K-Means Clustering Algorithm Based Arrhythmic Heart Beat Detection in ECG Signal

Abstract

Disorders in the functions of the heart cause heart diseases or arrhythmias in the cardiovascular system. Diagnosis in cardiac arrhythmias is realized utilizing the Electrocardiogram which is an electrophysiological signal. In this study, a three-class, K-means clustering-based arrhythmia detection method, distinguishing the cardiac arrhythmia type Right Bundle Branch Block and Left Bundle Branch Block from normal heart-beats, is proposed. Data from the MIT-BIH Arrhythmia Database were analyzed for clustering-based arrhythmia analysis. Feature Set 1 was created by extracting the features from the Electrocardiogram signal with the help of QRS morphology, Heart Rate Variability and statistical metrics. The RELIEF feature selection algorithm was used for dimensionality reduction of the obtained features and Feature Set 2 was obtained by determining the most appropriate features in Feature Set 1. Overall performance results for Feature Set 1 were obtained as 99,18% accuracy, the sensitivity of 98,78% and 99,39% specificity while overall performance results for Feature Set 2 were provided as 95,37% accuracy, the sensitivity of 92,99% and 96,54% specificity. In this study, the computational cost was decreased by reducing the processing complexity and load utilizing the reduced feature data set FS2 and an arrhythmia detection method having a satisfactory level of high performance was proposed.

Keywords

• Arrhythmia detection
• Electrocardiogram (ECG)
• K-means clustering
• Machine learning
• RELIEF feature selection algorithm

References

1. [1] O. Yakut, O. Timus, E. D. Bolat, HRV analysis based arrhythmic beat detection using knn classifier, WASET Int. J. Biomedical and Biological Eng., 2016, 10(2), 60-63.
2. [2] Yakut, O., Solak, S., Bolat, E. D., Measuring ECG signal using e-health sensor platform., In International Conference on Chemistry, Biomedical and Environment Engineering, 7-8, October, 2014, Antalya, Turkey.
3. [3] E. Ersoy, ECG signals used on arrhythmia diagnosis with multilayer perceptron neural network, M.S. thesis, Dept. Mechatr. Eng., Gaziosmanpasa Univ., 2016.
4. [4] E. Tek, Right bundle branch block, Available: https://www.resusitasyon. com/sag-dal-blogu/, (date of visit: 21.09.2020).
5. [5] E. Burns, Right bundle branch block (RBBB), Available: https://litfl. com/ right -bundle -branch-block-rbbb-ecg-library/, (date of visit: 21.09.2020).
6. [6] B. P. Griffin, C. M. Rimmerman and E. J. Topol, The cleveland clinic cardiology board review, Lippincott Williams & Wilkins, ch.45, sec.8, 2007.
7. [7] D. Da Costa, W. J. Brady, and J. Edhouse, ABC of clinical electrocardiography: bradycardias and atrioventricular conduction block, British Medical J., 2002, 324(7336), 535-538.
8. [8] E. Tek, Left bundle branch block, Available: https://www. resusitasyon.com/ sol-dal- blogu/, (date of visit: 24.09.2020).

9. [9] F. Akdeniz, Classification of ECG arrhythmias using time-frequency based features, M.S. thesis, Dept. Elec. and Electron. Eng., Karadeniz Technical Univ., 2017.
10. [10] B. Dogan, T. Olmez, Fuzzy clustering of ecg beats using a new metaheuristic approach, In Proc. IWBBIO, 7-9, April, 2014, Granada, Spain.
11. [11] F. I. Donoso, R. L. Figueroa, E. A. Lecannelier, E. J. Pino, A. J. Rojas, Clustering of atrial fibrillation based on surface ecg measurements, In Proc. IEEE EMBC, 3-7, July, 2013, Osaka, Japan.
12. [12] Suganthy, M., Analysis of R-peaks in fetal electrocardiogram to detect heart disorder using fuzzy clustering, In Proc. IEEE 5th I2CT, 29-31, March, 2019, Bombay, India.
13. [13] Wang, X., Wang, S., Tang, Y., Li, B., A new two-type fuzzy c-means clustering algorithm for the diagnosis of ventricular premature beats, In Proc. IEEE MLBDBI, 8-10, November, 2019, Taiyuan, China.
14. [14] S. Yücelbas, Diagnosis of the heart rhythm disorders by using hybrid classifiers, M.S. thesis, Dept. Comp. Eng., Selcuk Univ., 2013.
15. [15] Y. Zhang, X. Zhao, Y. Sun, M. Liu, D. Shi, Waveform classification based on wavelet transform and k-means clustering, In Proc. ICMLC, 14-17 July, 2013, Tianjin, China.
16. [16] A. Dallali, A. Kachouri, M. Samet, Classification of cardiac arrhythmia using wt, hrv, and fuzzy c-means clustering, An Int. J. Signal Processing, 2011, 5(3), 101-109.
17. [17] İ. Hilavin, M. Kuntalp, D. Kuntalp, Classification of arrhythmias using spectral features with k nearest neighbor method, In Proc. SIU, 20-22 April, 2011, Antalya, Turkey.
18. [18] Y. C. Yeh, H. J. Lin, Cardiac arrhythmia diagnosis method using fuzzy c-means algorithm on ecg signals, In Proc. 3CA, 5-7 May, 2010, Tainan, Taiwan.
19. [19] Mohebbanaaz, Y. P. Sai, LV R. Kumari, A review on arrhythmia classification using ecg signals. In Proc. IEEE SCEECS, 22-23, February, 2020, Bhopal, India.
20. [20] G. B. Moody, R. G. Mark, The impact of the MIT-BIH arrhythmia database, IEEE Eng. in Med. and Biol. Mag., 2001, 20(3), 45-50.
21. [21] K. Kira, L. A. Rendell, The feature selection problem: traditional methods and a new algorithm, In Proc. AAAI, 12-16 July, 1992, California, USA.
22. [22] Available: https://www.mathworks.com/ help/stats/relieff.html?s_tid =srchtitle, (date of visit: 11.10.2020).
23. [23] Available: https://home.deib.polimi.it/ matteucc/Clustering/ tutorial_html/kmeans.html, (Date of visit: 13.10.2020).
24. [24] O. Timus, Sleep respiration disorders diagnosis and classification utilizing soft computing algorithms, PhD dissertation, Dept. Elect. Comp. Edu., Kocaeli Univ., 2015.
25. [25] Ö. Yakut, Classification of arrhythmias in ECG signal using soft computing algorithms, PhD dissertation, Dept. Biomedical Engineering, Kocaeli Univ., 2018.