ECG arrhythmia classification using cyclic transformations and regression-based features

Abstract

The clinical importance of detecting cardiac diseases has led to ongoing efforts to improve classification algorithms used in electrocardiography (ECG) analysis. Because ECG signals are patterned, non-stationary, and complex, representing them in cyclic form and extracting features designed for this representation may improve classification performance compared to conventional methods. In this study, the ECG signals were transformed into cyclic form and this transformation was validated using statistical tests. The transformed signals were then classified using features specifically developed for cyclic data. At the same time, classification was also performed on the original raw, untransformed signals to enable comparison. In addition, the study introduced a regression-based feature set as a second novel contribution. This feature set was designed to work with both cyclic and non-cyclic signal representations, making it suitable for a broader range of analysis conditions. The classification results were evaluated across four transformation cases and three sets of characteristics, providing a comprehensive analysis of ECG signal classification. An important strength of this study is that the labels correspond to specific types of arrhythmia. This allows the evaluation to remain clinically grounded and supports a more meaningful assessment of how well different classes of ECG signal can be distinguished. In general, the proposed framework provides clinically relevant findings and may advance the detection of ECG-based arrhythmias.

Keywords

• Classification
• cyclic transformation
• electrocardiography
• feature extraction
• regression

Supporting Institution

Middle East Yechnical University

Ethical Statement

The datasets used in the analyses are publically available and no etchical statement is necessary.

Thanks

This work is supported by Middle East Technical University Research Project (No: 11401).

References

1. [1] S.S. Martin, A. Aday, Z.I. Almarzooq, C.A. Anderson, P. Arora, C.L. Avery et al., 2024 heart disease and stroke statistics: a report of US and global data from the American Heart Association, Circulation 149 (8), e347–e913, 2024.
2. [2] M. Kayikcioğlu and A. Oto, Control and management of cardiovascular disease in Turkey, Circulation 141 (1), 7–9, 2020.
3. [3] N.I. Fisher, Statistical Analysis of Circular Data, Cambridge University Press, 1995.
4. [4] A. Dravid, W.S. Sung, J. Song, A. Dubey, and B. Eftekhar, Subarachnoid haemorrhage incidence pattern analysis with circular statistics, Emerg. Med. Int. 2024 (1), 6631990, 2024.
5. [5] L. Wang, T. Bi, J. Hao, and T.H. Zhou, Heart diseases recognition model based on HRV feature extraction over 12-lead ECG signals, Sensors 24 (16), 5296, 2024.
6. [6] A. Gour, M. Gupta, R. Wadhvani, and S. Shukla, ECG based heart disease classification: advancement and review of techniques, Procedia Comput. Sci. 235, 1634–1648, 2024.
7. [7] V. Gupta, M. Mittal, V. Mittal, A.K. Sharma, and N.K. Saxena, A novel feature extraction-based ECG signal analysis, J. Inst. Eng. India Ser. B 102 (5), 903–913, 2021.
8. [8] G. Verardo, M. Boman, S. Bruchfeld, M. Chiesa, S. Koch, G.Q. Maguire Jr, and D. Kostic, FMM-Head: Enhancing autoencoder-based ECG anomaly detection with prior knowledge, arXiv:2310.05848, 2023.

9. [9] A.K. Singh and S. Krishnan, ECG signal feature extraction trends in methods and applications, Biomed. Eng. Online 22 (1), 22, 2023.
10. [10] S. Kuila, N. Dhanda, and S. Joardar, ECG signal classification and arrhythmia detection using ELM-RNN, Multimed. Tools Appl. 81 (18), 25233–25249, 2022.
11. [11] T. Anbalagan, M.K. Nath, D. Vijayalakshmi, and A. Anbalagan, Analysis of various techniques for ECG signal in healthcare, past, present, and future, Biomed. Eng. Adv. 6, 100089, 2023.
12. [12] J.M. Wiersema, A.E. Kamphuis, J.H. Rohling, L. Kervezee, A.A. Akintola, and S.W. Jansen et al., The association between continuous ambulatory heart rate, heart rate variability, and 24-h rhythms of heart rate with familial longevity and aging, Aging (Albany NY) 14 (18), 7223–7234, 2022.
13. [13] J.-D. Janßen and T. Schanze, Analysis and classification of ECG-waves and rhythms using circular statistics and vector strength, Curr. Dir. Biomed. Eng. 3 (2), 91–94, 2017.
14. [14] H. Masuda, S. Okada, and N. Shiozawa, Circadian rhythm estimation using electrocardiogram, in: Proc. IEEE Global Conf. Life Sciences and Technologies (LifeTech), 1–5, 2020.
15. [15] M.M. Massin, K. Maeyns, N. Withofs, F. Ravet, and P. Gérard, Circadian rhythm of heart rate and heart rate variability, Arch. Dis. Child. 83 (2), 179–182, 2000.
16. [16] S.C. Malpas and G.L. Purdie, Circadian variation of heart rate variability, Cardiovasc. Res. 24 (3), 210–213, 1990.
17. [17] M. Karlsson, M.Wallman, P.G. Platonov, S.R. Ulimoen, and F. Sandberg, ECG-based assessment of circadian variation in AV-nodal conduction during AF—Influence of rate control drugs, Front. Physiol. 13, 976526, 2022.
18. [18] S. Chen, S. Wang, and R. Sinnott, Parametric canonical correlation analysis, in: Proc. IEEE Int. Conf. Cloud Computing Technology and Science (CloudCom), 2019.
19. [19] K. Polat and S. Güneş, Detection of ECG arrhythmia using a differential expert system approach based on principal component analysis and least square support vector machine, Appl. Math. Comput. 186 (1), 898–906, 2007.
20. [20] F. Petitjean et al., Dynamic time warping averaging of time series allows faster and more accurate classification, in: Proc. IEEE Int. Conf. Data Mining, 2014.
21. [21] D.M. Pirouz, An overview of partial least squares, SSRN 1631359, 2006.
22. [22] D.S. Hickey, J.L. Kirkland, S.B. Lucaz, and M. Lye, Analysis of circadian rhythms by fitting a least squares sine curve, Comput. Biol. Med. 14 (2), 217–223, 1984.
23. [23] M. Alkhodari, H.F. Jelinek, N. Werghi, L.J. Hadjileontiadis, and A.H. Khandoker, Estimating left ventricle ejection fraction levels using circadian heart rate variability features and support vector regression models, IEEE J. Biomed. Health Inform. 25 (3), 746–754, 2020.
24. [24] Y. Luan and H. Li, Model-based methods for identifying periodically expressed genes based on time course microarray gene expression data, Bioinformatics 20 (3), 332–339, 2004.
25. [25] E.A.R. Hussein, H.M. Abdulridha, and A.N. Hassan, Feature extraction of ECG signal using cubic spline technique, Eur. J. Sci. Res. 128 (1), 97–107, 2015.
26. [26] A. Mishra, S. Bhusnur, S.K. Mishra, and P. Singh, Comparative analysis of parametric B-spline and Hermite cubic spline-based methods for accurate ECG signal modeling, J. Electrocardiol. 86, 153783, 2024.
27. [27] G. Soto and S. Torres, Feature extraction based on circular summary statistics in ECG signal classification, in: Proc. Int. Conf. Chilean Computer Science Society, 2009.
28. [28] A.K. Singh and S. Krishnan, ECG signal feature extraction trends in methods and applications, Biomed. Eng. Online 22 (1), 22, 2023.
29. [29] C.M. Akujuobi, Wavelets and Wavelet Transform Systems and Their Applications, Springer, 2022.
30. [30] P.S. Addison, Wavelet transforms and the ECG: a review, Physiol. Meas. 26 (5), R155–R199, 2005.
31. [31] E.F. Glynn, J. Chen, and A.R. Mushegian, Detecting periodic patterns in unevenly spaced gene expression time series using Lomb–Scargle periodograms, Bioinformatics 22 (3), 310–316, 2006.
32. [32] T. Ruf, The Lomb–Scargle periodogram in biological rhythm research: analysis of incomplete and unequally spaced time-series, Biol. Rhythm Res. 30 (2), 178–201, 1999.
33. [33] K. Liang, X. Wang, and T.-H. Li, Robust discovery of periodically expressed genes using the Laplace periodogram, BMC Bioinform. 10, 1, 2009.
34. [34] T.-H. Li, Laplace periodogram for time series analysis, J. Am. Stat. Assoc. 103 (482), 757–768, 2008.
35. [35] P. Berens, CircStat: a MATLAB toolbox for circular statistics, J. Stat. Softw. 31, 1, 2009.
36. [36] G.D. Ruxton, Testing for departure from uniformity and estimating mean direction for circular data, Biol. Lett. 13 (1), 20160756, 2017.
37. [37] R. Jahangir, M. Raiyan et al., ECG-based heart arrhythmia classification using feature engineering and a hybrid stacked machine learning, BMC Cardiovasc. Disord. 25 (1), 260, 2025.
38. [38] S.R. Jammalamadaka and A. Sengupta, Topics in Circular Statistics, World Scientific, 2001.
39. [39] E.A. Mahmood, S. Rana, H. Midi, and A.G. Hussin, Detection of outliers in univariate circular data using robust circular distance, J. Mod. Appl. Stat. Methods 16 (2), 22– 38, 2017.
40. [40] B. Rattanawong, N. Papukdee, and W. Srisodaphol, Detection of outliers in univariate circular data using new cut-off points for the circular distance, Philipp. J. Sci. 152 (5), 2019–2026, 2023.
41. [41] V. Tuzcu and S. Nas, Dynamic time warping as a novel tool in pattern recognition of ECG changes in heart rhythm disturbances, in: Proc. IEEE Int. Conf. Systems, Man and Cybernetics, 2005.
42. [42] R.J. Martis, U.R. Acharya, and L.C. Min, ECG beat classification using PCA, LDA, ICA and discrete wavelet transform, Biomed. Signal Process. Control 8 (5), 437–448, 2013.
43. [43] D. Weenink, Canonical correlation analysis, in: Proc. Institute of Phonetic Sciences, Univ. Amsterdam, 2003.
44. [44] A.L. Goldberger, L.A. Amaral, L. Glass, J.M. Hausdorff, P.C. Ivanov, R.G. Mark, H.E. Stanley et al., PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals, Circulation 101 (23), e215– e220, 2000.
45. [45] G.B. Moody and R.G. Mark, The impact of the MIT-BIH arrhythmia database, IEEE Eng. Med. Biol. Mag. 20 (3), 45–50, 2001.
46. [46] Ž. Vujović, Classification model evaluation metrics, Int. J. Adv. Comput. Sci. Appl. 12 (6), 599–606, 2021.