Advertisement

Preclustering of Electrocardiographic Signals Using Left-to-Right Hidden Markov Models

  • Pau Micó
  • David Cuesta
  • Daniel Novák
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3138)

Abstract

Holter signals are ambulatory long-term electrocardiographic (ECG) registers used to detect heart diseases which are difficult to find in normal ECGs. These signals normally include several channels and its duration is up to 48 hours. The principal problem for the cardiologists consists of the manual inspection of the whole holter ECG to find all those beats whose morphology differ from the normal synus rhythm. The later analisys of these arrhythmia beats yields a diagnostic from the pacient’s heart condition. The Hidden Markov Models (HMM) can be used in ECG diagnosis avoiding the manual inspection. In this paper we improve the performance of the HMM clustering method introducing a preclustering stage in order to diminish the number of elements to be finally processed and reducing the global computational cost. An experimental comparative study is carried out, utilizing records form the MIT-BIH Arrhythmia database. Finally some results are presented in order to validate the procedure.

References

  1. 1.
    Burrus, S.: Introduction to Wavelets andWavelet Transforms. Prentice-Hall, Englewood Cliffs (1997)Google Scholar
  2. 2.
    Cuesta, D.: Estudio de métodos para procesamiento y agrupación de senales electrocardiogr áficas. Ph.D.Thesis, Valencia (2001)Google Scholar
  3. 3.
    Cuesta, D., Micó, P., Novák, D.: Clustering electrocardiograph signals using Hidden Markov Models. In: European Medical and Biological Engineering Conference, Vienna (2002)Google Scholar
  4. 4.
    Daubechies, I.: Ten lectures on wavelets (1992)Google Scholar
  5. 5.
    Duda, R., Hart, P., Stork, D.: Pattern Classification. John Wiley & Sons, Chichester (2001)zbMATHGoogle Scholar
  6. 6.
    Koski, A.: Modelling ECG signals with hidden Markov models. Artificial Intelligence in Medicine 8 (1996)Google Scholar
  7. 7.
    Mark, R., Moody, G.: MIT-BIH arrhythmia data base directory. Massachusetts Institute of Technology - Beth Israel Deaconess Medical Center (1998)Google Scholar
  8. 8.
    Novák, D., Cuesta, D., Micó, P., Lhotská, L.: Number of arrhythmia beats in Holter ECG: how many clusters? In: 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Cancún (2003)Google Scholar
  9. 9.
    Novák, D.: Electrocardiogram Signal Processing using Hidden Markov Models. Ph.D.Thesis, Prague (2004)Google Scholar
  10. 10.
    Obermaier, B.: Hidden Markov Models for online classification of single trial EEG data. Pattern Recognition Letters 22 (2001)Google Scholar
  11. 11.
    Rabiner, R.: A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proceedings of the IEEE 77 (1989)Google Scholar
  12. 12.
    Rezek, I., Roberts, S.J.: Learning Ensemble Hidden Markov Models for Biosignal Analysis. In: 14th International Conference on Digital Signal Processing (2002)Google Scholar
  13. 13.
    Vidal, E., Marzal, A.: A Review and New Approaches for Automatic Segmentation of Speech Signals. In: Signal Processing V: Theories and Applications, Elsevier Science Publishers B. V, Amsterdam (1990)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Pau Micó
    • 1
  • David Cuesta
    • 1
  • Daniel Novák
    • 2
  1. 1.Department of Systems Informatics and ComputersPolytechnic School of AlcoiAlcoiSpain
  2. 2.Department of CyberneticsCzech Technical University in PragueCzech Republic

Personalised recommendations