Comparison of pattern recognition methods for computer-assisted classification of spectra of heart sounds in patients with a porcine bioprosthetic valve implanted in the mitral position

The diagnostic performance of two pattern recognition methods (or classifiers) for detecting valvular degeneration was evaluated in 48 patients with a porcine bioprosthetic heart valve inserted in the mitral position. Twenty patients had a normal porcine bioprosthetic valve and 28 patients had a degenerated bioprosthetic valve. One method was based on the Gaussian-Bayes model, and the second on the nearest neighbor algorithm using three distance measurements. Eighteen diagnostic features were extracted from the sound spectrum of each patient and, for each method, a two-class supervised learning approach was used to determine the most discriminant diagnostic patterns composed of six features or less. The probability of error of the classifiers was estimated with the leave-one-out approach. The performance of each method with respect to discriminating between normal and degenerated bioprosthetic valves was verified by clinical evaluation of the valves. The best performance in evaluation of the second spectrum (98% correct classifications) was obtained with the Bayes classifier and two patterns of six features each.<<ETX>>

[1]  R. Guardo,et al.  Bias and variability of diagnostic spectral parameters extracted from closing sounds produced by bioprosthetic valves implanted in the mitral position , 1989, IEEE Transactions on Biomedical Engineering.

[2]  P. Stein,et al.  Antithrombotic therapy in mechanical and biological prosthetic heart valves and saphenous vein bypass grafts. , 1989, Chest.

[3]  Louis-Gilles Durand,et al.  A Bayes model for automatic detection and quantification of bioprosthetic valve degeneration , 1988 .

[4]  M. S. Hamid,et al.  Vibrational Analysis of Bioprosthetic Heart Valve Leaflets Using Numerical Models: Effects of Leaflet Stiffening, Calcification, and Perforation , 1987, Circulation research.

[5]  R Guardo,et al.  Spectral analysis of closing sounds produced by Ionescu-Shiley bioprosthetic aortic heart valves. Part 3. Performance of FFT-based and parametric methods for extracting diagnostic spectral parameters. , 1987, Medical & biological engineering & computing.

[6]  Robert Guardo,et al.  Evaluation of FFT-Based and Moder Parametrc Methods for the Spectral Analysis of Bioprosthetic Valve Sounds , 1986, IEEE Transactions on Biomedical Engineering.

[7]  P D Stein,et al.  Relation of calcification to torn leaflets of spontaneously degenerated porcine bioprosthetic valves. , 1985, The Annals of thoracic surgery.

[8]  S L BeMent,et al.  Comments on "Pole-zero modeling and classification of phonocardiograms". , 1984, IEEE transactions on bio-medical engineering.

[9]  H N Sabbah,et al.  Frequency spectra of the first heart sound and of the aortic component of the second heart sound in patients with degenerated porcine bioprosthetic valves. , 1984, The American journal of cardiology.

[10]  J. McClellan,et al.  Detection of aortic porcine valve dysfunction by maximum entropy spectral analysis. , 1983, Circulation.

[11]  David A. Landgrebe,et al.  Predicting the Required Number of Training Samples , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  James H. McClellan,et al.  Pole-Zero Modeling and Classification of Phonocardiograms , 1983, IEEE Transactions on Biomedical Engineering.

[13]  P. Stein,et al.  Frequency of the First Heart Sound in the Assessment of Stiffening of Mitral Bioprosthetic Valves , 1981, Circulation.

[14]  H N Sabbah,et al.  Frequency spectrum of the aortic component of the second heart sound in patients with normal valves, aortic stenosis and aortic porcine xenografts. Potential for detection of porcine xenograft degeneration. , 1980, The American journal of cardiology.

[15]  Gerard V. Trunk,et al.  A Problem of Dimensionality: A Simple Example , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Jan M. Van Campenhout,et al.  On the Possible Orderings in the Measurement Selection Problem , 1977, IEEE Transactions on Systems, Man, and Cybernetics.

[17]  A R Feinstein,et al.  XXXI. On the sensitivity, specificity, and discrimination of diagnostic tests , 1975, Clinical pharmacology and therapeutics.

[18]  Godfried T. Toussaint,et al.  Bibliography on estimation of misclassification , 1974, IEEE Trans. Inf. Theory.

[19]  Donald H. Foley Considerations of sample and feature size , 1972, IEEE Trans. Inf. Theory.

[20]  P. Stein,et al.  Utility of physical examination and noninvasive tests in the diagnosis of degeneration of porcine bioprosthetic valves in the mitral position , 1988 .

[21]  Anil K. Jain Advances in statistical pattern recognition , 1987 .

[22]  D L Sikarskie,et al.  A mathematical model of aortic valve vibration. , 1984, Journal of biomechanics.

[23]  Paul D. Stein,et al.  A physical and physiological basis for the interpretation of cardiac auscultation : evaluations based primarily on the second sound and ejection murmurs , 1981 .

[24]  H N Sabbah,et al.  One-dimensional model of diastolic semilunar valve vibrations productive of heart sounds. , 1979, Journal of biomechanics.

[25]  Julius T. Tou,et al.  Pattern Recognition Principles , 1974 .