A Review of Kernel Methods in ECG Signal Classification

  • José L. Rojo-Álvarez
  • Gustavo Camps-Valls
  • Antonio J. Caamaño-Fernández
  • Juan F. Guerrero-Martínez


Kernel methods have been shown to be effective in the analysis of electrocardiogram (ECG) signals. These techniques provide a consistent and well-founded theoretical framework for developing nonlinear algorithms. Kernel methods exhibit useful properties when applied to challenging design scenarios, such as: (1) when dealing with low number of (potentially high dimensional) training samples; (2) in the presence of heterogenous multimodalities; and (3) with different noise sources in the data. These characteristics are particularly appropriate for biomedical signal processing and analysis, and hence, the widespread of these techniques in biomedical signal processing in general, and in ECG data analysis in particular. Specifically, kernel methods have improved the performance of both parametric linear methods and neural networks in applications such as cardiac beat detection in 12-lead ECG, detection of electrocardiographic changes in partial epileptic patients, automatic identification of reliable heart rates, detection of obstructive sleep apnea, automatic seizure detection in the newborn, or cardiac sound murmurs classification, just to name a few. This chapter provides a survey of applications of kernel methods in the context of ECG signal analysis. The chapter summarizes the theory of kernel methods, and studies the different application domains. Noting that the vast majority of applications in the literature reduce to the use of the standard support vector machine, we pay special attention to other kernel machines available in the literature that may be of interest for practitioners. Finally, we foresee some other future research lines in the development of specific kernel methods to deal with the data peculiarities.


Obstructive Sleep Apnea Heart Rate Variability Chronic Fatigue Syndrome Kernel Method Radial Basis Function Kernel 
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.



This work was partially supported by projects CICYT-FEDER TEC2009-13696, AYA2008-05965-C04-03, CSD2007-00018, TEC2009-12098, and TEC2010-19263.


  1. Abboud, M.F., Linkens, D.A., Mahfouf, M., Dounias, G.: Survey on the use of smart and adaptive engineering systems in medicine. Artif. Intell. Med. 26, 179–209 (2002)CrossRefGoogle Scholar
  2. Abreu-Lima, C., de Sa, J.P.: Automatic classifiers for the interpretation of electrocardiograms. Rev. Port. Cardiol. 17, 415–28 (1998)Google Scholar
  3. Alonso-Atienza, F., Rosado-Muñoz, A., Rojo-Álvarez, J.L., Camps-Valls, G.: Learning the relevant features of ventricular fibrillation from automatic detection algorithms. In: Hines, E., Martínez-Ramón, M., Pardo, M., Llobet, E., Leeson, M., Iliescu, D., J.Y. (eds.) Intelligent Systems: Techniques and Applications, pp. 505–534. Shaker Publishing, Maastrich, Netherlands (2008)Google Scholar
  4. Brugada, P., Brugada, J., Mont, L., Smeets, J., Andries, E.W.: A new approach to the differential diagnosis of a regular tachycardia with a wide QRS complex. Circulation 83, 1649–59 (1991)Google Scholar
  5. Camps-Valls, G., Guerrero-Martínez, J.F.: Neural networks in ECG classification: what is next in adaptive systems? In: Kamruzzaman, J., Begg, R.K., Sarker, R.A., (eds.) Neural Networks in Healthcare: Potential and Challenges, pp. 81–104. Idea Group Publishing, Hershey (2006). ISBN: 1-59140-848-2
  6. Carrault, G., Cordier, M.O., Quiniou, R., Wang, F.: Temporal abstraction and inductive logic programming for arrhythmia recognition from electrocardiograms. Artif. Intell. Med. 28, 231–63 (2003)CrossRefGoogle Scholar
  7. Dybowski, R.: Neural computation in medicine: perspectives and prospects. In: Proceedings of the Artificial Neural Networks in Medicine and Biology Conference, pp. 26–36. Springer, Göteborg, Sweden (2000)Google Scholar
  8. Einthoven: Un Nouveau galvanométre. Arch Néerland Sci exactes naturelles, Serie 2, 6, 625–633 (1901)Google Scholar
  9. Exarchos, T., Tsipouras, M., Exarchos, C., Papaloukas, C., Fotiadis, D., Michalis, L.: A methodology for the automated creation of fuzzy expert systems for ischaemic and arrhythmic beat classification based on a set of rules obtained by a decision tree. Artif. Intell. Med. 40, 187–200 (2007)CrossRefGoogle Scholar
  10. Golub, G.H., Van Loan, C.F.: Matrix Computations (Johns Hopkins Studies in Mathematical Sciences). The Johns Hopkins University Press, Baltimore (1996)Google Scholar
  11. Graja, S., Boucher, J.: SVM classification of patients prone to atrial fibrillation. In: IEEE International Workshop on Intelligent Signal Processing, pp. 370–374. Faro (2005)Google Scholar
  12. Itchhaporia, D., Snow, P.B., Almassy, R.J., Oetgen, W.J.: Artificial neural networks: current status in cardiovascular medicine. J. Am. Coll. Cardiol. 28, 515–21 (1996)CrossRefGoogle Scholar
  13. Ji, S.Y., Chen, W., Ward, K., Rickards, C., Ryan, K., Convertino, V., Najarian, K.: Wavelet based analysis of physiological signals for prediction of severity of hemorrhagic shock. In: International Conference on Complex Medical Engineering, pp. 1–6. ICME, IEEE press Tempe, AZ, USA (2009)Google Scholar
  14. Joshi, A., Chandran, S., Jayaraman, V., Kulkarni, B.: Hybrid SVM for multiclass arrhythmia classification. In: IEEE International Conference on Bioinformatics and Biomedicine, pp.287–290. IEEE Computer Society, Piscataway (2009)Google Scholar
  15. Kamousi, B., Tewfik, A., Lin, B., Al-Ahmad, A., Hsia, H., Zei, P., Wang, P.: A new approach for icd rhythm classification based on support vector machines. In: International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 2478–2481. IEEE Computer Society, Minneapolis (2009)Google Scholar
  16. Kampouraki, A., Manis, G., Nikou, C.: Heartbeat time series classification with support vector machines. IEEE Trans. Inf. Technol. Biomed. 13, 512–518 (2009)CrossRefGoogle Scholar
  17. Khandoker, A., Kimura, Y., Palaniswami, M.: Automated identification of abnormal fetuses using fetal ECG and Doppler ultrasound signals. In: Computers in Cardiology, pp. 709–712. IEEE, Piscataway (2009a)Google Scholar
  18. Khandoker, A., Palaniswami, M., Karmakar, C.: Support vector machines for automated recognition of obstructive sleep apnea syndrome from ECG recordings. IEEE Trans. Inf. Technol. Biomed. 13, 37–48 (2009b)CrossRefGoogle Scholar
  19. Kilpatrick, D., Johnston, P.: Origin of the electrocardiogram. IEEE Eng. Med. Biol. Mag. 13, 479–486 (1994)CrossRefGoogle Scholar
  20. Konttila, T., Stenroos, M., Vaananen, H., Hanninen, H., Lindholm, M., Tierala, I., Katila, T.: Support vector classification of acute myocardial ischemia with reduced sets of body surface potential map electrodes. In: Computers in Cardiology, pp. 869–872. IEEE, Piscataway (2005)Google Scholar
  21. Kostka, P., Tkacz, E.: Feature extraction for improving the support vector machine biomedical data classifier performance. In: Information Technology and Applications in Biomedicine, 2008. International Conference on ITAB 2008. 362–365. Shenzhen (2008)Google Scholar
  22. Kumaravel, N., Rajesh, J., Nithiyanandam, N.: Equivalent tree representation of electrocardiogram using genetic algorithm. Biomed. Sci. Instrum. 33, 573–578 (1997)Google Scholar
  23. Le Blanc, R.: Quantitative analysis of cardiac arrhythmias. crc: Critical review in biomedical engineeering. In: MIT-BIH Database Distribution. 2003. Mitchell, T.M., Machine Learning. pp. 14–1 (1986)
  24. Lisboa, P.J., Vellido, A., Wong, H.: Bias reduction in skewed binary classification with Bayesian neural networks. Neural Netw. 13, 407–410 (2000)CrossRefGoogle Scholar
  25. Mahalingam, N., Kumar, D.: Neural networks for signal processing applications: ECG classification. Austral. Phys. Eng. Sci. Med. 20, 147–151 (1997)Google Scholar
  26. Mehta, S., Lingayat, N.: Detection of T-waves in 12-lead electrocardiogram. In: International Conference on Computational Intelligence and Multimedia Applications, 2007, vol. 2. 512–516. IEEE Computer Society, Washington (2007)Google Scholar
  27. Mehta, S., Lingayat, N.: SVM-based algorithm for recognition of QRS complexes in electrocardiogram. IRBM 29, 310–317 (2008a)CrossRefGoogle Scholar
  28. Mehta, S., Lingayat, N.: Combined entropy based method for detection of QRS complexes in 12-lead electrocardiogram using SVM. Comput. Biol. Med. 38, 138–145 (2008b)CrossRefGoogle Scholar
  29. Mehta, S., Lingayat, N.: Development of SVM based classification techniques for the delineation of wave components in 12-lead electrocardiogram. Biomed. Signal Process. Control 3, 341–349 (2008c)CrossRefGoogle Scholar
  30. Melgani, F., Bazi, Y.: Classification of electrocardiogram signals with support vector machines and particle swarm optimization. IEEE Trans. Inf. Technol. Biomed. 12, 667–677 (2008)CrossRefGoogle Scholar
  31. Miller, A.S., Blott, B.H., Hames, T.K.: Review of neural network applications in medical imaging and signal processing. Med. Biol. Eng. Comput. 30, 449–464 (1992)CrossRefGoogle Scholar
  32. Miyaji, M., Kawanaka, H., Oguri, K.: Driver’s cognitive distraction detection using physiological features by the adaboost. In: International IEEE Conference on Intelligent Transportation Systems, pp. 1–6. IEEE, St. Louis (2009)Google Scholar
  33. Mora, F., Passariello, G., Carrault, G., Le Pichon, J.P.: Intelligent patient monitoring and management systems: a review. IEEE Eng. Med. Biol. Mag. 12, 23–33 (1993)CrossRefGoogle Scholar
  34. Nugent, C.D., Webb, J.A.C., Black, N.D., Wright, G.T.H., McIntyre, M.: An intelligent framework for the classification of the 12-lead ECG. Artif. Intell. Med. 16, 205–222 (1999)CrossRefGoogle Scholar
  35. Osowski, S., Hoai, L.T., Markiewicz, T.: Support vector machine-based expert system for reliable heartbeat recognition. IEEE Trans. Biomed. Eng. 51, 582–589 (2004)CrossRefGoogle Scholar
  36. Patangay, A., Vemuri, P., Tewfik, A.: Monitoring of obstructive sleep apnea in heart failure patients. In: Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 1043–1046. IEEE, Lyon (2007)Google Scholar
  37. Reed, M.C., Simon, B.: Functional Analysis. Volume I of Methods of Modern Mathematical Physics. Academic, New York (1980)MATHGoogle Scholar
  38. Ribeiro, B., Marques, A., Henriques, J., Antunes, M.: Premature ventricular beat detection by using spectral clustering methods. In: Computers in Cardiology, 2007, pp. 149–152. IEEE, Piscataway (2007)Google Scholar
  39. Ribeiro, B., Henirques, J., Marques, A., Antunes, M.: Manifold learning for premature ventricular contraction detection. In: Computers in Cardiology, pp. 917–920. IEEE, Piscataway (2008)Google Scholar
  40. Rojo-Alvarez, J.L., Arenal-Maiz, A., Artes-Rodriguez, A.: Discriminating between supraventricular and ventricular tachycardias from egm onset analysis. IEEE Eng. Med. Biol. Mag. 21, 16–26 (2002a)CrossRefGoogle Scholar
  41. Rojo-Alvarez, J.L., Arenal-Maiz, A., Artes-Rodriguez, A.: Support vector black-box interpretation in ventricular arrhythmia discrimination. IEEE Eng. Med. Biol. Mag. 21, 27–35 (2002b)CrossRefGoogle Scholar
  42. Schölkopf, B., Smola, A.: Learning with Kernels – Support Vector Machines, Regularization, Optimization and Beyond. MIT Press, Cambridge, MA (2002)Google Scholar
  43. Schölkopf, B., Williamson, R.C., Smola, A., Shawe-Taylor, J.: Support vector method for novelty detection. In: Advances in Neural Information Processing Systems (NIPS), Vol. 12. MIT Press, Cambridge, MA, (1999)Google Scholar
  44. Schölkopf, B., Smola, A.J., Williamson, R.C., Bartlett, P.L.: New support vector algorithms. J. Neural Comput. 2, 1207–1245 (2000)CrossRefGoogle Scholar
  45. Sepúlveda-Sanchis, J., Camps-Valls, G., Soria-Olivas, E., Salcedo-Sanz, S., Bousoño-Calzón, C., Sanz-Romero, G., Marrugat de la Iglesia, J.: Support vector machines and genetic algorithms for detecting unstable angina. In: Computers in Cardiology, Vol. 29, pp. 261–265. IEEE, Piscataway (2002)Google Scholar
  46. Tax, D., Duin, R.P.: Support vector domain description. Pattern Recognit. Lett. 20, 1191–1199 (1999)CrossRefGoogle Scholar
  47. Ubeyli, E.D.: ECG beats classification using multiclass support vector machines with error correcting output codes. Digit. Signal Process. 17, 675–684 (2007)CrossRefGoogle Scholar
  48. Uyar, A., Gurgen, F.: Arrhythmia classification using serial fusion of support vector machines and logistic regression. In: IEEE Workshop on Intelligent Data Acquisition and Advanced Computing Systems, Technology and Applications, pp. 560–565. IEEE, Piscataway (2007)Google Scholar
  49. Watrous, R., Towell, G.: A patient-adaptive neural network ECG patient monitoring algorithm. In: Computers in Cardiology 1995. pp. 229–232. IEEE Computer Society, Long Beach (1995)Google Scholar
  50. Yi-Zhi, W., Hong-An, X., Yong-Sheng, D., Jin-Lan, S., Bo-Hui, Z.: SVM based chronic fatigue syndrome evaluation for intelligent garment. In: International Conference on Bioinformatics and Biomedical Engineering. pp. 1947–1950. IEEE Xplore, Piscataway (2008)Google Scholar
  51. Zellmer, E., Shang, F., Zhang, A.: Highly accurate ECG beat classification based on continuous wavelet transformation and multiple support vector machine classifiers. In: International Conference on Biomedical Engineering and Informatics. pp. 1–5. IEEE, Piscataway (2009)Google Scholar
  52. Zhao, Q., Zhang, L.: ECG feature extraction and classification using wavelet transform and support vector machines. In: International Conference on Neural Networks and Brain, Vol. 2, pp. 1089–1092. IEEE, Piscataway (2005)Google Scholar

Copyright information

© Springer-Verlag London Limited 2012

Authors and Affiliations

  • José L. Rojo-Álvarez
    • 1
  • Gustavo Camps-Valls
    • 2
  • Antonio J. Caamaño-Fernández
    • 1
  • Juan F. Guerrero-Martínez
    • 2
  1. 1.Universidad Rey Juan Carlos de MadridFuenlabradaSpain
  2. 2.Universitat de ValènciaBurjassotSpain

Personalised recommendations