Classification of heart arrhythmia by digital image processing and machine learning
Resumo
O exame de eletrocardiograma (ECG) pode ser utilizado de forma confiável como medida para monitorar a funcionalidade do sistema cardiovascular. Embora existam muitas semelhanças entre diferentes condições de ECG, o foco da maioria dos estudos tem sido classificar um conjunto de sinais de banco de dados conhecido como conjuntos de dados PhysionNet MIT-BIH e PTB Diagnostics, em vez de classificar problemas em imagens reais. Neste artigo, propomos métodos para extrair recursos da imagem do exame e, em seguida, algoritmos como CNN, árvore de decisão, árvores extras e floresta aleatória são usados para a classificação dos exames, que é capaz de classificar com precisão de acordo com o padrão AAMI EC57. De acordo com os resultados, o método sugerido é capaz de fazer previsões com uma precisão média de 97,4 %.Referências
Acharya, U. R., Fujita, H., Lih, O. S., Hagiwara, Y., Tan, J. H., and Adam, M. (2017). Automated detection of arrhythmias using different intervals of tachycardia ecg segments with convolutional neural network. Information Sciences, 405:81–90.
Al-Ani, M. (2018). Ecg waveform classification based on p-qrs-t wave recognition.
Benner, J. P., Borloz, M. P., Adams, M., and Brady, W. J. (2007). Impact of the 12-lead electrocardiogram on ED evaluation and management. Am J Emerg Med, 25(8):942–948.
Bunch, J. R. and Hopcroft, J. E. (1974). Triangular factorization and inversion by fast matrix multiplication. Mathematics of Computation, 28(125):231–236.
carvalho, I. C. (2004). Métodos de mineração de dados (data mining) como suporte à tomada de decisão.
Fairley, R. (2017). Ecg analysis: Where do we go wrong and how can we improve? Feldman, J. and Goldwasser, G. P. (2004). Eletrocardiograma: recomendações para a sua interpretação. Revista da SOCERJ, 17(4):251–256.
Ho, T. K. (1995). Random decision forests. In Proceedings of 3rd International Conference on Document Analysis and Recognition, volume 1, pages 278–282 vol.1.
Holmvang, L., Hasbak, P., Clemmensen, P., Wagner, G., and Grande, P. (1998). Differences between local investigator and core laboratory interpretation of the admission electrocardiogram in patients with unstable angina pectoris or non-q-wave myocardial infarction (a thrombin inhibition in myocardial ischemia [TRIM] substudy). Am J Cardiol, 82(1):54–60.
Ji, Y., Zhang, S., and Xiao, W. (2019). Electrocardiogram classification based on faster regions with convolutional neural network. Sensors (Basel), 19(11).
Jin, L. and Dong, J. (2018). Normal versus abnormal ecg classification by the aid of deep learning.
Kaw, A., Kalu, E., and Nguyen, D. (2018). Numerical methods with applications: chapter 04.06 gaussian elimination.
Massel, D., Dawdy, J. A., and Melendez, L. J. (2000). Strict reliance on a computer algorithm or measurable st segment criteria may lead to errors in thrombolytic therapy eligibility. American Heart Journal, 140(2):221–226.
Moody, G. and Mark, R. (2001). The impact of the mit-bih arrhythmia database. IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine e Biology Society, 20:45–50.
Myerburg, R. J., Chaitman, B. R., Ewy, G. A., and Lauer, M. S. (2008). Task force 2: Training in electrocardiography, ambulatory electrocardiography, and exercise testing. Journal of the American College of Cardiology, 51(3):348–354.
Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9(1):62–66.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830.
Podgorelec, V., Kokol, P., Stiglic, B., and Rozman, I. (2002). Decision trees: An overview and their use in medicine. Journal of Medical Systems, 26(5):445–463.
Ramos, A. and Sousa, B. S. (2007). Eletrocardiograma: princípios, conceitos e aplicações. centro de estudos de fisiologia do exercício.
Reis, B. F., Teixeira, J. M., Teichrieb, V., and Kelner, J. (2008). Perspective correction implementation for embedded (maker-based) augmented reality. universidade federal de pernambuco, centro de informática. Workshop de Realidade Virtual e Aumentada, Bauru.
Ribeiro, A. (1991). Sistema para simulação de ecg/arritmias cardíacas para ensino e treinamento de pessoal.
Salerno, S. M., Alguire, P. C., and Waxman, H. S. (2003). Competency in interpretation of 12-lead electrocardiograms: a summary and appraisal of published evidence. Ann Intern Med, 138(9):751–760.
Schwartzman, A., Gavrilov, Y., and Adler, R. J. (2011). MULTIPLE TESTING OF LOCAL MAXIMA FOR DETECTION OF PEAKS IN 1D. Ann Stat, 39(6):3290–3319.
Suzuki, S. and be, K. (1985). Topological structural analysis of digitized binary images by border following. Computer Vision, Graphics, and Image Processing, 30(1):32–46.
WHO (2017). Cardiovascular diseases (cvds).
Xavier, S. and Reshmi, R. (2016). Automatic detection and recognition of tet in traffic sign boards based on word recognizer.
Zhou, Q., Lan, W., Zhou, Y., and Mo, G. (2020). Effectiveness evaluation of anti-bird devices based on random forest algorithm. In 2020 7th International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS), pages 743–748.
Al-Ani, M. (2018). Ecg waveform classification based on p-qrs-t wave recognition.
Benner, J. P., Borloz, M. P., Adams, M., and Brady, W. J. (2007). Impact of the 12-lead electrocardiogram on ED evaluation and management. Am J Emerg Med, 25(8):942–948.
Bunch, J. R. and Hopcroft, J. E. (1974). Triangular factorization and inversion by fast matrix multiplication. Mathematics of Computation, 28(125):231–236.
carvalho, I. C. (2004). Métodos de mineração de dados (data mining) como suporte à tomada de decisão.
Fairley, R. (2017). Ecg analysis: Where do we go wrong and how can we improve? Feldman, J. and Goldwasser, G. P. (2004). Eletrocardiograma: recomendações para a sua interpretação. Revista da SOCERJ, 17(4):251–256.
Ho, T. K. (1995). Random decision forests. In Proceedings of 3rd International Conference on Document Analysis and Recognition, volume 1, pages 278–282 vol.1.
Holmvang, L., Hasbak, P., Clemmensen, P., Wagner, G., and Grande, P. (1998). Differences between local investigator and core laboratory interpretation of the admission electrocardiogram in patients with unstable angina pectoris or non-q-wave myocardial infarction (a thrombin inhibition in myocardial ischemia [TRIM] substudy). Am J Cardiol, 82(1):54–60.
Ji, Y., Zhang, S., and Xiao, W. (2019). Electrocardiogram classification based on faster regions with convolutional neural network. Sensors (Basel), 19(11).
Jin, L. and Dong, J. (2018). Normal versus abnormal ecg classification by the aid of deep learning.
Kaw, A., Kalu, E., and Nguyen, D. (2018). Numerical methods with applications: chapter 04.06 gaussian elimination.
Massel, D., Dawdy, J. A., and Melendez, L. J. (2000). Strict reliance on a computer algorithm or measurable st segment criteria may lead to errors in thrombolytic therapy eligibility. American Heart Journal, 140(2):221–226.
Moody, G. and Mark, R. (2001). The impact of the mit-bih arrhythmia database. IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine e Biology Society, 20:45–50.
Myerburg, R. J., Chaitman, B. R., Ewy, G. A., and Lauer, M. S. (2008). Task force 2: Training in electrocardiography, ambulatory electrocardiography, and exercise testing. Journal of the American College of Cardiology, 51(3):348–354.
Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9(1):62–66.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830.
Podgorelec, V., Kokol, P., Stiglic, B., and Rozman, I. (2002). Decision trees: An overview and their use in medicine. Journal of Medical Systems, 26(5):445–463.
Ramos, A. and Sousa, B. S. (2007). Eletrocardiograma: princípios, conceitos e aplicações. centro de estudos de fisiologia do exercício.
Reis, B. F., Teixeira, J. M., Teichrieb, V., and Kelner, J. (2008). Perspective correction implementation for embedded (maker-based) augmented reality. universidade federal de pernambuco, centro de informática. Workshop de Realidade Virtual e Aumentada, Bauru.
Ribeiro, A. (1991). Sistema para simulação de ecg/arritmias cardíacas para ensino e treinamento de pessoal.
Salerno, S. M., Alguire, P. C., and Waxman, H. S. (2003). Competency in interpretation of 12-lead electrocardiograms: a summary and appraisal of published evidence. Ann Intern Med, 138(9):751–760.
Schwartzman, A., Gavrilov, Y., and Adler, R. J. (2011). MULTIPLE TESTING OF LOCAL MAXIMA FOR DETECTION OF PEAKS IN 1D. Ann Stat, 39(6):3290–3319.
Suzuki, S. and be, K. (1985). Topological structural analysis of digitized binary images by border following. Computer Vision, Graphics, and Image Processing, 30(1):32–46.
WHO (2017). Cardiovascular diseases (cvds).
Xavier, S. and Reshmi, R. (2016). Automatic detection and recognition of tet in traffic sign boards based on word recognizer.
Zhou, Q., Lan, W., Zhou, Y., and Mo, G. (2020). Effectiveness evaluation of anti-bird devices based on random forest algorithm. In 2020 7th International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS), pages 743–748.
Publicado
06/08/2023
Como Citar
OLIVEIRA, Gustavo Henrique de; FLORES, Franklin César.
Classification of heart arrhythmia by digital image processing and machine learning. In: SEMINÁRIO INTEGRADO DE SOFTWARE E HARDWARE (SEMISH), 50. , 2023, João Pessoa/PB.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2023
.
p. 167-178.
ISSN 2595-6205.
DOI: https://doi.org/10.5753/semish.2023.230225.
