Diagnosing aortic valve stenosis by correlation analysis of wavelet filtered heart sounds

  • J. Herold
  • R. Schroeder
  • F. Nasticzky
  • V. Baier
  • A. Mix
  • T. Huebner
  • A. Voss
Article

Abstract

Traditional auscultation performed by the general practitioner remains problematic and often gives significant results only in a late stage of heart valve disease. Valve stenoses and insufficiencies are nowadays diagnosed with accurate but expensive ultrasonic devices. This studyaimed to develop a new heart sound analysis method for diagnosing aortic valve stenoses (AVS) based on a wavelet and correlation technique approach. Heart sounds recorded from 373 patients (107 AVS patients, 61 healthy controls (REF) and 205 patients with other valve diseases (OVD)) with an electronic stethoscope were wavelet filtered, and envelopes were calculated. Three correlations on the basis of these envelopes were performed: within the AVS group, between the groups AVS and REF and between the groups AVS and OVD, resulting in the mean correlation coefficients rAVS, rAVSv.REF and rAVSv.OVD. These results showed that rAVS (0.783±0.097) is significantly higher (p<0.0001) than rAVSv.REF (0.590±0.056) and rAVSv.OVD (0.516±0.056), leading to a highly significant discrimination between the groups. The wavelet and correlation-based heart sound analysis system should be useful to general practitioners for low-cost, easy-to-use automatic diagnosis of aortic valve stenoses.

Keywords

Electronic stethoscope Heart sound Aortic valve stenosis Phonocardiography Wavelet decomposition Correlation technique 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bousseljot, R., andKreiseler, D. (1998): ‘ECG signal analysis by pattern comparison’,Comput. Cardiol.,25, p. 349Google Scholar
  2. Bulgrin, J. R., Rubal, B. J., Thompson, C. R., andMoody, J. M. (1993): ‘Comparison of short-time fourier, wavelet and timedomain analyses of intercardiac sounds’,Biomed. Sci. Instrum.,29, pp. 465–472Google Scholar
  3. Cathers, I. (1995): ‘Neural network assisted cardiac auscultation’,Artif. Intell. Med.,7, pp. 53–66Google Scholar
  4. De Groff, C., Bhatikar, S., Hertzberg, J., Shandas, R., Valdescruz, L., andMahajan, R. (2001): ‘Artificial neural networkbased method of screening heart murmurs in children’,Circulation,103, pp. 2711–2716Google Scholar
  5. Durand, L.-G., andPibarot, P. (1995): ‘Digital signal processing of the phonocardiogram: Review of the most recent advancements’,Crit. Rev. TM Biomed. Eng.,23, pp. 163–219Google Scholar
  6. Ergen, B., andTatar, Y. (2003): ‘Optimal continuous wavelet analysis of periodogram signals’. Proc. Int. Conf. Sign. Process., Çanakkale, Turkey,1, pp. 188–192Google Scholar
  7. Folland, R., Hines, E. L., Boilot, P., andMorgan, D. (2002): ‘Classifying coronary dysfunction using neural networks through cardiovascular auscultation’,Med. Biol. Eng. Comput.,40, pp. 339–343CrossRefGoogle Scholar
  8. Hall, L., Maple, J., Agzarian, J., andAbbott, D. (1999): ‘Sensor system for heart sound biomonitor’,Microelectron. J.,31, pp. 583–592Google Scholar
  9. Holldack, K., andRautenberg, H.-W. (Eds) (1979): ‘Phonocardiography (in German: Phono-kardiographie)’ (Georg Thieme Verlag, Stuttgart, Germany, 1979)Google Scholar
  10. Kim, D., andTavel, M. E. (2003): ‘Assessment of severity of aortic stenosis through time-frequency analysis of murmur’,Chest,124, pp. 1638–1644Google Scholar
  11. Lukkarinen, S., Sikioe, K., Noponen, A.-L., Angerla, A., andSepponen, R. (Eds) (1997): ‘Novel software for real-time processing of phonocardiographic signal’ (Helsinki University of Technology, Applied Electronics Laboratory, Chicago, USA, 1997)Google Scholar
  12. Maass, H., andWeber, A. (1952): ‘Recording of heart sounds using distinguishing filters. A study for standardization of the heart sounds (in German: Herzschallregistrierung mittels differenzierender Filter. Eine Studie zur Herzschallnormung)’,Cardiologia,21, p. 773Google Scholar
  13. Mallat, S. G. (1989): ‘A theory for multiresolution signal decomposition’,IEEE Trans. Pattern Anal. Mach. Intell.,11, pp. 674–693CrossRefMATHGoogle Scholar
  14. Messer, S., Agzarian, J., andAbbott, D. (2001): ‘Optimal wavelet denoising for phonocardiograms’,Microelectron. J.,32, pp. 931–941Google Scholar
  15. Moghavvemi, M., Tan, B., andTan, S. (2003): ‘A noninvasive pcbased measurement of fetal phonocardiography’,Sensors Actuators,107, pp. 96–103CrossRefGoogle Scholar
  16. Nesje, O. A. (1978): ‘Severity of aortic stenosis assessed by carotid pulse recordings and phonocardiography’,Acta Med Scand.,204, pp. 321–330Google Scholar
  17. Oelmez, T., andDokur, Z. (2002): ‘Classification of heart sounds using an artificial neural network’,Pattern Recognit. Lett.,24, pp. 617–629Google Scholar
  18. Pavlopoulos, S. A., Stasis, A. C., andLoukis, E. N. (2004): ‘A decision tree-based method for the differential diagnosis of aortic stenosis from mitral regurgitation using heart sounds’,Biomed. Eng. Online 2004,3, p. 21Google Scholar
  19. Rangayyan, R. M., andLehner, R. J. (1987): ‘Phonocardiogram signal analysis: A review’,Crit. Rev. TM Biomed. Eng.,15, pp. 211–236Google Scholar
  20. Tavel, M. (1996): ‘Cardiac auscultation: A glorious past—but does it have a future?’,Circulation,93, pp. 1250–1253Google Scholar
  21. Turkoglu, I., Arslan, A., andIlkay, E. (2003): ‘An intelligent system for diagnosis of the heart valve diseases with wavelet packet neural networks’,Comput. Biol. Med.,33, pp. 319–331CrossRefGoogle Scholar

Copyright information

© IFMBE 2005

Authors and Affiliations

  • J. Herold
    • 1
  • R. Schroeder
    • 1
  • F. Nasticzky
    • 2
  • V. Baier
    • 1
  • A. Mix
    • 1
    • 2
  • T. Huebner
    • 2
  • A. Voss
    • 1
  1. 1.Department of Medical EngineeringUniversity of Applied SciencesJenaGermany
  2. 2.medtrans GmbHJenaGermany

Personalised recommendations