Aprendizaje profundo para la evaluación del ritmo cardiaco: Evaluación de modelos CNN en datos de ECG
Barra lateral del artículo
Contenido principal del artículo
Resumen
El electrocardiograma (ECG) es una técnica para detectar problemas en el ritmo cardíaco y evaluar el sistema cardiovascular. Tradicionalmente, los médicos confiaban en observaciones manuales, pero esto tenía limitaciones en términos de precisión. En esta investigación, se utilizaron redes neuronales convolucionales para la identificación de arritmias cardiacas en pacientes. Se entrenaron tres modelos diferentes, usando arquitecturas: VGG16 y ResNet-50, así mismo una propuesta por los investigadores. Todos los modelos se entrenaron con el dataset (PhysioNet MIT-BIH), con la misma cantidad de datos y configuración. La evaluación de los modelos se realizó utilizando métricas: precisión, recall, F1Score y accuracy. El modelo VGG16 demostró ser el más efectivo, logrando una accuracy del 98,8%. Los resultados de la investigación pueden llegar a mejorar la detección de arritmias cardiacas, lo que podría llevar a diagnósticos más precisos y un mejor cuidado de la salud cardiovascular en pacientes.
Descargas
Detalles del artículo
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.
Todos los textos publicados en esta revista se distribuyen bajo una Licencia Creative Commons «Reconocimiento-No Comercial-Compartir igual» desde 2020.
Citas
L. Zhang, M. Karimzadeh, M. Welch, C. McIntosh y B. Wang, "Chapter 7 - Analytics methods and tools for integration of biomedical data in medicine," en Artificial Intelligence in Medicine, 2021, pp. 113-129. https://doi.org/10.1016/B978-0-12-821259-2.00007-7.
National Library of Medicine, "MedlinePlus," 10 de diciembre de 2020. [En línea]. Disponible en: https://medlineplus.gov/lab-tests/electrocardiogram/. [Último acceso: 24 de febrero de 2022].
J. Huang, B. Chen, B. Yao y W. He, "ECG Arrhythmia Classification Using STFT-Based Spectrogram and Convolutional Neural Network," IEEE Access, vol. 7, pp. 92871-92880, 2019. https://doi.org/10.1109/ACCESS.2019.2928017.
B. Pyakillya, N. Kazachenko y N. Mikhailovsky, "Deep Learning for ECG Classification," Journal of Physics: Conference Series, vol. 913, p. 012004, 2017. https://doi.org/10.1088/1742-6596/913/1/012004.
D. A. Revelo Luna, J. E. Mejía Manzano y J. A. Munoz Chaves, "Effect of Pre-processing of CT Images on the Performance of Deep Neural Networks Based Diagnosis of COVID-19," Journal of Scientific & Industrial Research, vol. 80, nº 11, pp. 992-1000, 2021. http://nopr.niscpr.res.in/handle/123456789/58523.
K. K. Verma, "Deep Learning Approach to Recognize COVID-19, SARS and Streptococcus," Journal of Scientific & Industrial Research, vol. 80, nº 01, pp. 51-59, 2021. http://nopr.niscpr.res.in/handle/123456789/55855.
P. Chazal, M. O'Dwyer y R. Reilly, "Automatic classification of heartbeats using ECG morphology and heartbeat interval features," IEEE Transactions on Biomedical Engineering, vol. 51, nº 7, pp. 1196-1206, 2004. https://doi.org/10.1109/TBME.2004.827359.
A. Lanatá, G. Valenza, C. Mancuso y E. Scilingo, "Robust multiple cardiac arrhythmia detection through bispectrum analysis," Expert Systems with Applications, vol. 38, nº 6, pp. 6798-6804, 2011. https://doi.org/10.1016/j.eswa.2010.12.066.
E. J. Luz, T. Nunes, V. H. de Albuquerque, J. Papa y D. Menotti, "ECG arrhythmia classification based on optimum-path forest," Expert Systems with Applications, vol. 40, nº 9, pp. 3561-3573, 2013. https://doi.org/10.1016/j.eswa.2012.12.063.
T. Dózsa and P. Kovács, "ECG Signal Compression Using Adaptive Hermite Functions," in ICT Innovations 2015, S. Loshkovska and S. Koceski, Eds. Cham: Springer International Publishing, 2016, pp. 245-254. https://doi.org/10.1007/978-3-319-25733-4_25.
M. Amon and F. Jager, "Electrocardiogram ST-Segment Morphology Delineation Method Using Orthogonal Transformations," PLOS ONE, vol. 11, no. 2, pp. 1-18, Feb. 2016. https://doi.org/10.1371/journal.pone.0148814.
H. Khorrami y M. Moavenian, "A comparative study of DWT, CWT and DCT transformations in ECG arrhythmias classification," Expert Systems with Applications, vol. 37, nº 8, pp. 5751-5757, 2010. https://doi.org/10.1016/j.eswa.2010.02.033.
M. H. Song, J. Lee, S. P. Cho, K. J. Lee y S. K. Yoo, "Support vector machine based arrhythmia classification using reduced features," INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS, vol. 3, nº 4, pp. 571-579, 2005. https://ir.ymlib.yonsei.ac.kr/handle/22282913/149913.
S. N. Yu y Y. H. Chen, "Electrocardiogram beat classification based on wavelet transformation and probabilistic neural network," Pattern Recognition Letters, vol. 28, nº 10, pp. 1142-1150, 2007. https://doi.org/10.1016/j.patrec.2007.01.017.
C. Ye, M. T. Coimbra y V. Kumar, "Arrhythmia detection and classification using morphological and dynamic features of ECG signals," Annual International Conference of the IEEE Engineering in Medicine and Biology, pp. 1918-1921, 2010. doi: 10.1109/IEMBS.2010.5627645.
T. Li y M. Zhou, "ECG Classification Using Wavelet Packet Entropy and Random Forests," Entropy, vol. 18, nº 8, 2016. https://doi.org/10.3390/e18080285.
S.-W. Lin, K.-C. Ying, S.-C. Chen y Z.-J. Lee, "Particle swarm optimization for parameter determination and feature selection of support vector machines," Expert Systems with Applications, vol. 32, nº 4, pp. 1817-1824, 2008. https://doi.org/10.1016/j.eswa.2007.08.088.
M. Moavenian y H. Khorrami, "A qualitative comparison of Artificial Neural Networks and Support Vector Machines in ECG arrhythmias classification," Expert Systems with Applications, vol. 37, nº 4, pp. 3088-3093, 2010. https://doi.org/10.1016/j.eswa.2009.09.021.
S.-N. Yu y K.-T. Chou, "Selection of significant independent components for ECG beat classification," Expert Systems with Applications, vol. 36, nº 2, pp. 2088-2096, 2009. https://doi.org/10.1016/j.eswa.2007.12.016.
M. Kachuee, S. Fazeli y M. Sarrafzadeh, "ECG Heartbeat Classification: A Deep Transferable Representation" IEEE International Conference on Healthcare Informatics, p. 2018 IEEE International Conference on Healthcare Informatics, 2018. https://doi.org/10.1109/ICHI.2018.00092.
M. Wiggins, A. Saad, B. Litt y G. Vachtsevanos, "Evolving a Bayesian classifier for ECG-based age classification in medical applications," Applied Soft Computing, vol. 8, nº 1, pp. 599-608, 2008. https://doi.org/10.1016/j.asoc.2007.03.009.
A. Goldberger, L. Amaral, L. Glass, J. Hausdorff, P. Ivanov, R. Mark, J. Mietus, G. Moody, C.-K. Peng y E. Stanley, "PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals," Circulation, vol. 101, nº 23, p. 215–220, 2000. https://doi.org/10.1161/01.CIR.101.23.e215.
G. Moody y R. Mark, "The Impact of the MIT-BIH Arrhythmia Database," IEEE engineering in medicine and biology, vol. 20, nº 3, pp. 45-50, 2001. https://doi.org/10.13026/C2F305.
J. Kojuri, R. Boostani, P. Dehghani, F. Nowroozipour y N. Saki, "Prediction of acute myocardial infarction with artificial neural networks in patients with nondiagnostic electrocardiogram," Journal of Cardiovascular Disease Research, vol. 6, nº 2, pp. 51-59, 2015. http://dx.doi.org/10.5530/jcdr.2015.2.2.
N. Safdarian, N. Jafarnia Dabanloo y G. Attarodi, "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, vol. 07, pp. 818-824, 2014. http://dx.doi.org/10.4236/jbise.2014.710081.
B. Liu, J. Liu, G. Wang, K. Huang, F. Li, Y. Zheng, Y. Luo y F. Zhou, "A novel electrocardiogram parameterization algorithm and its application in myocardial infarction detection," Computers in Biology and Medicine, vol. 61, pp. 178-184, 2015. https://doi.org/10.1016/j.compbiomed.2014.08.01.