Assessing the robustness of information theory descriptors in cardiac signal classification
DOI:
https://doi.org/10.24054/rcta.v2i48.4593Keywords:
Shannon entropy, complexity analysis, ECG signal processing, mutual information, least information lost, information theoryAbstract
Automated classification of electrocardiographic (ECG) signals can be a useful tool for identifying cardiovascular abnormalities. However, the nonlinear and nonstationary nature of these signals may limit the use of conventional parametric methods. This study evaluates Information Theory (IT) descriptors as a nonparametric alternative for characterizing heartbeat segments. A total of 14,552 segments from the ECG Heartbeat Categorization Dataset were analyzed, each represented by 187 temporal positions, and the interdependence between diagnostic categories and amplitudes was quantified using entropy and mutual information. An IT based clustering procedure was also implemented. For the abnormal category, the confusion matrix showed a sensitivity of 94.38% and a specificity of 70.53%; balanced accuracy was 82.46%. Cluster purity was close to 0.877. The results indicate partial separation between normal and abnormal segments and should be interpreted considering class imbalance, preprocessing, and the effect of zero-padding.
Downloads
References
K. Balasubramanian, S. Rajendran, and S. Pati, “Complexity Measures in Biomedical Signal Analysis: A Clinically-Grounded Survey Across EEG, ECG, Intracranial Pressure, and Photoplethysmogram Modalities,” IEEE Access, vol. 13, pp. 155285–155304, 2025. doi: 10.1109/access.2025.3603848
L. Acosta and M. Pacheco, “Entropy and Statistical Complexity in Bioelectrical Signals: A Literature Review,” Signals, vol. 6, no. 1, p. 7, 2025. doi: 10.3390/signals6010007
J. Li, G. Feng, C. Ling, X. Ren, X. Liu, S. Zhang, L. Wang, Y. Chen, X. Zeng, and R. Chen, “A Resource-Efficient Multi-Entropy Fusion Method and Its Application for EEG-Based Emotion Recognition,” Entropy, vol. 27, no. 1, p. 96, 2025. doi: 10.3390/e27010096
C. Wu, B. Yao, X. Zhang, T. Li, J. Wang, and J. Pu, “The Application of Entropy in Motor Imagery Paradigms of Brain–Computer Interfaces,” Brain Sci., vol. 15, no. 2, p. 168, 2025. doi: 10.3390/brainsci15020168
D. Platakis and G. Manis, “Review of Recent (2015–2024) Popular Entropy Definitions Applied to Physiological Signals,” Entropy, vol. 27, no. 9, p. 983, 2025. doi: 10.3390/e27090983
L. A. Luengas and L. F. Wanumen Silva, “Modelos computacionales en la posturografía,” Tecnura, vol. 26, no. 73, pp. 30–48, 2022. doi: 10.14483/22487638.18060.
Zandbagleh, S. Sanei, L. Penalba-Sánchez, P. Rodrigues, M. Crook-Rumsey, and H. Azami, “Intra- and Inter-Regional Complexity in Multi-Channel Awake EEG Through Multivariate Multiscale Dispersion Entropy for Assessing Sleep Quality and Aging,” Biosensors, vol. 15, no. 4, p. 240, 2025. doi: 10.3390/bios15040240
L. Sparacino, Y. Antonacci, G. Mijatovic, and L. Faes, “Measuring hierarchically-organized interactions in dynamic networks through spectral entropy rates: Theory, estimation, and illustrative application to physiological networks,” Neurocomputing, vol. 630, p. 129675, 2025. doi: 10.1016/j.neucom.2025.129675
D. Sengupta, P. Gupta, and A. Biswas, “An efficient similarity metric for 3D medical image registration,” Multimedia Tools Appl., vol. 83, pp. 87987–88017, 2024. doi: 10.1007/s11042-024-18710-1
M. Zbili and S. Rama, “A Quick and Easy Way to Estimate Entropy and Mutual Information for Neuroscience,” Front. Neuroinform., vol. 15, p. 596443, 2021. doi: 10.3389/fninf.2021.596443
S. Uda, “Application of information theory in systems biology,” Biophys. Rev., vol. 12, pp. 377–384, 2020. doi: 10.1007/s12551-020-00665-w
N. Amer and S. Belhaouari, “EEG Signal Processing for Medical Diagnosis, Healthcare, and Monitoring,” IEEE Access, vol. 11, pp. 143116–143142, 2023. doi: 10.1109/access.2023.3341419
T. Wang, W. Jia, F. Li, X. Liu, X. Zhang, and F. Hu, “Multi-dimensional feature extraction of EEG signal and its application in stroke classification,” Sci. Rep., vol. 15, 2025. doi: 10.1038/s41598-025-04756-0
F. Von Wegner, M. Wiemers, G. Hermann, I. Tödt, E. Tagliazucchi, and H. Laufs, “Complexity Measures for EEG Microstate Sequences: Concepts and Algorithms,” Brain Topogr., vol. 37, pp. 296–311, 2023. doi: 10.1007/s10548-023-01006-2
Z. Zhang, “Research on Mutual Information Analysis in EEG Based on Different Entropy Measures,” in Proc. IEEE 5th Int. Conf. Information Systems and Computer Aided Education (ICISCAE), 2022, pp. 548–553. doi: 10.1109/iciscae55891.2022.9927610.
Asgharzadeh-Bonab, M. Amirani, and A. Mehri, “Spectral entropy and deep convolutional neural network for ECG beat classification,” Biocybern. Biomed. Eng., vol. 40, pp. 691–700, 2020. doi: 10.1016/j.bbe.2020.02.004
T. Li and M. Zhou, “ECG Classification Using Wavelet Packet Entropy and Random Forests,” Entropy, vol. 18, no. 8, p. 285, 2016. doi: 10.3390/e18080285
H. Wu, “Multiscale entropy with electrocardiograph, electromyography, electroencephalography, and photoplethysmography signals,” Biomed. Signal Process. Control, vol. 93, p. 106124, 2024. doi: 10.1016/j.bspc.2024.106124
M. Coq, A. Rey, O. Rosso, R. Armentano, and W. Legnani, “Detection of cardiac arrhythmia patterns in ECG through H × C plane,” Chaos, vol. 32, no. 12, p. 123118, 2022. doi: 10.1063/5.0118717
S. Aulia and S. Hadiyoso, “Abnormal ECG Classification using Empirical Mode Decomposition and Entropy,” Jurnal Rekayasa Elektrika, vol. 17, no. 3, 2021. doi: 10.17529/jre.v17i3.22070
L. Xie, Z. Li, Y. Zhou, Y. He, and J. Zhu, “Computational Diagnostic Techniques for Electrocardiogram Signal Analysis,” Sensors, vol. 20, no. 21, p. 6318, 2020. doi: 10.3390/s20216318
E. Ramírez, S. Ruipérez-Campillo, R. Casado-Arroyo, J. Merino, J. Vogt, F. Castells, and J. Millet, “The art of selecting the ECG input in neural networks to classify heart diseases,” Front. Physiol., vol. 15, 2024. doi: 10.3389/fphys.2024.1452829
J. Sahores, V. Bank, M. Meijome, I. Ziccardi, and W. Legnani, “Study of Information Flow Among ECG Leads,” in IEEE Biennial Congress of Argentina (ARGENCON), 2024, pp. 1–8. doi: 10.1109/argencon62399.2024.10735814
B. Andayeshgar, F. Abdali-Mohammadi, M. Sepahvand, A. Almasi, and N. Salari, “Arrhythmia detection by the graph convolution network and a proposed structure for communication between cardiac leads,” BMC Med. Res. Methodol., vol. 24, 2024. doi: 10.1186/s12874-024-02223-4
H. Zhang, Z. Bian, X. Guo, X. Li, S. Yin, and D. Cui, “Measuring phase-amplitude coupling using dispersion fuzzy mutual information,” Comput. Methods Programs Biomed., vol. 272, p. 109075, 2025. doi: 10.1016/j.cmpb.2025.109075
L. A. Luengas, “Modelo de alineación estática para prótesis transtibiales”, PhD Thesis, Facultad de Ingeniería, Pontificia Universidad Javeriana, 2016. https://repository.javeriana.edu.co/items/4297eb56-d54f-401c-bb6c-8cb1b7c029a1
M. Kachuee, S. Fazeli, and M. Sarrafzadeh, “ECG Heartbeat Classification: A Deep Transferable Representation,” 2018 IEEE International Conference on Healthcare Informatics (ICHI), New York, NY, USA, 2018, pp. 443–444. doi: 10.1109/ICHI.2018.00092.
Pyle, D. (1999). Data preparation for data mining. In Morgan Kaufmann Publishers, Inc. Morgan Kaufmann Publishers, Inc. https://doi.org/10.1080/713827180
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Lely Adriana Luengas Contreras, Esperanza Camargo Casallas, Jonathan Roberto Torres Castillo
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
