Skip to main content
Log in

Automatic P-wave analysis of patients prone to atrial fibrillation

  • Published:
Medical and Biological Engineering and Computing Aims and scope Submit manuscript


A method is presented for automatic analysis of the P-wave, based on lead II of a 12-lead standard ECG, in resting conditions during a routine examination for the detection of patients prone to atrial fibrillation (AF), one of the most prevalent arrhythmias. First, the P-wave was delineated, and this was achieved in two steps: the detection of the QRS complexes for ECG segmentation, using a wavelet analysis method, and a hidden Markov model to represent one beat of the signal for P-wave isolation. Then, a set of parameters to detect patients prone to AF was calculated from the P-wave. The detection efficiency was validated on an ECG database of 145 patients, including a control group of 63 people and a study group of 82 patients with documented AF. A discriminant analysis was applied, and the results obtained showed a specificity and a sensitivity between 65% and 70%.

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

Access this article

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

Instant access to the full article PDF.

Similar content being viewed by others


  • Abeysekera, R. M. (1994): ‘Detection and classification of ECG signals in the time frequency domain’,Appl. Signal Process.,1, pp. 35–51

    Google Scholar 

  • Clavier, L., Boucher, J. M., andBlanc, J. J. (1996): ‘P-wave parameters for atrial fibrillation risk detection’. 18th Annual International Conference of IEEE Engineering in Medicine Biology Society (IV), pp. 1367–1368

  • Clavier, L., Maheu, B., Provost, K., Mansourati, J., Boucher, J. M., andBlanc, J. J. (1997): ‘Shape and time and frequency domain analysis in addition to P-wave duration markedly improves detection of patients prone to atrial fibrillation’,PACE. NASPE Abstr.,20, p. 1116

    Google Scholar 

  • Clavier, L., Boucher, J. M., andPollard, e. (1998): ‘Hidden Markov models compared to the wavelet transform for P-wave segmentation in ECG signals’ IX European Signal Processing Conference, Rhodes, (IV), pp. 2453–2456

  • Coast, D. A., Stern, R. M., Cano, G. G., andBriller, S. A. (1990): ‘An approach to cardiac arrhythmia analysis using hidden Markov models’,IEEE Trans. Biomed. Eng.,37, pp. 826–836

    Article  Google Scholar 

  • Czys, Z., Petelenz, T., Flak, Z., Sosnowski, M., andLeski, J. (1993): ‘A time frequency domain analysis of atrial late potentials for paroxysmal atrial fibrillation and assessment’,Comput. Cardiol., pp. 45–48

  • Fukunami, M., Yamada, T., Ohmori, M., Kumagai, K., andUmemoto, K. (1991): ‘Detection of patients at risk of paroxysmal atrial fibrillation during sinus rhythm by P wave-triggered signalaveraged electrocardiogram’,Circulation,83, pp. 162–169

    Google Scholar 

  • Kanel, W. B., Abbott, R. D., Savage, D. D., andMcNamara, P. M. (1982): ‘Epidemiologic features of chronic atrial fibrillation: the Framingham Study’,N. Engl. J. Med.,306, pp. 1018–1022

    Google Scholar 

  • Lemire, D., Pharand, C., Rajaonah, J. C., Dube, B., andLeblanc, A. R. (2000): ‘Wavelet time entropy, T-wave morphology and myocardial ischemia’,IEEE Trans. Biomed. Eng.,47, pp. 967–970

    Article  Google Scholar 

  • Li, C., Zheng, C., andTai, C. (1995): ‘Detection of ECG characteristic points using wavelet transform’,IEEE Trans. Biomed. Eng.,42(1), pp. 21–28

    Google Scholar 

  • Niranjan, U. C., andMurthy, I. S. N. (1993): ‘ECG component delineation by Prony's method’,Signal Process.,31, pp. 191–202

    Article  Google Scholar 

  • Pan, J., andTompkins, W. J. (1985): ‘A real-time QRS detector’,IEEE Trans. Biomed. Eng.,32, pp. 230–236

    Google Scholar 

  • Rabiner, L. R. (1989): ‘A tutorial on hidden Markov models and selected applications in speech recognition’,Proc. IEEE,77, pp. 257–286

    Article  Google Scholar 

  • Raitt, M. H., Ingram, K. D., andShinnamon, A. F. (1997): ‘Frequency analysis of the signal averaged P-wave differentiates patients with history of atrial fibrillation from controls independent to P-wave duration’,RACE, NASPE abstracts,20, p. 1220

    Google Scholar 

  • Raudys, S. J., andJain, A. N. (1991): ‘Small sample size effects in statistical pattern recognition: recommendations for practitioners’,IEEE Trans. Pattern Anal. Mach. Intell.,13, pp. 252–264

    Article  Google Scholar 

  • Rix, H., andMalenge, J. P. (1980): ‘Detecting small variations in shape’,IEEE Trans. Syst Man Cybern.,10, pp. 90–96

    MathSciNet  Google Scholar 

  • Saoudi, S., Ghorbel, F., andHillion, A. (1997): ‘Some statistical properties of the Kernel diffeomorphism estimator’,Appl. Stochast. model Data Anal.,13, pp. 39–58

    MathSciNet  Google Scholar 

  • Stafford, P. J., Turner, I., Phil, D., andVincent, R. (1991): ‘Quantitative analysis of signal-averaged P-wave in idiopathic paroxysmal atrial fibrillation’,Am. J. Cardiol.,68, pp. 751–755

    Article  Google Scholar 

  • Thakor, N. V., andZhu, Y. S. (1991): ‘Applications of adaptive filtering to ECG analysis: noise cancellation and arrhythmia detection’,IEEE Trans. Biomed Eng.,38, pp. 785–794

    Article  Google Scholar 

  • Villani, G. O., Piepoli, M., Cripps, T., Rosi, A., andGazzola, U. (1994): ‘Atral late potentials in patient with paroxysmal atrial fibrillation detected using a high gain, signal averaged oesophageal lead’,Pacing Clin. Electrophysiol.,17, pp. 1118–1123

    Google Scholar 

Download references

Author information

Authors and Affiliations


Corresponding author

Correspondence to J. -M. Boucher.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Clavier, L., Boucher, J.M., Lepage, R. et al. Automatic P-wave analysis of patients prone to atrial fibrillation. Med. Biol. Eng. Comput. 40, 63–71 (2002).

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: