Skip to main content

Advertisement

Springer Nature Link
Log in

Noninvasive diagnosis of coronary artery disease using a neural network algorithm

  • Published:
Biological Cybernetics Aims and scope Submit manuscript

Abstract

This study examines the utility of neural networks for detecting coronary artery disease noninvasively by using the clinical examination variables and extracting useful information from the diastolic heart sounds associated with coronary occlusions. It has been widely reported that coronary stenoses produce sounds due to the turbulent blood flow in these vessels. These complex and highly attenuated signals taken from recordings made in both soundproof and noisy rooms were detected and analyzed to provide feature set based on the poles and power spectral density function (PSD) of the Autoregressive (AR) method after Adaptive Line Enhancement (ALE) method. In addition, some physical examination variables such as sex, age, body weight, smoking condition, diastolic pressure, systolic pressure and derivation from them were included in the feature vector. This feature vector was used as the input pattern to the neural network. The analysis was studied on one hundred recordings (63 abnormal, 37 normals). The network correctly identified 84% of the subjects with coronary artery disease and 89% of the normal subjects.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Akay M, Semmlow JL, Welkowitz W, Bauer M, Kostis J (1990a) Detection of coronary occlusions using AR modelling of diastolic heart sounds. IEEE Trans Biomed Eng BME-37:366–373

    Article  CAS  Google Scholar 

  • Akay M, Semmlow JL, Welkowitz W, Bauer M, Kostis J (1990b) Noninvasive detection of coronary occlusions using eigenvector methods before and after angioplasty. IEEE Trans Biomed Eng BME-37:1095–1105

    Article  CAS  Google Scholar 

  • Akay M (1990) Noninvasive detection of coronary artery disease using advanced signal processing methods. Ph.D. Dissertation, Rutgers University, Piscataway, NJ

    Google Scholar 

  • Akay M, Welkowitz W, Semmlow JL, Kostis J (1991) Application of the ARMA method to acoustic detection of coronary artery disease. Med Biol Eng Comput 29:365–362

    CAS  PubMed  Google Scholar 

  • Akay M, Welkowitz W, Semmlow JL, Kostis J (1992) Noninvasive acoustical detection of coronary artery disease using adaptive line enhancer method. Med Biol Eng Comput, in press

  • Al-Nashash HAM, Kelly SW (1987) Beat-to-beat detection of hispurkinje system signals using adaptive filters. Med. Biol Eng Comput 26:117–125

    Google Scholar 

  • Berne RM, Levy MN (1986) Cardiovascular physiology. Mosby, St. Louis

    Google Scholar 

  • Blinowska A, Chatellier G, Bernier J, Larvil M (1991) Bayesian statistics as applied to hypertension diagnosis. IEEE Trans BME-38:699–706

    CAS  Google Scholar 

  • Chen J, Vandewalle J, Sansen W, Vantrappen G, Janssens J (1989) Adaptive method for cancellation of respiratory artifact in electrogastric measurements. Med Biol Eng Comp 27:57–63

    CAS  Google Scholar 

  • Cheng TO (1970) Diagnostic murmer caused by coronary artery stenosis. Ann Int Med 72:543–546

    CAS  PubMed  Google Scholar 

  • Connor WE, Bristow JD (1985) Coronary heart disease. Lippincott, Philadelphia

    Google Scholar 

  • Costantini C, Sampaolesi A, Serra CM, Pacheco G, Neuburger J, Conci E, Haendchen R (1991) Coronary venous retroperfusion support high risk angioplasty in patients with unstable angina: preliminary experience. American College of Cardiology 18:283–292

    Article  CAS  Google Scholar 

  • David J-Y, Jones SA, Giddens DP (1991) Modern spectral analysis techniques for blood flow velocity and spectral measurements with pulsed doppler ultrasound. IEEE Trans BME-38:589–596

    CAS  Google Scholar 

  • Dock W, Zoneraich S (1967) A diastolic murmer arising in a stenosed coronary artery. Am J Med 42:617

    Article  CAS  PubMed  Google Scholar 

  • Duncan GW, Gruber TO, Dewey CF, Myers GS, Lees RS (1975) Evaluation of carotid stenosis by phonoangiography. N Eng J Med 27:1124–1128

    Article  Google Scholar 

  • Eaker ED, Packard B, Thom TJ (1989) Epidemiology and risk factors for coronary artery disease in women. Cardiovas Clin 19:129–145

    CAS  Google Scholar 

  • Ferrara ER, Widrow B (1981) Adaptive filtering for signal enhancement. IEEE Trans ASSP 29:458–460

    Google Scholar 

  • Feyter PJ, Serruys PW, Davies MJ, Richardson P, Lubsen J, Oliver MF (1991) Quantitative coronary angiography to measure progression and regression of coronary atherosclerosis. Circulation 84:412–423

    PubMed  Google Scholar 

  • Ganong WF (1981) Review of medical physiology. Lange, Los Altos, pp 485–488

    Google Scholar 

  • Gillum RF (1987) Coronary artery bypass surgery and coronary angiography in the United States. Am Heart J 113:1255–1260

    Article  CAS  PubMed  Google Scholar 

  • Goldberg S (1988) Coronary angioplasty. Davis, Philadelphia

    Google Scholar 

  • Gruntzig AR, King SB, Schlumpf M (1987) Long term follow-up after percutaneous transluminal coronary angioplasty. N Eng J Med 316:1127

    Article  Google Scholar 

  • Guyton AC (1987) Textbook of medical physiology. Saunders, Philadelphia

    Google Scholar 

  • Haykin S (1986) Adaptive filter theory. Prentice Hall, Englewood Cliffs

    Google Scholar 

  • Huang W, Lippmann R (1987) Comparison between neural network and conventional classifiers. Proc IEEE International Conference on Neural networks, pp 485–494

  • Iwata A, Nagasaka Y, Suzumura N (1990) Data compression of the ECG using neural network for digital holter monitor. IEEE EMBS Magazine, pp 53

  • Iyer VK, Ramamoorthy PA, Ploysongsang Y (1989) Autoregressive modeling of lung sounds: characterization of source and transmission. IEEE Trans BME-36:1133–1136

    CAS  Google Scholar 

  • Johnson MR (1985) Special diagnostic tests and procedures. Phys Ther 65:1856–1865

    CAS  PubMed  Google Scholar 

  • Lees RS, Myers GS (1982) Noninvasive diagnosis of arterial disease. Adv Int 23:475–509

    Google Scholar 

  • Lippmann R (1987) An introduction to computing with neural networks. IEEE ASSP Magazine 4–22

  • Kartchner MM, McRae LP, Morrison FD (1973) Noninvasive detection and evaluation of carotid occlusive disease. Arch Surg 106:528–535

    CAS  PubMed  Google Scholar 

  • Kaul S, Newell JB, Chesler DA, Pohost GM, Okada RD, Guiney TE, Boucher CA (1986) Value of computer analysis of exercise thallium images in the noninvasive detection of coronary artery disease. JAMA 255:508–511

    Article  CAS  PubMed  Google Scholar 

  • Kay SM, Marple SL (1981) Spectral analysis: a modern perspective. Proc IEEE 69:1380–1419

    Article  Google Scholar 

  • Kelly MF, Parker PA, Scott RN (1990) The application of neural networks to myoelectric analysis: a preliminary study. IEEE Trans Biomed Eng 37:221–230

    Article  CAS  PubMed  Google Scholar 

  • Kentie MA, Van Der Schee ET, Grashius JL, Smout AJPM (1981) Adaptive filtering of canine electrogastrographic signals — Part I; System design. Med Biol Eng Comput 19:759–764

    CAS  PubMed  Google Scholar 

  • Khalifa AMA, Giddens DP (1981) Characterization of post-stenotic flow disturbances. J Biomech 14:275–296

    Article  Google Scholar 

  • Khan SS, Nessim S, Gray R, Czer LS, Chaux A, Matloff J (1990) Increased mortality of women in coronary artery bypass surgery: evidence for referral bias. Ann Int Med. 107:19–25

    Google Scholar 

  • Krupp MA (1982) Current medical diagnosis and treatment. Lange, Los Altos, pp 193–210

    Google Scholar 

  • Kurogi S (1991) Speech recognition by an artificial neural network using findings on the afferent auditory system. Biol Cybern 64:243–250

    Article  CAS  PubMed  Google Scholar 

  • Kurtz KJ (1984) Dynamic vascular ausculation. Am J Med 76:1066–1074

    Article  CAS  PubMed  Google Scholar 

  • Larvil M, Chateller G, Degoulet P, Sauquet D, Jeunemaitre X, Menard J, Rovani C (1988) ARTEL: an expert system in hypertension for the general practitioner. In: Lecture Notes in Medical Informatics. Springer, Berlin Heidelberg New York pp 314–321

    Google Scholar 

  • Makhoul J (1981) Spectral linear properties and applications. Trans ASSP 29:282–296

    Google Scholar 

  • Marmarou RM, White MW, Marmarou A (1990) Classification of somatosensory of evoked potentials recorded from patients with severe head injuries. IEEE BME Mag 43–49

  • Marple SL (1976) Conventional fourier, autoregressive, and special ARMA methods of spectrum analysis. Engineer's Dissertation, Stanford University

  • Orfanidis SJ (1988) Optimum signal processing. Macmillan, New York

    Google Scholar 

  • Padmanabhan V, Fisher R, Semmlow JL, Welkowitz W, Kostis J (1989) High sensitivity PCG transducer for extended frequency applications. Proc IEEE Front Med 57–59

  • Rumelhart D, Hunton GE, Williams RJ (1986) Learning internal representations by error propagation. Chap 8, Vol I: Parallel Distributed Processing: Explorations in the microstructure of cognition. MIT Press, Cambridge pp 318–362

    Google Scholar 

  • Sejnowski T, Rosenberg CR (1986) NET talk: a parallel network that learns to read aloud. Johns Hopkins University Technical Reports, JHU/EECS-86/01

  • Semmlow JL, Welkowitz W, Kostis J, Mackenzie JW (1983) Coronary artery disease-correlates between diastolic auditory characteristic and coronary artery stenoses. IEEE Trans Biomed Eng 30:136–139

    CAS  PubMed  Google Scholar 

  • Semmlow JL, Akay M, Welkowitz W (1990) Noninvasive detection of CAD using parametric analysis methods. IEEE, EMBS Mag 9:33–37

    Article  CAS  Google Scholar 

  • Shen D, Semmlow J, Welkowitz W (1990) Automated identification of artifact-free diastolic heart sounds. Proc IEEE Front Med 569–570

  • Sox HC, Blatt MA, Higgins MC, Marton KI (1988) Medical decision making. Butterworth, London

    Google Scholar 

  • Stolzenberg J (1980) Stress-thalium-201 scanning in CAD. Med Clin North Am 64:149–162

    CAS  PubMed  Google Scholar 

  • Teichholtz LE (1984) Cardiointegram detection CAD using in normal resting electrocardiograms. J Am Coll Cardiol 3:598

    Google Scholar 

  • Topol EJ (1989) Emergency strategies for failed percutaneous transluminal coronary angioplasty. Am J Cardiol 63:249–250

    Article  CAS  PubMed  Google Scholar 

  • Vogl TP, Mangis JK, Rigler JK, Zink WT, Alken TL (1988) Accelerating the convergence of the back propagation method. Biol Cybern 59:257–263

    Article  Google Scholar 

  • Wegner NK (1990) Gender, coronary artery disease, and coronary by-pass surgery. Ann Int Med 112:557–558

    Google Scholar 

  • Welkowitz W, Akay M, Wang JZ, Semmlow J, Kostis J (1990) A model for disturbed coronary artery flow with phonocardiographic verification. In: Sideman S, Beyer R (eds) Activation, circulation and transport in the cardiac muscle. Kluwer, New York

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Biomedical Engineering Department, Rutgers University, College of Engineering, P.O. Box 909, 08855-0909, Piscataway, NJ, USA

    Metin Akay

Authors
  1. Metin Akay
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Akay, M. Noninvasive diagnosis of coronary artery disease using a neural network algorithm. Biol. Cybern. 67, 361–367 (1992). https://doi.org/10.1007/BF02414891

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02414891

Keywords