logo

Classification of cardiac arrhythmias using convolutional neural networks in ECG samples

10.24050/reia.v21i41.1719
Published 2024-01-01
Articles

Abstract

The electrocardiogram (ECG) is an essential tool in the diagnosis of cardiovascular disease, providing valuable information about heart rhythm and function. Traditionally, physicians relied on manually identified heuristic features to detect ECG abnormalities. However, this methodology had limitations in terms of accuracy and reliability. With the aim of improving accuracy in the identification of cardiac arrhythmias, this research focused on the development of models based on convolutional neural networks. Two data sets were used: the PhysioNet MIT-BIH dataset, widely used in the scientific community, and data acquired by the Bio-Tek BP Pump NIBP arrhythmia simulator. Five models were trained with different architectures, including conventional models such as (VGG16, ResNet-50 and AlexNet), as well as two architectures proposed by the authors. All models were trained with the same number of samples and hyperparameter settings. Performance evaluation was performed using common metrics such as precision, recall, F1-score and accuracy. The results showed that the VGG16 architecture was the most effective in classifying cardiac arrhythmias, achieving an accuracy of 98.8% on the MIT-BIH dataset. Furthermore, when evaluating test data from the Bio-Tek BP Pump NIBP simulator, the customize-2 model demonstrated the best performance with an accuracy of 96.3%. These results are promising, as they demonstrate the potential of convolutional neural networks to improve accuracy in the diagnosis of cardiac arrhythmias. The models developed in this research could be a useful tool for clinicians in the early detection and appropriate treatment of these cardiovascular conditions.

Keywords

Categories

Authors

  • Victor manuel astudillo Delgado

    Corporación Universitaria Comfacauca - Unicomfacauca

  • David Revelo Luna

    Corporación Universitaria Comfacauca - Unicomfacauca

  • Javier Andres Muñoz Chaves

    Corporación Universitaria Comfacauca - Unicomfacauca

References

Chazal, P.; O'Dwyer, M. and Reilly, R. (2004). Automatic classification of heartbeats using ECG morphology and heartbeat interval features. IEEE Transactions on Biomedical Engineering, 51(7), 1196-1206. doi:10.1109/TBME.2004.827359

Goldberger, A.L; Amaral, L.A.; Glass, L; Hausdorff, J.M.; Ivanov, P.C.; Mark, R.G.; Mietus, J.E.; Moody, G.B.; Peng, C.K and Stanley, H.E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation, 101(23), 215–220. doi:https://doi.org/10.1161/01.CIR.101.23.e215

Gómez Herrero, G.; Gotchev, A.; Christov, I. and Egiazarian, K. (2005). Feature extraction for heartbeat classification using independent component analysis and matching pursuits. Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005. Philadelphia, PA, USA 4, pp.725-728. doi:10.1109/ICASSP.2005.1416111

Huang, J.; Chen, B.; Yao, B. and He, W. (2019). ECG Arrhythmia Classification Using STFT-Based Spectrogram and Convolutional Neural Network. IEEE Access, 7, 92871-92880. doi:https://doi.org/10.1109/ACCESS.2019.2928017

Kachuee, M.; Fazeli, S., and Sarrafzadeh, M. (2018). ECG Heartbeat Classification: A Deep Transferable Representation. IEEE International Conference on Healthcare Informatics, 2018 IEEE International Conference on Healthcare Informatics. (ICHI). New York City, NY, USA pp. 443-444 doi:10.1109/ICHI.2018.00092

Khorrami, H. and Moavenian, M. (2010). A comparative study of DWT, CWT and DCT transformations in ECG arrhythmias classification. Expert Systems with Applications, 37(8), 5751-5757. doi:https://doi.org/10.1016/j.eswa.2010.02.033

Kojuri, J.; Boostani, R.; Dehghani, P.; Nowroozipour, F. and Saki, N. (2015). Prediction of acute myocardial infarction with artificial neural networks in patients with nondiagnostic electrocardiogram. Journal of Cardiovascular Disease Research, 6(2), 51-59. doi:10.5530/jcdr.2015.2.2

Laguna, P.; Jane, R.; Olmos, S.; Thakor, N.; Rix, H. and Caminal, P. (1996). Adaptive estimation of QRS complex wave features of ECG signal by the Hermite model. Medical & biological engineering & computing, 34(1), 58-88. doi:https://doi.org/10.1007/BF02637023

Lanatá, A.; Valenza, G.; Mancuso, C. and Scilingo, E. (2011). Robust multiple cardiac arrhythmia detection through bispectrum analysis. Expert Systems with Applications, 38(6), 6798-6804. doi:https://doi.org/10.1016/j.eswa.2010.12.066

Li, T. and Zhou, M. (2016). ECG Classification UsingWavelet Packet Entropy and Random Forests. Entropy, 18(8), 285. doi:10.3390/e18080285

Lin, S.W.; Ying, K.C.; Chen, S.C. and Lee, Z. J. (2008). Particle swarm optimization for parameter determination and feature selection of support vector machines. Expert Systems with Applications, 32(4), 1817-1824. doi:https://doi.org/10.1016/j.eswa.2007.08.088

Liu, B.; Liu, J.; Wang, G.; Huang, K.; Li, F.; Zheng, Y.; Luo, Y. and Zhou, F. (2015). A novel electrocardiogram parameterization algorithm and its application in myocardial infarction detection. Computers in Biology and Medicine, 61, 178-184. doi:https://doi.org/10.1016/j.compbiomed.2014.08.010

Luz, E.; Nunes, T.; de Albuquerque, V.; Papa, J. and Menotti, D. (2013). ECG arrhythmia classification based on optimum-path forest. Expert Systems with Applications, 40(9), 3561-3573. doi:https://doi.org/10.1016/j.eswa.2012.12.063

Moavenian, M. and Khorrami, H. (2010). A qualitative comparison of Artificial Neural Networks and Support Vector Machines in ECG arrhythmias classification. Expert Systems with Applications, 37(4), 3088-3093. doi:https://doi.org/10.1016/j.eswa.2009.09.021

Moody, G. and Mark, R. (2001). The Impact of the MIT-BIH Arrhythmia Database. IEEE engineering in medicine and biology, 20(3), 45-50. doi:https://doi.org/10.13026/C2F305

Moody, G. and Mark, R. (1989). QRS morphology representation and noise estimation using the Karhunen-Loeve transform. Proceedings. Computers in Cardiology, 269-272. doi:10.1109/CIC.1989.130540

National Library of Medicine. (10 de 12 de 2020). MedlinePlus. Recuperado el 24 de 02 de 2022, de MedlinePlus: https://medlineplus.gov/lab-tests/electrocardiogram/

Pal, S. (2019). ECG Monitoring: Present Status and Future Trend. En Encyclopedia of Biomedical Engineering. University of Calcutta, Kolkata, India. pp. 363-379. doi:https://doi.org/10.1016/B978-0-12-801238-3.10892-X

Pyakillya, B.; Kazachenko, N. and Mikhailovsky, N. (2017). Deep Learning for {ECG} Classification. Journal of Physics: Conference Series, IOP Publishing. 913, 012004. doi:https://doi.org/10.1088/1742-6596/913/1/012004

Revelo Luna, D. A.; Mejía Manzano, J. E. and Munoz Chaves, J. A. (2021). Effect of Pre-processing of CT Images on the Performance of Deep Neural Networks Based Diagnosis of COVID-19. Journal of Scientific & Industrial Research, 80(11), 992-1000

Safdarian, N.; Jafarnia D.N., and Attarodi, G. (2014). A New Pattern Recognition Method for Detection and Localization of Myocardial Infarction Using T-Wave Integral and Total Integral as Extracted Features from One Cycle of ECG Signal. Journal of Biomedical Science and Engineering, 07, 818-824. doi:10.4236/jbise.2014.710081

Song, M.H.; Lee, J.; Cho, S.P.; Lee, K.J. and Yoo, S.K. (2005). Support vector machine based arrhythmia classification using reduced features. International journal of control automation and systems, 3(4), 571-579. doi:http://dx.doi.org/OAK-2005-06773

Verma, K. K. (2021). Deep Learning Approach to Recognize COVID-19, SARS and Streptococcus. Journal of Scientific & Industrial Research, 80(01), 51-59.

Wiggins, M.; Saad, A.; Litt, B. and Vachtsevanos, G. (2008). Evolving a Bayesian classifier for ECG-based age classification in medical applications. Applied Soft Computing, 8(1), 599-608. doi:https://doi.org/10.1016/j.asoc.2007.03.009

World Heath Organization. (11 de 06 de 2021). World Heath Organization. Obtenido de https://www.who.int/en/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds)

Ye, C.; Coimbra, M. T.; and Kumar, V. (2010). Arrhythmia detection and classification using morphological and dynamic features of ECG signals. Annual International Conference of the IEEE Engineering in Medicine and Biology 2010, Buenos Aires, Argentina, pp.1918-1921. doi:10.1109/IEMBS.2010.5627645

Yu, S. N. and Chen, Y. H. (2007). Electrocardiogram beat classification based on wavelet transformation and probabilistic neural network. Pattern Recognition Letters, 28(10), 1142-1150. doi:https://doi.org/10.1016/j.patrec.2007.01.017

Yu, S. N. and Chou, K.T. (2009). Selection of significant independent components for ECG beat classification. Expert Systems with Applications, 36(2), 2088-2096. doi:https://doi.org/10.1016/j.eswa.2007.12.016

Zhang, L.; Karimzadeh, M.; Welch, M.; McIntosh, C. and Wang, B. (2021). Chapter 7 - Analytics methods and tools for integration of biomedical data in medicine. Xing, L.; Giger, M.L., and Min, J.K. Artificial Intelligence in Medicine. Academic Press, pp. 113-129. doi:https://doi.org/10.1016/B978-0-12-821259-2.00007-7

Statistics

Abstract
0
PDF accesses
0

Dimensions

PlumX

Downloads

Download data is not yet available.