Classification of coronary artery diseased and normal subjects using multi-channel phonocardiogram signal

• Autorzy: Samanta Pranab , Pathak Akanksha , Mandana Kayapanda , Saha Goutam

Identyfikatory

DOI

10.1016/j.bbe.2019.02.003

• Języki publikacji: EN

Abstrakty

EN

Coronary artery disease (CAD) is one of the leading causes of mortality and morbidity. There is a need to develop a simple, reliable, and non-invasive screening tool to diagnose CAD. Prior studies reported that turbulent blood flow due to stenosed coronary arteries causes weak CAD murmurs. Analysis of phonocardiogram (PCG) signals can be useful to detect these murmurs. In this work, we propose a new multi-channel PCG-based system to classify CAD-affected and normal subjects, and it does not require any additional reference signal, such as an electrocardiogram (ECG) signal. The proposed system simultaneously acquires PCG signals from four different auscultation sites on the chest. It extracts five different features from time and frequency domains of the PCG signals. The two-class classification is done in a machine learning framework by employing an artificial neural network (ANN) classifier. The classification performances are evaluated for each channel as well as for their combinations. Experimental results show that the proposed sub-band-based spectral features perform well for both clean and noisy data. An accuracy of 82.57% is obtained using the combination of the signals acquired from tricuspid, mitral, and midaxillary regions. The multi-channel system gives more than 4% relative improvement over the best performance obtained by its single-channel counterpart, and the proposed features outperform earlier used features.

Słowa kluczowe

EN

artificial neural network; coronary artery disease; multichannel PCG signal; signal complexity; spectral features; sub-band analysis

PL

sztuczna sieć neuronowa; choroba wieńcowa; kompleksowość sygnału; cecha spektralna

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2019
• Tom: Vol. 39, no. 2
• Strony: 426--443
• Opis fizyczny: Bibliogr. 43 poz., rys., tab., wykr.

Twórcy

autor

Samanta Pranab

• Indian Institute of Technology Kharagpur, Electronics and Electrical Communication Engineering IIT Kharagpur, Kharagpur, West Bengal 721302, India

autor

Pathak Akanksha

• Indian Institute of Technology Kharagpur, Electronics and Electrical Communication Engineering IIT Kharagpur, Kharagpur, West Bengal India

autor

Mandana Kayapanda

• Indian Institute of Technology Kharagpur, Electronics and Electrical Communication Engineering IIT Kharagpur, Kharagpur, West Bengal India

autor

Saha Goutam

• Indian Institute of Technology Kharagpur, Electronics and Electrical Communication Engineering IIT Kharagpur, Kharagpur, West Bengal India

Bibliografia

• [1] WH Organisation. Cardiovascular diseases; 2012, URL www.who.int/mediacentre/factsheets/fs317/en/ (accessed: 2.10.2016).
• [2] Nissen SE. Limitations of computed tomography coronary angiography. J Am Coll Cardiol 2008;52(25):2145–7.
• [3] Papadakis SJM, Maxine A, Rabow MW. Current medical diagnosis and treatment. 55th edition. New York, NY: Lange Medical Book; 2016, McGraw Hill Medical, 2016.
• [4] Ari S, Hembram K, Saha G. Detection of cardiac abnormality from PCG signal using LMS based least square SVM classifier. Expert Syst Appl 2010;37(12):8019–26.
• [5] Lees RS, Dewey CF. Phonoangiography: a new noninvasive diagnostic method for studying arterial disease. Proc Natl Acad Sci USA 1970;67(2):935–42.
• [6] Semmlow J, Welkowitz W, Kostis J, Mackenzie J. Coronary artery disease-correlates between diastolic auditory characteristics and coronary artery stenoses. IEEE Trans Biomed Eng 1983;2(BME-30):136–9.
• [7] Wang J-z, Tie B, Welkowitz W, Semmlow JL, Kostis JB. Modeling sound generation in stenosed coronary arteries. IEEE Trans Biomed Eng 1990;37(11):1087–94.
• [8] Akay YM, Akay M, Welkowitz W, Semmlow JL, Kostis JB. Noninvasive acoustical detection of coronary artery disease: a comparative study of signal processing methods. IEEE Trans Biomed Eng 1993;40(6):571–8.
• [9] Dock W, Zoneraich S. A diastolic murmur arising in a stenosed coronary artery. Am J Med 1967;42(4):617–9.
• [10] Padmanabhan V, Semmlow JL. Dynamical analysis of diastolic heart sounds associated with coronary artery disease. Ann Biomed Eng 1994;22(3):264–71.
• [11] Akay M, Akay YM, Gauthier D, Paden RG, Pavlicek W, Fortuin FD, et al. Dynamics of diastolic sounds caused by partially occluded coronary arteries. IEEE Trans Biomed Eng 2009;56(2):513–7.
• [12] Schmidt SE, Holst-Hansen C, Hansen J, Toft E, Struijk JJ. Acoustic features for the identification of coronary artery disease. IEEE Trans Biomed Eng 2015;62(11):2611–9.
• [13] Griffel B, Zia M, Fridman V, Saponieri C, Semmlow J. Microphone placement evaluation for acoustic detection of coronary artery disease. 2011 IEEE 37th Annual Northeast Bioengineering Conference (NEBEC); 2011. pp. 1–2.
• [14] Griffel B, Zia MK, Fridman V, Saponieri C, Semmlow JL. Detection of coronary artery disease using automutual information. Cardiovasc Eng Technol 2012;3(3):333–44.
• [15] Griffel B, Zia MK, Fridman V, Saponieri C, Semmlow JL. Path length entropy analysis of diastolic heart sounds. Comput Biol Med 2013;43(9):1154–66.
• [16] Duncan GW, Gruber JO, Dewey CFJ, Myers GS, Lees RS. Evaluation of carotid stenosis by phonoangiography. N Engl J Med 1975;293(22):1124–8. http://dx.doi.org/10.1056/NEJM197511272932205. PMID: 127121.
• [17] Ganong WF. Review of medical physiology. 17-th edition. East Norwalk, CT: Lange Medical Book, Appleton & Lange; 1995. p. 565–8.
• [18] Gibson TAPDG, Brown DJ. Analysis of left ventricular wall movement during isovolumic relaxation and its relation to coronary artery disease. Br Heart J 1976;38(10):1010–9.
• [19] Akay M. Noninvasive diagnosis of coronary artery disease using a neural network algorithm. Biol Cybern 1992;67(4):361–7.
• [20] Akay M, Welkowitz W. Acoustical detection of coronary occlusions using neural networks. J Biomed Eng 1993;15 (6):469–73.
• [21] Liu C, Springer D, Li Q, Moody B, Juan RA, Chorro FJ, et al. An open access database for the evaluation of heart sound algorithms. Physiol Meas 2016;37(12):2181.
• [22] Meloun M, Militky J. Statistical data analysis. New Delhi, India: WPI; 2011. p. 259–60.
• [23] White NK, Edwards JE, Dry TJ. The relationship of the degree of coronary atherosclerosis with age, in men. Circulation 1950;1(4):645–54.
• [24] Segall HN. Heart sounds and murmurs in 400 normal subjects. Can Med Assoc J 1962;87(8):377.
• [25] Rodeheffer RJ, Gerstenblith G, Becker LC, Fleg JL, Weisfeldt ML, Lakatta EG. Exercise cardiac output is maintained with advancing age in healthy human subjects: cardiac dilatation and increased stroke volume compensate for a diminished heart rate. Circulation 1984;69(2):203–13.
• [26] Swinne CJ, Shapiro EP, Lima SD, Fleg JL. Age-associated changes in left ventricular diastolic performance during isometric exercise in normal subjects. Am J Cardiol 1992;69(8):823–6. http://dx.doi.org/10.1016/0002-9149(92)90518-4.
• [27] Ari S, Saha G. On a robust algorithm for heart sound segmentation. J Mech Med Biol 2007;7(02):129–50.
• [28] Rangayyan RM, Reddy NP. Biomedical Signal Analysis: A Case-Study Approach, vol. 30. New York: Pergamon Press; 2002. p. 259–63. 305–307.
• [29] Hjorth B. EEG analysis based on time domain properties. Electroencephalogr Clin Neurophysiol 1970;29(3):306–10.
• [30] Guion-Johnson M. Detection of coronary artery disease using an electronic stethoscope, Google Patents 2009, US Patent A 12/406,849. URL https://www.google.co.in/patents/US20090177107.
• [31] Friedman HH. Diagnostic electrocardiography and vectorcardiography. 2nd ed. New York: McGraw Hill Inc.; 1977 [appendix: 593].
• [32] Proakis JG, Manolakis DG. Digital signal processsing principles, algorithms, and applications. 3rd ed. Prentice Hall; 1996. p. 448–94.
• [33] Welch PD. The use of fast Fourier transform for the estimation of power spectra: a method based on time averaging over short, modified periodograms. IEEE Trans Signal Process 1967;15(2):70–3.
• [34] Chua KC, Chandran V, Acharya UR, Lim CM. Application of higher order statistics/spectra in biomedical signals – a review. Med Eng Phys 2010;32(7):679–89.
• [35] Sabeti M, Katebi S, Boostani R. Entropy and complexity measures for EEG signal classification of schizophrenic and control participants. Artif Intell Med 2009;47(3):263–74.
• [36] Johnson GR, Adolph RJ, Campbell DJ. Estimation of the severity of aortic valve stenosis by frequency analysis of the murmur. J Am Coll Cardiol 1983;1(5):1315–23.
• [37] Møller MF. A scaled conjugate gradient algorithm for fast supervised learning. Neural Netw 1993;6(4):525–33.
• [38] Mitchell T. Machine learning. 2nd ed. McGraw Hill Education (India) Private Limited; 2013. p. 108–12.
• [39] Wilamowski BM, Yu H. Improved computation for levenberg-marquardt training. IEEE Trans Neural Netw 2010;21(6):930–7.
• [40] Hadi HM, Mashor MY, Suboh MZ, Mohamed MS. Classification of heart sound based on S-transform and neural network. 2010 10th International Conference on Information Sciences Signal Processing and their Applications (ISSPA); 2010. pp. 189–92.
• [41] Demuth HB, Beale MH, De Jess O, Hagan MT. Neural network design. Martin Hagan; 2014.
• [42] Sengupta N, Sahidullah M, Saha G. Lung sound classification using cepstral-based statistical features. Comput Biol Med 2016;75:118–29.
• [43] Physionet 2016. Classification of normal/abnormal heart sound recordings: the physionet/computing in cardiology challenge; 2016, URL http://physionet.org/challenge/2016/ (accessed: 14.4.2016).

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).