SPECTRAL CHARACTERIZATION AND CLASSIFICATION OF CARPENTIER-EDWARDS HEART-VALVES IMPLANTED IN THE AORTIC POSITION

This paper demonstrates an improvement in the performance of spectral phonocardiography, combined with pattern recognition techniques for mo nitoring the condition of bioprosthetic heart valves, The analysis of the heart sounds is performed using a modified forward-backward overde termined Prony's method, Results show that the condition of the biopro sthesis affects mostly the higher part of the spectrum (i.e., above 25 0 Hz) where no frequency components were found for malfunctioning case s. Therefore, the amplitudes of the three highest frequency components are used as the input vector of an adaptive single layer perceptron-b ased classifier to identify normal and malfunctioning classes, For the sample set examined, this method gives 100% correct discrimination be tween normal and malfunctioning Carpentier-Edwards (C-E) valves.