Order determination in autoregressive modeling of diastolic heart sounds
- 47 Downloads
Previous studies demonstrated that spectral analysis of diastolic heart sounds may provide valuable information for the detection of coronary artery disease. Although parametric modeling methods were successfully used to achieve this goal, and showed considerable performance, the accuracy and precision of the analysis is strongly dependent on the model order selected. In order to investigate the effects of model order selection on the analysis, diastolic heart sounds recorded from both normal and diseased patients were analyzed using the AR modeling, which is computationally the most efficient parametric spectral analysis method. The model orders were determined by using four different model order selection criteria. The results showed that the four criteria yielded different orders for the same data set. On the other hand, different criteria showed different performance in different measurement conditions. Effect of arbitrary order selection was also discussed. As a result, an optimal AR model order that may be used for every case was determined.
Key Wordsdiastolic heart sounds coronary artery disease model order selection
Unable to display preview. Download preview PDF.
- 2.Cheng, T. O., Diagnostic murmur caused by coronary artery stenosis,Ann. Intern. Med. 72:543–546, 1970.Google Scholar
- 3.Sangster, J. F., Diagnostic murmur of coronary artery stenosis.Brit. Heart J. 35:840–844, 1973.Google Scholar
- 6.Lees, R. S. and Myers, G. S., Noninvasive diagnosis of arterial disease.Adv. Intern. 23:475–509, 1983.Google Scholar
- 7.Semmlow, J. L., Welkowitz, W., Kostis, J. B., and Mackenzie, J. W., Coronary artery disease-correlates between diastolic auditory characteristics and coronary artery stenoses.IEEE Trans. Biomed. Eng. 30:136–139, 1983.Google Scholar
- 8.Akay M., Bauer, M., Semmlow, J. L., Welkowitz, W., and Kostis, J. B., AR modeling of diastolic heart sounds.Proc. IEEE Front. Med. New Orleans, LA, 172–175, 1988.Google Scholar
- 9.Akay M., Semmlow, J. L., Welkowitz, W., and Kostis, J. B., Parametric analysis of diastolic heart sounds before and after angioplasty.Proc. IEEE Front. Med. Seattle, WA, 51–53, 1989.Google Scholar
- 12.Akay, M., Welkowitz, W., Semmlow, J. L., and Kostis, J., Application of ARMA method to acoustic detection of coronary artery disease.Med. Biol. Eng. Comp. 29:365–372, 1991.Google Scholar
- 13.Kay, S. M., and Marple, S. L., Spectral analysis: a modern perspective.Proc. IEEE 69:1380–1419, 1981.Google Scholar
- 14.Paiss, O., and Inbar, G. F., Autoregressive modeling of surface EMG and its spectrum with application to fatigueIEEE Trans. Biomed. Eng. 34:761–771, 1987.Google Scholar
- 19.Güler, N. F., Kiymik, M. K., and Güler, I., Autoregressive-based sonogram outputs of 20 MHz pulsed Doppler data.Med. Progress Tech. 21:105–110, 1995.Google Scholar
- 21.Ulrich, T. J., and Bishop, T. N., Maximum entropy spectral analysis and autoregressive decomposition.Rev. Geophys. Space Phys. 13:183–200, 1975.Google Scholar