Model-Based Atrial Fibrillation Detection

  • Paulo de Carvalho
  • Jorge Henriques
  • Ricardo Couceiro
  • Matthew Harris
  • Manuel Antunes
  • Joerg Habetha


Atrial fibrillation (AF) is the most common cardiac arrhythmia, leading to several patient risks. This kind of arrhythmia affects mostly elderly people, in particular those who suffer from heart failure disease, one of the main causes of hospitalization. Thus, detection of AF becomes decisive in the diagnosis and prevention of cardiac threats, with particular interest in the context of pHealth solutions.This chapter presents a real-time AF detection scheme, developed within the MyHeart project, a pHealth project financed by the European Commission. The proposed strategy is based on a computational intelligence approach, combining expert knowledge and neural networks. In particular, it makes use of the three principal physiological characteristics of AF, applied by cardiologists in their daily reasoning: P wave absence/presence, heart rate irregularity, and atrial activity analysis. This knowledge-based approach has the advantage of increasing interpretability of the results to the medical community, while improving detection robustness.The clinical validation of the strategy is performed using public databases (MIT-BIH Arrhythmia and QT databases from Physionet) as well as the ECG data acquired with the MyHeart vest during the MyHeart trial.


Atrial Fibrillation Atrial Fibrillation Patient Atrial Fibrillation Episode Morphological Derivative Lone Atrial Fibrillation 



This project was partially financed by the IST FP6 MyHeart project, IST-2002-507816 supported by the European Union.


  1. Alan, G., Hylek, E., Phillips, K., Chang, Y., Henault, L., Selby, J., Singer, D.: Prevalence of diagnosed atrial fibrillation in adults: national implications for rhythm management and stroke prevention: the nticoagulation and risk factors in atrial fibrillation (ATRIA) study. JAMA. 285, 2370–2375 (2001)CrossRefGoogle Scholar
  2. Al-Nashash, H.: Cardiac arrhythmia classification using neural networks. Technol. Health Care. 8(6), 363–372 (2000)Google Scholar
  3. Cerutti, S., Mainardi, L.T., Porta, A., Bianchi, A.: Analysis of the dynamics of RR interval series for the detection of atrial fibrillation episodes. IEEE Comput. Cardiol. 24, 77–80 (1997)Google Scholar
  4. Chikh, M., Gbelgacem, N., Reguig, F.: The use of artificial neural networks to detect PVC beats. Lab. de Génie Biomédical. Dép. d’électronique, Univ. Abou Bekr Belkaïd (2003)Google Scholar
  5. Chikh, M., Belgacem, N., Chikh, A., Reguig, F.: The use of artificial neural network to detect the premature ventricular contraction (PVC) beats. Electron. J. Tech. Acoust. 2, 1–14 (2004)Google Scholar
  6. Christov, I., Bortolan, G.: Ranking of pattern recognition parameters for premature ventricular contractions classification by neural networks. Physiol. Meas. 25, 1281–1290 (2004)CrossRefGoogle Scholar
  7. Christov, I., Jekova, I., Bortolan, G.: Premature ventricular contraction classification by the Kth nearest-neighbours rule. Physiol. Meas. 26, 123–130 (2005)CrossRefGoogle Scholar
  8. Cleland, J., Louis, A., Rigby, A., Janssens, U., Balk, A.: Noninvasive home telemonitoring for patients with heart failure at high risk of recurrent admission and death. J. Am. Coll. Cardiol. 45, 1654–1664 (2005)CrossRefGoogle Scholar
  9. Couceiro, R., Carvalho, P., Henriques, J., Antunes, M.: On the detection of premature ventricular contractions. Conf. Proc. IEEE Eng. Med. Biol. Soc. 2008:1087–1091 (2008)Google Scholar
  10. Fuster, V., Rydén, L., Asinger, R., Cannom, D., Crijns, H., Frye, R., Halperin, J., Kay, G., Klein, E., Lévy, S., MCNamara, R., Prysowsky, E., Wann, L., Wyse, D.: ACC/AHA/ESC guidelines for the management of patients with atrial fibrillation. J. Am. Coll. Cardiol. 38(4), 1231–1265, 765 (2001)Google Scholar
  11. Habetha, J.: The myheart project – fighting cardiovascular diseases by prevention and early diagnosis. Conf. Proc. IEEE Eng. Med. Biol. Soc. 6746–6749 (2006)Google Scholar
  12. Ham, F., Han, S.: Classification of cardiac arrhythmias using Fuzzy ARTMAP. IEEE Trans. Biomed. Eng. 43(4), 425–430 (1996)CrossRefGoogle Scholar
  13. Jalife, J.: Experimental and clinical AF mechanisms: bridging the divide. J. Intervent. Card. Electrophysiol. 9, 85–92 (2003)CrossRefGoogle Scholar
  14. Jekova, I., Bortolan, G., Christov, I.: Pattern recognition and optimal parameter selection in premature ventricular contraction classification. IEEE Comput. Cardiol. 31, 357–360 (2004)CrossRefGoogle Scholar
  15. Levy, A., Camm, J., Saksena, S.: International consensus on nomenclature and classification of atrial fibrillation: a collaborative of the working group an arrhythmias and the work group of cardiac pacing of the European society of cardiology and the north American society of pain and electrophysiology. Cardiovasc. Electrophysiol. 14, 443–445 (2003)CrossRefGoogle Scholar
  16. Lévy, S., Breithardt, G., Campbell, R., Camm, A., Daubert, J., Allessie, M., Aliot, E., Capucci, A., Cosio, F., Crijns, H., Jordaens, L., Hauer, R., Lombardi, F., Lüderitz, B.: Atrial fibrillation: current knowledge and recommendations for management. Eur. Heart J. 19(9), 1294–1320 (1998)CrossRefGoogle Scholar
  17. Millet, J., Perez, M., Joseph, G., Mocholi, A., Chorro, J.: Previous identification of QRS onset and offset is not essential for classifying QRS complexes in a single lead. IEEE Comput. Cardiol. 24, 299–302 (1997)Google Scholar
  18. Moe, G., Abildskov, J.: Observations on the ventricular dysrhythmia associated with atrial fibrillation in the dog heart. Circ. Res. 4, 447–460 (1964)Google Scholar
  19. Moody, B., Mark, R.: A new method for detecting atrial fibrillation using RR intervals. IEEE Comput. Cardiol. 10, 227–230 (1983)Google Scholar
  20. Moraes, J., Seixas, M., Vilani, F., Costa, E.: A real time QRS complex classification method using Mahalanobis distance. IEEE Comput. Cardiol. 29, 201–204 (2002)Google Scholar
  21. Omer, T., Giovangrandi, L., Kovacs, G.: Robust neural-network-based classification of premature ventricular contraction using wavelet transform and timing interval features. IEEE Trans. Biomed. Eng. 53(12), 2507–2515 (2006)CrossRefGoogle Scholar
  22. Reiter, H., Maglaveras, N.: HeartCycle: compliance and effectiveness in HF and CAD closed-loop management. Conf. Proc. IEEE Eng. Med. Biol. Soc. 299–302 (2009)Google Scholar
  23. Ribeiro, B., Marques, A., Henriques, J.: Choosing real-time predictors for ventricular arrhythmia detection. Int. J. Pattern Recog. Artifi. Intell. 21(8), 1–15 (2007)Google Scholar
  24. Sanchez, C., Millet, J., Rieta, J., Castells, F., Ródenas, J., Ruiz-Granell, R., Ruiz, V.: Packet wavelet decomposition: an approach for atrial activity extraction. IEEE Comput. Cardiol. 29, 33–36 (2002)Google Scholar
  25. Senhadji, L., Wang, F., Hernandez, A., Carrault, G.: Wavelets extrema representation for QRS-T cancellation and P wave detection. IEEE Comput. Cardiol. 29, 37–40 (2002)Google Scholar
  26. Sherman, D.: Pharmacological rate versus rhythm control. Stroek. 38, 615 (2007)Google Scholar
  27. Shkurovich, S., Sahakian, A., Swiryn, S.: Detection of atrial activity from high-voltage leads of implantable ventricular fibrillators, using a cancellation technique. IEEE Trans. Biomed. Eng. 45(2), 229–234 (1998)CrossRefGoogle Scholar
  28. Sun, Y., Chan, K., Krishnan, S.: Characteristic wave detection in ECG signal using morphological transform. BMC Cardiovasc. Disord. 5, 28 (2005)CrossRefGoogle Scholar
  29. Tateno, K., Glass, L.: A method for detection of atrial fibrillation using RR intervals. IEEE Comput. Cardiol. 27, 391–394 (2000)Google Scholar
  30. Waldo, A.: Mechanisms of atrial fibrillation. J. Cardiovasc. Electrophysiol. 14(12), 267–274 (2003)CrossRefGoogle Scholar
  31. Wang, J., Yeo, C., Aguire, A.: The design and evaluation of a new multi-lead arrhythmia monitoring algorithm. IEEE Comput. Cardiol. 26, 675–678 (1999)Google Scholar
  32. Wieben, O., Afonso, V., Tompkinks, W.: Classification of premature ventricular complexes using filter bank features, induction of decision trees and a fuzzy rule-based system. Med. Biol. Eng. Comput. 37(1), 560–565 (1999)CrossRefGoogle Scholar
  33. Wolf, P., Abbott, R., Kannel, W.: Atrial fibrillation as an independent risk factor for stroke: the Framingham Study. Stroke. 22, 983–988 (1991)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2012

Authors and Affiliations

  • Paulo de Carvalho
    • 1
  • Jorge Henriques
    • 1
  • Ricardo Couceiro
    • 1
  • Matthew Harris
    • 2
    • 3
  • Manuel Antunes
    • 4
  • Joerg Habetha
    • 4
  1. 1.Center for Informatics and SystemsUniversity of CoimbraCoimbraPortugal
  2. 2.Cardio-thoracic Surgery CenterUniversity Hospital of CoimbraCoimbraPortugal
  3. 3.Faculty of MedicineUniversity of CoimbraCoimbraPortugal
  4. 4.Philips Research LaboratoriesAachenGermany

Personalised recommendations