Distinguishing Innocent Murmurs from Murmurs caused by Aortic Stenosis by Recurrence Quantification Analysis

It is sometimes difficult to differentiate between innocent murmurs and pathological murmurs during auscultation. In these difficult cases, an intelligent stethoscope with decision support abilities would be of great value. In this study, using a dog model, phonocardiographic recordings were obtained from 27 boxer dogs with various degrees of aortic stenosis (AS) severity. As a reference for severity assessment, continuous wave Doppler was used. The data were analyzed with recurrence quantification analysis (RQA) with the aim to find features able to distinguish innocent murmurs from murmurs caused by AS. Four out of eight investigated RQA features showed significant differences between innocent murmurs and pathological murmurs. Using a plain linear discriminant analysis classifier, the best pair of features (recurrence rate and entropy) resulted in a sensitivity of 90% and a specificity of 88%. In conclusion, RQA provide valid features which can be used for differentiation between innocent murmurs and murmurs caused by AS.

Authors:

• Christer Ahlstrom
• Katja Höglund
• Peter Hult
• Jens Häggström
• Clarence Kvart
• Per Ask

Keywords:

• Bioacoustics
• murmur
• phonocardiographic signal
• recurrence quantification analysis.

References:

[1] A. G. Tilkian and M. B. Conover, Understanding heart sounds and
murmurs: with an introduction to lung sounds, 4. ed. Philadelphia:
Saunders, 2001.
[2] A. N. Pelech, "The physiology of cardiac auscultation," Pediatr Clin
North Am, vol. 51, pp. 1515-1535, 2004.
[3] C. Ahlstrom, "Processing of the phonocardiographic signal," Licentiate
degree in Linköping Studies in Science and Technology, Thesis no
1253, Dept. of Biomedical Engineering, Linköpings universitet,
Linköping, Sweden, 2006.
[4] K. Höglund, C. Ahlstrom, J. H├ñggström, and C. Kvart, "Spectral analysis
of heart murmurs in boxer dogs," in Proc. 16th ECVIM-CA Congress,
Amsterdam, the Netherlands, 2006, pp. 172.
[5] L. G. Durand and P. Pibarot, "Digital signal processing of the
phonocardiogram: review of the most recent advancements," Crit. Rev.
Biomed. Eng., vol. 23, pp. 163-219, 1995.
[6] R. M. Rangayyan and R. J. Lehner, "Phonocardiogram signal analysis: a
review," Crit Rev Biomed Eng, vol. 15, pp. 211-236, 1987.
[7] S. R. Bhatikar, C. DeGroff, and R. L. Mahajan, "A classifier based on
the artificial neural network approach for cardiologic auscultation in
pediatrics," Artif Intell Med, vol. 33, pp. 251-260, 2005.
[8] I. Cathers, "Neural network assisted cardiac auscultation," Artif. Intell.
Med., vol. 7, pp. 53-66, 1995.
[9] H. Shino, H. Yoshida, K. Yana, K. Harada, J. Sudoh, and E. Harasewa,
"Detection and classification of systolic murmur for phonocardiogram
screening," in Proc. 18th Ann. Int. Conf. of the IEEE, EMBS,
Amsterdam, the Netherlands, 1996, pp. 123-124.
[10] H. N. Sabbah and P. D. Stein, "Turbulent blood flow in humans: its
primary role in the production of ejection murmurs," Circ Res, vol. 38,
pp. 513-525, 1976.
[11] C. Ahlstrom, P. Hult, P. Rask, J. E. Karlsson, E. Nylander, U.
Dahlström, and P. Ask, "Feature Extraction for Systolic Heart Murmur
Classification," Ann Biomed Eng, vol. 34, pp. 1666-1677, 2006.
[12] V. Nigam and R. Priemer, "Accessing heart dynamics to estimate
durations of heart sounds," Physiol Meas, vol. 26, pp. 1005-1018, 2005.
[13] V. Padmanabhan and J. L. Semmlow, "Dynamical analysis of diastolic
heart sounds associated with coronary artery disease," Ann Biomed Eng,
vol. 22, pp. 264-271, 1994.
[14] M. E. Tavel and H. Katz, "Usefulness of a new sound spectral averaging
technique to distinguish an innocent systolic murmur from that of aortic
stenosis," Am J Cardiol, vol. 95, pp. 902-904, 2005.
[15] W. P. Thomas, C. E. Gaber, G. J. Jacobs, P. M. Kaplan, C. W. Lombard,
N. S. Moise, and B. L. Moses, "Recommendations for standards in
transthoracic two-dimensional echocardiography in the dog and cat," J
Vet Intern Med, vol. 7, pp. 247-252, 1993.
[16] L. B. Lehmkuhl and J. D. Bonagura, "Comparison of transducer
placement sites for Doppler echocardiography in dogs with subaortic
stenosis," Am J Vet Res, vol. 55, pp. 192-198, 1994.
[17] R. D. Kienle, "Aortic Stenosis," in Small animal cardiovascular
medicine, M. D. Kittleson and R. D. Kienle, Eds. St. Louis, MO: Mosby,
1998, pp. 260-272.
[18] N. Marwan, N. Wessel, U. Meyerfeldt, A. Schirdewan, and J. Kurths,
"Recurrence-plot-based measures of complexity and their application to
heart-rate-variability data," Phys. Rev. E., vol. 66, pp. 1-8, 2002.
[19] H. Kantz and T. Schreiber, Nonlinear Time Series Analysis, 2. ed.
Cambridge: Cambridge Univ. Press, 2004.
[20] L. Y. Cao, "Practical method for determining the minimum embedding
dimension of a scalar time series," Physica D, vol. 110, pp. 43-50, 1997.
[21] C. L. Webber and J. P. Zbilut, "Dynamical assessment of physiological
systems and states using recurrence plot strategies," J. Appl. Physiol.,
vol. 76, pp. 965-973, 1994.
[22] R. A. Fisher, "The Use of Multiple Measurements in Taxonomic
Problems," Annals of Eugenics, vol. 7, pp. 179-188, 1936.
[23] S. Theodoridis and K. Koutroumbas, Pattern Recognition, 2. ed.
Amsterdam: Academic Press, 2003.
[24] C. Kvart, A. T. French, V. L. Fuentes, J. Haggstrom, J. D. McEwan, and
K. E. Schober, "Analysis of murmur intensity, duration and frequency
components in dogs with aortic stenosis," J Small Anim Pract, vol. 39,
pp. 318-324, 1998.
[25] C. Basso, P. R. Fox, K. M. Meurs, J. A. Towbin, A. W. Spier, F.
Calabrese, B. J. Maron, and G. Thiene, "Arrhythmogenic right
ventricular cardiomyopathy causing sudden cardiac death in boxer dogs:
a new animal model of human disease," Circulation, vol. 109, pp. 1180-
1185, 2004.
[26] C. Bussadori, C. Quintavalla, and A. Capelli, "Prevalence of congenital
heart disease in boxers in Italy," Journal of Veterinary Cardiology, vol.
3, pp. 7-11, 2001.
[27] V. Luis-Fuentes, P. G. C. Darke, and B. M. Cattanach, "Aortic stenosis
in boxer dogs," in Proc. 12th Ann. Forum, ACVIM, San Fransisco, CA,
1994, pp. 309-311.