-Chul Kim,et al.  Constructing support vector machine ensemble , 2003, Pattern Recognit..

[22]  Metin Akay,et al.  Neural networks for the diagnosis of coronary artery disease , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[23]  H. Liang,et al.  A feature extraction algorithm based on wavelet packet decomposition for heart sound signals , 1998, Proceedings of the IEEE-SP International Symposium on Time-Frequency and Time-Scale Analysis (Cat. No.98TH8380).