A Model-Based Approach for Arrhythmia Detection and Classification

  • Hongzu Li
  • Pierre BoulangerEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11010)


Automatic real-time ECG patterns detection and classification has great importance in early diagnosis and treatment of life-threatening cardiac arrhythmia [7]. In this paper, we developed an algorithm which could classify abnormal heartbeat at more than 85% accuracy. The ECG data of this research are provided by MIT-BIH Arrhythmia Database from Physionet. We extracted seven features from each ECG record to represent the ECG signal. Furthermore, Support Vector Machine and Multi-Layer Perceptron Neural Network are used for classification. We were able to achieve over 85% accuracy and with only 10% difference between sensitivity and specificity.


ECG Machine learning Pattern recognition Support vector machine Neural network 


  1. 1.
    Clifford, G., Lopez, D., Li, Q., Rezek, I.: Signal quality indices and data fusion for determining acceptability of electrocardiograms collected in noisy ambulatory environments. In: Computing in Cardiology, pp. 285–288. IEEE (2011)Google Scholar
  2. 2.
    Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)zbMATHGoogle Scholar
  3. 3.
    Natrella, M.: NIST/SEMATECH e-Handbook of Statistical Methods (2010)Google Scholar
  4. 4.
    Nordqvist, C.: Arrhythmia: causes, symptoms, types, and treatment (2017).
  5. 5.
    Sathyanarayana, S.: A gentle introduction to backpropagation (2014)Google Scholar
  6. 6.
    Tat, T.H.C., Xiang, C., Thiam, L.E.: Physionet challenge 2011: improving the quality of electrocardiography data collected using real time QRS-complex and t-wave detection. In: Computing in Cardiology, pp. 441–444. IEEE (2011)Google Scholar
  7. 7.
    Tuzcu, V., Nas, S.: Dynamic time warping as a novel tool in pattern recognition of ECG changes in heart rhythm disturbances. In: 2005 IEEE International Conference on Systems, Man and Cybernetics, vol. 1, pp. 182–186. IEEE (2005)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.University of AlbertaEdmontonCanada

Personalised recommendations