ECG Arrythmia Analysis: Design and Evaluation Strategies

  • Roger G. Mark
  • George B. Moody

Abstract

Cardiac arrhythmias are a major cause of morbidity and mortality. Long-term ECG analysis is an important diagnostic technique for characterizing arrhythmias and documenting response to therapy. This paper reviews the technology of real-time automated ECG arrhythmia analysis, including principles of algorithm design, and the use of standard ECG databases in development and evaluation.

Keywords

Atrial Fibrillation IEEE Computer Society Ventricular Ectopic Beat Morphology Cluster Arrhythmia Detector 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Mark, R.G., Schluter, P.S., Moody, G.B., Devlin, P.H., Chernoff, D., 1982, An annotated ECG database for evaluating arrhythmia detectors, pp. 205–210, in Frontiers of Engineering in Health Care, Proc. 4th Ann. Conf. IEEE Engineering in Medicine and Biology Soc., IEEE Computer Society Press, Los Alamitos, CA.Google Scholar
  2. 2.
    Hermes, R.E., Geselowitz, D.B., Oliver, G.C., 1980, Development, distribution, and use of the American Heart Association database for ventricular arrhythmia detector evaluation, pp. 263–266, in Computers in Cardiology 1980, IEEE Computer Society Press, Los Alamitos, CA.Google Scholar
  3. 3.
    Moody, G.B., Mark, R.G., 1990, The MIT-BIH Arrhythmia Database on CD ROM and software for use with it, 1991, pp. 185–188, in Computers in Cardiology 1990, IEEE Computer Society Press, Los Alamitos, CA.Google Scholar
  4. 4.
    Nolle, F.M., Badura, F.K., Catlett, J.M., et al., 1986, CREI-GARD: a new concept in computerized arrhythmia monitoring systems, pp. 515–518, in Computers in Cardiology 1986, IEEE Computer Society Press, Los Alamitos, CA.Google Scholar
  5. 5.
    Taddei, A., Biagini, A., Distante, G., et al., 1990, The European ST-T Database: development, distribution, and use, pp. 177–180, in Computers in Cardiology 1990, IEEE Computer Society Press, Los Alamitos, CA.Google Scholar
  6. 6.
    Schluter, P.S., Mark, R.G., Moody, G.B., Olson, W.H., Peterson, S.K., 1980, Performance measures for arrhythmia detectors, pp. 267–270, in Computers in Cardiology 1980, IEEE Computer Society Press, Los Alamitos, CA.Google Scholar
  7. 7.
    Arrhythmia Monitoring Subcommittee of the AAMI ECG Committee]. Testing and Reporting Performance Results of Ventricular Arrhythmia Detection Algorithms [AAMI ECAR]. Association for the Advancement of Medical Instrumentation, Arlington, VA, 1987.Google Scholar
  8. 8.
    Moody, G.B., Feldman, C.L., Bailey, J.J., 1993. Standards and applicable databases for long-term ECG monitoring. J. Electrocardiology 26 (Suppl): 151 - I55.Google Scholar
  9. 9.
    Ambulatory ECG Subcommittee of the AAMI ECG Committee]. American National Standard: Ambulatory Electrocardiographs [ANSUAAMI EC-38] Association for the Advancement of Medical Instrumentation, Arlington. VA. 1994.Google Scholar
  10. 10.
    Moody, G.B., Mark, R.G., 1983. How can we predict real-world performance of an arrhythmia detector?, pp. 71–76, in Computers in Cardiology 1983, IEEE Computer Society Press, Los Alamitos, CA.Google Scholar
  11. 11.
    Greenwald, S.D., Albrecht, P., Moody, G.B., Mark, R.G. 1985, Estimating confidence limits for atrhythmiadetector performance. pp. 383–386. in Computers in Cardiology 1985, IEEE Computer Society Press. Los Alamitos. CA.Google Scholar
  12. 12.
    Albrecht. P., Moody, G.B., Mark, R.G., 1988, Use of the `bootstrap’ to assess the robustness of the performance statistics of an arrhythmia detector, J. Ambulatory Monitoring 1(2): 171–176. Google Scholar
  13. 13.
    Efron, B., 1979, Bootstrap methods: another look at the jackknife. Annals of Statistics, 7: 1–26.MathSciNetMATHCrossRefGoogle Scholar
  14. 14.
    Moody, G.B., Muldrow, W.K., Mark, R.G., 1984, A noise stress test for arrhythmia detectors, pp. 381–384, in Computers in Cardiology 1984, IEEE Computer Society Press, Los Alamitos, CA.Google Scholar
  15. 15.
    Hu, Y.H., Tompkins, W.J., Urrusti, M.S., and Afonso,V.X., 1993, Applications of artificial neural networks for ECG signal detection and classification, J. Electrocardiology, 26 (suppl): 66–73.Google Scholar
  16. 16.
    Moody, G.B., and Mark, R.G., 1982, Development and evaluation of a two-lead ECG analysis program. pp. 39–44, in Computers in Cardiology 1982, IEEE Computer Society Press. Los Alamitos, CA.Google Scholar
  17. 17.
    Rappaport, S.H., Gillick, L., Moody, G.B., and Mark, R.G., 1982, QRS morphology classification: quantitative evaluation of different strategies, pp. 33–38, in Computers in Cardiology 1982, IEEE Computer Society Press, Los Alamitos. CA.Google Scholar
  18. 18.
    Chow, H.S., Moody, G.B., and Mark, R.G., 1992, Detection of ventricular ectopic beats using neural networks, pp. 659–662. in Computers in Cardiology 1992, IEEE Computer Society Press. Los Alamitos, CA.Google Scholar
  19. 19.
    Gersh, W., Eddy, P., and Dong, E., 1970, Cardiac arrhythmia classification: a heart-heat interval Markov chain approach, Comp. Biomed. Res. 4: 385–392.CrossRefGoogle Scholar
  20. 20.
    Moody, G.B., and Mark, R.G., 1983, A new method for detecting atrial fibrillation using RR intervals, pp. 227–230, in Computers in Cardiology 1983, IEEE Computer Society Press. Los Alamitos, CA.Google Scholar
  21. 21.
    Artis, S.G., Mark, R.G., and Moody, G.B., 1991. Detection of atrial fibrillation using artificial neural networks, pp. 173–176. in Computers in Cardiology 1991, IEEE Computer Society Press. Los Alamitos, (’A.Google Scholar
  22. 22.
    Moody, G.B., and Mark, R.G., 1989, QRS morphology representation and noise estimation using the Karhunan-Loeve transform. pp 269–272, in Computers in Cardiology 1989. IEEE Computer Society Press. Los Alamitos, CA.Google Scholar
  23. 23.
    Feldman, C.L., and Hubelbank. M., 1978, Apparatus and method for ECG baseline shift detecting. U.S. Patent 41.112, 930.Google Scholar
  24. 24.
    Devlin, P.H., Mark, R.G., and Moody, G.B., 1984, Detecting electrode motion noise in ECG signals by monitoring electrode impedance, pp. 51–56, in Computers in Cardiology 1984, IEEE Computer Society Press, Los Alamitos, (.’A.Google Scholar
  25. 25.
    Ferguson, P. F., and Mark. R•G., 1986, An algorithm to reduce false positive alarms in arrhythmia detectors using dynamic electrode impedance monitoring. pp. 511–514. in Compeers in Cardiology 1986, IEEE Computer Society Press, Los Alamitos, CA.Google Scholar
  26. 26.
    Muldrow, W.K., Mark, R.G.. Long. W.J., and Moody, G.B., 1986. CALVIN: A rule-based expert system for improving arrhythmia detector performance during noisy ECGs. pp. 21–26, in Computers in Cardiology 1986, IEEE Computer Society Press. Los Alamitos. CA.Google Scholar
  27. 27.
    Greenwald, S.D., Patil, R.S., and Mark, R.G., 1992, Improved detection and classification of arrhythmias in noise-corrupted electrocardiograms using contextual information within an expert system, Biomed. Instrum. Technol. 26 (2): 124–132.Google Scholar
  28. 28.
    Greenwald, S.D., 1990, Improved Detection and Classification of Arrhythmias in Noise-Corrupted Electrocardiograms using Contextual Information. Doctoral Thesis. Massachusetts Institute of Technology, June, 1990.Google Scholar

Copyright information

© Springer Science+Business Media New York 1996

Authors and Affiliations

  • Roger G. Mark
    • 1
  • George B. Moody
    • 1
  1. 1.Massachusetts Institute of TechnologyHarvard-MIT Division of Health Sciences and TechnologyCambridgeUSA

Personalised recommendations