Cardiac pathology classification with one-dimensional convolutional neural network
Resumo
Currently, technology is indispensable in the medical field and the use of artificial intelligence tools is responsible for accelerating several processes, facilitating data acquisition, and recognizing important patterns for patient diagnosis. Focusing on cardiac pathologies, the electrocardiogram is the most widely used examination to diagnose patients, and optimizing this process is extremely important. Therefore, the objective of this study is to develop a model capable of classifying cardiac pathologies using raw ECG signals. For this purpose, signals from the PTB-XL database, recorded in the 12-lead standard, were used to train a 1D convolutional neural network without pre-training. Various hyperparameters were adjusted to find the model that is the best suited to the application. The model was evaluated using a test dataset, achieving an accuracy of 84%. The model demonstrated satisfactory performance, which can lead to the possibility of improving the current diagnostic system by accelerating the examination reading process and helping healthcare professionals interpret the results.Referências
Ayadi, W., Elhamzi, W., Charfi, I., and Atri, M. (2021). Deep cnn for brain tumor classification. Neural processing letters, 53:671–700.
Bhanjaa, M. N. and Khampariya, P. (2023). Design and comparison of deep learning model for ecg classification using ptb-xl dataset.
Bian, Y., Chen, J., Chen, X., Yang, X., Chen, D. Z., and Wu, J. (2023). Identifying electrocardiogram abnormalities using a handcrafted-rule-enhanced neural network. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 20(4):2434–2444.
Eren, L., Ince, T., and Kiranyaz, S. (2019). A generic intelligent bearing fault diagnosis system using compact adaptive 1d cnn classifier. Journal of Signal Processing Systems, 91(2):179–189.
Fabian, P. (2011). Scikit-learn: Machine learning in python. Journal of machine learning research 12, page 2825.
Fawaz, H. I. (2020). Deep learning for time series classification. arXiv preprint arXiv:2010.00567.
Hall, J. E. (2021). Guyton & Hall. Tratado de fisiología médica. Elsevier Health Sciences.
Hasan, N. I. and Bhattacharjee, A. (2019). Deep learning approach to cardiovascular disease classification employing modified ecg signal from empirical mode decomposition. Biomedical signal processing and control, 52:128–140.
Kaplan, J. D., Evans, G., Foster, E., Lim, D., and Schiller, N. B. (1994). Evaluation of electrocardiographic criteria for right atrial enlargement by quantitative two-dimensional echocardiography. Journal of the American College of Cardiology, 23(3):747–752.
Khan, A., Sohail, A., Zahoora, U., and Qureshi, A. S. (2020). A survey of the recent architectures of deep convolutional neural networks. Artificial intelligence review, 53:5455–5516.
Kusuma, S. and Udayan, J. D. (2020). Analysis on deep learning methods for ecg based cardiovascular disease prediction. Scalable Computing: Practice and Experience, 21(1):127–136.
Lu, J., Tan, L., and Jiang, H. (2021). Review on convolutional neural network (cnn) applied to plant leaf disease classification. Agriculture, 11(8):707.
Maccagnan, G. C., Schmith, J., Santos, M., and de Figueiredo, R. M. (2023). Toolbox for vessel x-ray angiography images simulation. In Anais do XXIII Simpósio Brasileiro de Computação Aplicada à Saúde, pages 59–70. SBC.
Maione, C. et al. (2020). Balanceamento de dados com base em oversampling em dados transformados.
Nyholm, B. C., Ghouse, J., Lee, C. J.-Y., Rasmussen, P. V., Pietersen, A., Hansen, S. M., Torp-Pedersen, C., Køber, L., Haunsø, S., Olesen, M. S., et al. (2022). Fascicular heart blocks and risk of adverse cardiovascular outcomes: Results from a large primary care population. Heart Rhythm, 19(2):252–259.
Pastore, A. C., Samesima, N., Tobias, N. M. M. d. O., and Pereira Filho, H. G. (2016). Eletrocardiografia atual: curso do serviço de eletrocardiografia do incor. In Eletrocardiografia atual: curso do serviço de eletrocardiografia do InCor, pages 413–413.
Prati, R. C., Batista, G., Monard, M. C., do Trabalhador Sao-Carlense, A., and Postal, C.-C. (2003). Uma experiência no balanceamento artificial de conjuntos de dados para aprendizado com classes desbalanceadas utilizando análise roc. In Proc. of the Workshop on Advances & Trends in AI for Problem Solving, volume 1, pages 28–33.
Rose, L. and Kuhn, L. (2009). Ecg interpretation part 2: determination of bundle branch and fascicular blocks. Journal of Emergency Nursing, 35(2):123–126.
Śmigiel, S., Pałczyński, K., and Ledziński, D. (2021). Ecg signal classification using deep learning techniques based on the ptb-xl dataset. Entropy, 23(9):1121.
Taud, H. and Mas, J.-F. (2017). Multilayer perceptron (mlp). In Geomatic approaches for modeling land change scenarios, pages 451–455. Springer.
Thygesen, K., Alpert, J. S., Jaffe, A. S., Simoons, M. L., Chaitman, B. R., and White, H. D. (2012). Third universal definition of myocardial infarction. Circulation, 126(16):2020–2035.
Tortora, G. J. and Derrickson, B. H. (2018). Principles of anatomy and physiology. John wiley & sons.
Tsao, C. W., Josephson, M. E., Hauser, T. H., O’Halloran, T. D., Agarwal, A., Manning, W. J., and Yeon, S. B. (2008). Accuracy of electrocardiographic criteria for atrial enlargement: validation with cardiovascular magnetic resonance. Journal of Cardiovascular Magnetic Resonance, 10(1):7.
Wagner, P., Strodthoff, N., Bousseljot, R.-D., Kreiseler, D., Lunze, F. I., Samek, W., and Schaeffter, T. (2020). Ptb-xl, a large publicly available electrocardiography dataset. Scientific data, 7(1):1–15.
Wang, Z., Yan, W., and Oates, T. (2017). Time series classification from scratch with deep neural networks: A strong baseline. In 2017 International joint conference on neural networks (IJCNN), pages 1578–1585. IEEE.
Wilmore, J. H., Costill, D. L., and Kenney, W. L. (2004). Physiology of sport and exercise, volume 20. Human kinetics Champaign, IL.
Xie, C., McCullum, L., Johnson, A., Pollard, T., Gow, B., and Moody, B. (2022). Waveform database software package (wfdb) for python. PhysioNet.
Bhanjaa, M. N. and Khampariya, P. (2023). Design and comparison of deep learning model for ecg classification using ptb-xl dataset.
Bian, Y., Chen, J., Chen, X., Yang, X., Chen, D. Z., and Wu, J. (2023). Identifying electrocardiogram abnormalities using a handcrafted-rule-enhanced neural network. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 20(4):2434–2444.
Eren, L., Ince, T., and Kiranyaz, S. (2019). A generic intelligent bearing fault diagnosis system using compact adaptive 1d cnn classifier. Journal of Signal Processing Systems, 91(2):179–189.
Fabian, P. (2011). Scikit-learn: Machine learning in python. Journal of machine learning research 12, page 2825.
Fawaz, H. I. (2020). Deep learning for time series classification. arXiv preprint arXiv:2010.00567.
Hall, J. E. (2021). Guyton & Hall. Tratado de fisiología médica. Elsevier Health Sciences.
Hasan, N. I. and Bhattacharjee, A. (2019). Deep learning approach to cardiovascular disease classification employing modified ecg signal from empirical mode decomposition. Biomedical signal processing and control, 52:128–140.
Kaplan, J. D., Evans, G., Foster, E., Lim, D., and Schiller, N. B. (1994). Evaluation of electrocardiographic criteria for right atrial enlargement by quantitative two-dimensional echocardiography. Journal of the American College of Cardiology, 23(3):747–752.
Khan, A., Sohail, A., Zahoora, U., and Qureshi, A. S. (2020). A survey of the recent architectures of deep convolutional neural networks. Artificial intelligence review, 53:5455–5516.
Kusuma, S. and Udayan, J. D. (2020). Analysis on deep learning methods for ecg based cardiovascular disease prediction. Scalable Computing: Practice and Experience, 21(1):127–136.
Lu, J., Tan, L., and Jiang, H. (2021). Review on convolutional neural network (cnn) applied to plant leaf disease classification. Agriculture, 11(8):707.
Maccagnan, G. C., Schmith, J., Santos, M., and de Figueiredo, R. M. (2023). Toolbox for vessel x-ray angiography images simulation. In Anais do XXIII Simpósio Brasileiro de Computação Aplicada à Saúde, pages 59–70. SBC.
Maione, C. et al. (2020). Balanceamento de dados com base em oversampling em dados transformados.
Nyholm, B. C., Ghouse, J., Lee, C. J.-Y., Rasmussen, P. V., Pietersen, A., Hansen, S. M., Torp-Pedersen, C., Køber, L., Haunsø, S., Olesen, M. S., et al. (2022). Fascicular heart blocks and risk of adverse cardiovascular outcomes: Results from a large primary care population. Heart Rhythm, 19(2):252–259.
Pastore, A. C., Samesima, N., Tobias, N. M. M. d. O., and Pereira Filho, H. G. (2016). Eletrocardiografia atual: curso do serviço de eletrocardiografia do incor. In Eletrocardiografia atual: curso do serviço de eletrocardiografia do InCor, pages 413–413.
Prati, R. C., Batista, G., Monard, M. C., do Trabalhador Sao-Carlense, A., and Postal, C.-C. (2003). Uma experiência no balanceamento artificial de conjuntos de dados para aprendizado com classes desbalanceadas utilizando análise roc. In Proc. of the Workshop on Advances & Trends in AI for Problem Solving, volume 1, pages 28–33.
Rose, L. and Kuhn, L. (2009). Ecg interpretation part 2: determination of bundle branch and fascicular blocks. Journal of Emergency Nursing, 35(2):123–126.
Śmigiel, S., Pałczyński, K., and Ledziński, D. (2021). Ecg signal classification using deep learning techniques based on the ptb-xl dataset. Entropy, 23(9):1121.
Taud, H. and Mas, J.-F. (2017). Multilayer perceptron (mlp). In Geomatic approaches for modeling land change scenarios, pages 451–455. Springer.
Thygesen, K., Alpert, J. S., Jaffe, A. S., Simoons, M. L., Chaitman, B. R., and White, H. D. (2012). Third universal definition of myocardial infarction. Circulation, 126(16):2020–2035.
Tortora, G. J. and Derrickson, B. H. (2018). Principles of anatomy and physiology. John wiley & sons.
Tsao, C. W., Josephson, M. E., Hauser, T. H., O’Halloran, T. D., Agarwal, A., Manning, W. J., and Yeon, S. B. (2008). Accuracy of electrocardiographic criteria for atrial enlargement: validation with cardiovascular magnetic resonance. Journal of Cardiovascular Magnetic Resonance, 10(1):7.
Wagner, P., Strodthoff, N., Bousseljot, R.-D., Kreiseler, D., Lunze, F. I., Samek, W., and Schaeffter, T. (2020). Ptb-xl, a large publicly available electrocardiography dataset. Scientific data, 7(1):1–15.
Wang, Z., Yan, W., and Oates, T. (2017). Time series classification from scratch with deep neural networks: A strong baseline. In 2017 International joint conference on neural networks (IJCNN), pages 1578–1585. IEEE.
Wilmore, J. H., Costill, D. L., and Kenney, W. L. (2004). Physiology of sport and exercise, volume 20. Human kinetics Champaign, IL.
Xie, C., McCullum, L., Johnson, A., Pollard, T., Gow, B., and Moody, B. (2022). Waveform database software package (wfdb) for python. PhysioNet.
Publicado
09/06/2025
Como Citar
PASTORE, Thomas Sponchiado; RAMOS, Gabriel de Oliveira; SCHMITH, Jean.
Cardiac pathology classification with one-dimensional convolutional neural network. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 25. , 2025, Porto Alegre/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 248-259.
ISSN 2763-8952.
DOI: https://doi.org/10.5753/sbcas.2025.7008.
