Medidas de Entropia e Inteligência Artificial para a Detecção de Arritmias Cardíacas em Sinais de ECG

• André R. Coimbra UFG / IFG
• Ana Cristina S. Rebelo UFG
• Maria Ribeiro UFG / INESC TEC
• Antonio Oliveira-Jr UFG / Fraunhofer Portugal AICOS

DOI: https://doi.org/10.5753/sbcas.2026.20768

Resumo

A arritmia cardíaca é uma condição clínica frequente, caracterizada por alterações no ritmo cardíaco. Este trabalho investigou o uso de medidas de entropia extraídas de sinais de Eletrocardiograma (ECG) de curta duração para a detecção automática de arritmias utilizando Redes Neurais Artificiais (ANNs), em cenários de classificação binária e multiclasse. Foram avaliadas cinco medidas clássicas de entropia, individualmente e em pares, e a entropia de Microestados de Recorrência (RMEn). A combinação da Entropia Amostral (SampEn) com a baseada na Decomposição em Valores Singulares (SVDEn) apresentou desempenho equivalente ao da RMEn, superando-a em 4 dos 6 cenários de classificação binária e alcançando acurácia de 77,6% ± 2,1% na multiclasse.

Referências

Asgharzadeh-Bonab, A., Amirani, M. C., and Mehri, A. (2020). Spectral entropy and deep convolutional neural network for ecg beat classification. Biocybernetics and Biomedical Engineering, 40(2):691–700.

Bandt, C. and Pompe, B. (2002). Permutation entropy: a natural complexity measure for time series. Physical review letters, 88(17):174102.

Boaretto, B. R. R. et al. (2024). The use of entropy of recurrence microstates and artificial intelligence to detect cardiac arrhythmia in ecg records. Applied Mathematics and Computation, 475:128738.

Corso, G., Prado, T. L. d. L., Lima, G. Z. d. S., Kurths, J., and Lopes, S. R. (2018). Quantifying entropy using recurrence matrix microstates. Chaos: An Interdisciplinary Journal of Nonlinear Science, 28(8).

Henriques, T., Ribeiro, M., Teixeira, A., Castro, L., Antunes, L., and Costa-Santos, C. (2020). Nonlinear methods most applied to heart-rate time series: A review. Entropy, 22(3):309.

Inouye, T., Shinosaki, K., Sakamoto, H., Toi, S., Ukai, S., Iyama, A., Katsuda, Y., and Hirano, M. (1991). Quantification of eeg irregularity by use of the entropy of the power spectrum. Electroencephalography and Clinical Neurophysiology, 79(3):204–210.

Jiang, W. and Wang, J. (2024). Classification of ecg signals based on local fractal feature. Multimedia Tools and Applications, 83(18):54773–54789.

Kim, S. H., Lim, K. R., Seo, J.-H., Ryu, D. R., Lee, B.-K., Cho, B.-R., and Chun, K. J. (2022). Higher heart rate variability as a predictor of atrial fibrillation in patients with hypertension. Scientific Reports, 12(1):3702.

Lindstrom, M. et al. (2022). Global burden of cardiovascular diseases and risks collaboration, 1990–2021. Journal of the American College of Cardiology, 80(25):2372–2425.

Liu, C., Oster, J., Reinertsen, E., Li, Q., Zhao, L., Nemati, S., and Clifford, G. D. (2018). A comparison of entropy approaches for af discrimination. Physiological Measurement, 39(7):074002.

Mandal, S., Roy, A. H., and Mondal, P. (2025). Discrimination of life-threatening arrhythmias using self-adaptive vmd, rqa techniques and efficientnetv2-l classifier. Biomedical Signal Processing and Control, 110:108301.

Neha, Sardana, H., Kanwade, R., and Tewary, S. (2021). Arrhythmia detection and classification using ecg and ppg techniques: A review. Physical and Engineering Sciences in Medicine, 44(4):1027–1048.

Oliveira, R. F., Ferreira, A. A., Moreira, G. J. P., and Luz, E. J. S. (2022). Um Método Ensemble para Classificação de Arritmias: Uma Avaliação com Mais de 10 Mil Registros de Sinais de ECG. In Anais do Simpósio Brasileiro de Computação Aplicada à Saúde (SBCAS), pages 13–24. SBC.

Prado, T. L., Corso, G., Lima, G. Z. d. S., Budzinski, R. C., Boaretto, B. R. R., Ferrari, F. A. S., Macau, E. E. N., and Lopes, S. R. (2020). Maximum entropy principle in recurrence plot analysis on stochastic and chaotic systems. Chaos: An Interdisciplinary Journal of Nonlinear Science, 30(4).

Prystowsky, E. N., Klein, G. J., and Daubert, J. P. (2020). Cardiac Arrhythmias: Interpretation, Diagnosis and Treatment. McGraw Hill Professional.

Rahul, J. and Sharma, L. D. (2025). Advancements in ai for cardiac arrhythmia detection: A comprehensive overview. Computer Science Review, 56:100719.

Rathnayake, C., Chen, W., Ran, G., Zhang, H., Thilakarathne, B. S., Lai, D., et al. (2026). Multimodal ecg–ppg wearable technologies and modern fusion methods for atrial fibrillation detection: A review. IEEE Sensors Journal.

Richman, J. S. and Moorman, J. R. (2000). Physiological time-series analysis using approximate entropy and sample entropy. American Journal of Physiology - Heart and Circulatory Physiology, 278(6):H2039–H2049.

Schnabel, R. B. et al. (2023). Early diagnosis and better rhythm management to improve outcomes in patients with atrial fibrillation: the 8th afnet/ehra consensus conference. Europace, 25(1):6–27.

Shannon, C. E. (1948). A mathematical theory of communication. The Bell System Technical Journal, 27(3):379–423.

Śmigiel, S., Pałczyński, K., and Ledziński, D. (2021). Ecg signal classification using deep learning techniques based on the ptb-xl dataset. Entropy, 23:1121.

Sridhar, A. R. et al. (2024). State of the art of mobile health technologies use in clinical arrhythmia care. Communications Medicine, 4(1):218.

Sridhar, C., Lih, O. S., Jahmunah, V., Koh, J. E., Ciaccio, E. J., San, T. R., Arunkumar, N., Kadry, S., and Rajendra Acharya, U. (2021). Accurate detection of myocardial infarction using non linear features with ecg signals. Journal of Ambient Intelligence and Humanized Computing, 12(3):3227–3244.

Zheng, J. et al. (2020). A 12-lead electrocardiogram database for arrhythmia research covering more than 10,000 patients. Scientific Data, 7(1):48.