• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology


Indian Journal of Science and Technology

Year: 2022, Volume: 15, Issue: 17, Pages: 767-777

Original Article

Atrial Fibrillation Discrimination for Real-Time ECG Monitoring Based On QT Interval Variation

Received Date:07 January 2022, Accepted Date:12 March 2022, Published Date:09 May 2022


Background/Objectives: An occasional Atrial Fibrillation (AF) event in heart rhythm should be monitored regularly, in continuous intervals. Timely detection of these anomalies in heart rhythm is required to save patients from sudden cardiac arrest. Method: A long-duration ECG categorization algorithm named AFECOC is proposed. For this one-minute-long 71 signals are attained from the Physionet’s “MIT-BIH arrhythmia (MA)” and “AF” database. Two-stage filtering of noisy signals is employed before signal analysis. Four algorithms i.e. Error-Correcting Output Code (ECOC), Naïve Bayes, Decision Tree, and K-Nearest Neighbor(K-NN) are applied to reduce the feature set and then signals are classified with ECOC classifier. Findings: It was found that the ECOC algorithm gives the highest accuracy of 81.95% on the complete feature set. To exclude the irrelevant features, the highest performing algorithm ECOC was used that extracts the combination of the feature sets that get most affected during AF. The combination of ’heart-beat’ and ’mean QT-interval’ are found to be the most relevant features affected during AF events. The accuracy of these two features was evaluated with four classifiers namely ECOC, Naïve Bayes, Decision tree-based and K mean classifier and the accuracy obtained was 89.6%, 76.19%, 76.19%, and 61% respectively. It concludes that the proposed methodology achieved the highest accuracy of 89.6% with the ECOC classifier. Finally, all the AF rhythms have been checked using annotated labels for spontaneous change in QT-interval to verify the designed methodologies. Novelty: Instead of missing P-waves and RR-interval variation, recognition of mean QT interval variation-based AF event detection algorithm gives better accuracy for longer signals. Hence, it can be implemented in Real- Time continuous monitoring.

Keywords: Atrial Fibrillation (AF); Classification; Error Correcting Output Code (ECOC); Feature extraction; QTinterval


  1. Ioannidis P, Zografos T, Christoforatou E, Kouvelas K, Tsoumeleas A, Vassilopoulos C. The Electrophysiology of Atrial Fibrillation: From Basic Mechanisms to Catheter Ablation. Cardiology Research and Practice. 2021;2021:1–14. Available from: https://dx.doi.org/10.1155/2021/4109269
  2. Salinas-Martínez R, Bie Jd, Marzocchi N, Sandberg F. Detection of Brief Episodes of Atrial Fibrillation Based on Electrocardiomatrix and Convolutional Neural Network. Frontiers in Physiology. 2021;12:1–16. Available from: https://dx.doi.org/10.3389/fphys.2021.673819
  3. Dias FM, Samesima N, Ribeiro A, Moreno RA, Pastore CA, Krieger JE, et al. 2D Image-Based Atrial Fibrillation Classification. 2021 Computing in Cardiology (CinC). 2021;48:1–4. doi: 10.23919/CinC53138.2021.9662735
  4. Wang D, Meng Q, Chen D, Zhang H, Xu L. Automatic Detection of Arrhythmia Based on Multi-Resolution Representation of ECG Signal. Sensors. 2020;20(6):1579. Available from: https://dx.doi.org/10.3390/s20061579
  5. Shen M, Zhang L, Luo X, Xu J. Atrial Fibrillation Detection Algorithm Based on Manual Extraction Features and Automatic Extraction Features. IOP Conference Series: Earth and Environmental Science. 2020;428(1):012050. Available from: https://dx.doi.org/10.1088/1755-1315/428/1/012050
  6. Tooley J, Ouyang D, Hadley D, Turakhia M, Wang P, Ashley E, et al. Comparison of QT Interval Measurement Methods and Correction Formulas in Atrial Fibrillation. The American Journal of Cardiology. 2019;123(11):1822–1827. Available from: https://dx.doi.org/10.1016/j.amjcard.2019.02.057
  7. Zheng J, Chu H, Struppa D, Zhang J, Yacoub SM, El-Askary H, et al. Optimal Multi-Stage Arrhythmia Classification Approach. Scientific Reports. 2020;10(1):1–17. Available from: https://dx.doi.org/10.1038/s41598-020-59821-7
  8. Dash A, Torado C, Paw N, Fan D, Pezeshkian N, Srivatsa U. QT correction in atrial fibrillation – Measurement revisited. Journal of Electrocardiology. 2019;56:70–76. Available from: https://dx.doi.org/10.1016/j.jelectrocard.2019.06.009
  9. Sai YP. A review on arrhythmia classification using ECG signals. In 2020 IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS). 2020;p. 1–6. doi: 10.1007/978-981-33-6081-5_31
  10. Chen H, Maharatna K. An Automatic R and T Peak Detection Method Based on the Combination of Hierarchical Clustering and Discrete Wavelet Transform. IEEE Journal of Biomedical and Health Informatics. 2020;24(10):2825–2832. Available from: https://dx.doi.org/10.1109/jbhi.2020.2973982
  11. Brian A, Sabna N, Paulson GG. ECG based algorithm for detecting ventricular arrhythmia and atrial fibrillation. 2017 International Conference on Intelligent Computing and Control Systems (ICICCS). 2017;p. 506–511. doi: 10.1109/ICCONS.2017.8250773
  12. Venkatesan C, Karthigaikumar P, Paul A, Satheeskumaran S, Kumar R. ECG Signal Preprocessing and SVM Classifier-Based Abnormality Detection in Remote Healthcare Applications. IEEE Access. 2018;6:9767–9773. Available from: https://dx.doi.org/10.1109/access.2018.2794346
  13. Zhao T, Wang X, Qiu C. An Early Warning of Atrial Fibrillation Based on Short-Time ECG Signals. Journal of Healthcare Engineering. 2022;2022:1–7. Available from: https://dx.doi.org/10.1155/2022/2205460
  14. Nagpal A, Singh V. Feature selection from high dimensional data based on iterative qualitative mutual information. Journal of Intelligent & Fuzzy Systems. 2019;36:5845–5856. Available from: https://dx.doi.org/10.3233/jifs-181665
  15. Seo HC, Oh S, Kim H, Joo S. ECG data dependency for atrial fibrillation detection based on residual networks. Scientific Reports. 2021;11(1):1–8. Available from: https://dx.doi.org/10.1038/s41598-021-97308-1
  16. Xia Y, Wulan N, Wang K, Zhang H. Detecting atrial fibrillation by deep convolutional neural networks. Computers in Biology and Medicine. 2018;93:84–92. Available from: https://dx.doi.org/10.1016/j.compbiomed.2017.12.007
  17. Xiong Z, Stiles MK, Zhao J. Robust ECG Signal Classification for the Detection of Atrial Fibrillation Using Novel Neural Networks. Computing in Cardiology Conference (CinC). 2017;p. 1–4. doi: 10.22489/CinC.2017.066-138
  18. Andersen RS, Peimankar A, Puthusserypady S. A deep learning approach for real-time detection of atrial fibrillation. Expert Systems with Applications. 2019;115:465–473. Available from: https://dx.doi.org/10.1016/j.eswa.2018.08.011
  19. Al-dabag M, ALRikabi H, Al-Nima R. Anticipating Atrial Fibrillation Signal Using Efficient Algorithm. International Journal of Online and Biomedical Engineering (iJOE). 2021;17:106. Available from: https://dx.doi.org/10.3991/ijoe.v17i02.19183
  20. Christov I, Krasteva V, Simova I, Neycheva T, Schmid R. Multi-parametric analysis for atrial fibrillation classification in ECG. In: In 2017 Computing in Cardiology (CinC). (pp. 1-4) 2017. 10.22489/CinC.2017.175-021
  21. Dang H, Sun M, Zhang G, Qi X, Zhou X, Chang Q. A Novel Deep Arrhythmia-Diagnosis Network for Atrial Fibrillation Classification Using Electrocardiogram Signals. IEEE Access. 2019;7:75577–75590. Available from: https://dx.doi.org/10.1109/access.2019.2918792
  22. Calderon A, Perez A, Valente J. ECG Feature Extraction and Ventricular Fibrillation (VF) Prediction using Data Mining Techniques. 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS). 2019;p. 14–19. doi: 10.1109/CBMS.2019.00014
  23. Ebrahimzadeh E, Kalantari M, Joulani M, Shahraki RS, Fayaz F, Ahmadi F. Prediction of paroxysmal Atrial Fibrillation: A machine learning based approach using combined feature vector and mixture of expert classification on HRV signal. Computer Methods and Programs in Biomedicine. 2018;165:53–67. doi: 10.1016/j.cmpb.2018.07.014
  24. Boon KH, Khalil-Hani M, Malarvili M. Paroxysmal atrial fibrillation prediction based on HRV analysis and non-dominated sorting genetic algorithm III. Computer Methods and Programs in Biomedicine. 2018;153:171–184. Available from: https://dx.doi.org/10.1016/j.cmpb.2017.10.012
  25. Pyakillya B, Kazachenko N, Mikhailovsky N. Deep Learning for ECG Classification. Journal of Physics: Conference Series. 2017;913:012004. Available from: https://dx.doi.org/10.1088/1742-6596/913/1/012004
  26. Liu N, Sun M, Wang L, Zhou W, Dang H, Zhou X. A support vector machine approach for AF classification from a short single-lead ECG recording. Physiological Measurement. 2018;39(6):064004. Available from: https://dx.doi.org/10.1088/1361-6579/aac7aa


© 2022 Soni et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Published By Indian Society for Education and Environment (iSee)


Subscribe now for latest articles and news.