Classificação de anomalias cardíacas a partir de exames de Eletrocardiograma
Abstract
This paper presents an algorithm to classify electrocardiograms according to some types of abnormalties in order to assist the expert in the triage of critical exams. The cardiac abnormalites are related to typical cardiac arrhythmias such as: right bundle branch block (R), left bundle branch block (L), premature ventricular (V), premature atrial (A) and paced beat (PB). A pre-processing step is performed through signal filtering and baseline line removal which is performed after the detection of heartbeat. A vector of 106 features based on the RR interval and the beat morphology were extracted from ECG signal. The size of the feature vector was reduced by the Principal Component Analysis (PCA) method. The reduced feature vector were employed as input of a Artificial Neural Network (ANN). The classification performance on a test set of 18 ECG recordings of 30 min each were an accuracy of 96.97%, sensitivity of 95.05%, specificity of 90.88%, positive predictive value of 95.11% and a negative predictive value of 92.7%. The results make the automatic triage a feasible strategy to prioritize abnormal ECGs to the cardiologist interpretation in a Telecardiology Service.
References
Andreão, R. V.; Sarti T.; Clestrini, J.; Schimidt, M. Q. (2013) “Automatic Triage of Electrocardiograms”, Global Telemedicine and eHealth Updates: Knowledge Resources, vol. 6, p. 143-147.
Arif, M.; Akram, M. U.; Afsar, F. A. (2009) “Arrhythmia Beat Classification using Pruned Fuzzy K-Nearest Neighbor Classifier”, International Conference of Soft Computing and Pattern Recognition.
Assis, P. O (2009) “que são Redes Neurais?”, http://www.tecmundo.com.br/programacao/2754-o-que-sao-redes-neurais-.htm, fevereiro de 2015.
Chazal, P. D.; O’Dwyer, M.; Reilly, R. B. (2004) “Automatic Classification of Heartbeats Using ECG Morphology and Heartbeat Interval Features” IEEE Transactions on Biomedical Engineering, vol. 51, no. 7, p. 1196-1206.
Chazal, P.D.; Reilly, R. (2006) “A patient-adapting heartbeat classifier using ECG morphology and heartbeat interval features”, IEEE Trans Biomed Engineering, vol. 53, p. 2535-2543.
Christov, I.; Gómez-Herrero, G.; Krasteva, V.; Jekova, I.; Gotchev, A.; Egiazarian, K. (2006) “Comparative study of morphological and time-frequency ECG descriptors for heartbeat classification”, Medical Engineering & Physics, vol. 28, p. 876–887.
Hamilton, P. S.; Tompkins, W. (1986) “Quantitative investigation of QRS detection rules using the MIT/BIH arrhythmia database”, IEEE Trans Biomed Engineering, vol. 33, p. 1157-1165.
Igarashi, M. O. (2007) “Utilização de filtros para remoção de interferência de sinais de eletrocardiograma”, Trabalho de graduação interdisciplinar, Escola de Engenharia da Universidade Presbiteriana Mackenzie, São Paulo.
Ince, T.; Kiranyaz, S.; Gabbouj, M. (2009) “A generic and robust system for automated patient-specific classification of ECG signals”, IEEE Trans Biomed Engineering, vol. 56, p.1415-1426.
Kim, J.; Min, S. D.; Lee, M. (2011) “An arrhythmia classification algorithm using a dedicated wavelet adapted to different subjects” BioMedical Engineering OnLine.
Llamedo, M.; Martínez, J. (2011) “Heartbeat classification using feature selection driven by database generalization criteria”, IEEE Trans Biomed Engineering, vol. 58, p. 616–625.
Madeiro, J. P. V.; Cortez, P. C.; Oliveira, F. I.; Siqueira, R. S. (2007) “A new approach to QRS segmentation based on wavelet bases and adaptive threshold technique”, Medical Engineering & Physics, vol. 29, p. 26–37.
Marcolino, M.; Alkmim, M. B.; Palhares, D.; Ribeiro, A. L. (2012) “Prevalence of Normal Electrocardiograms in Primary Care Patients: a Study by a Telemedicine Service in Brazil”, Global Telemedicine and eHealth Updates: Knowledge Resources, vol. 5, p. 615-618.
Martínez, J. P.; Almeida, R.; Olmos, S.; Rocha, A. P.; Laguna, P. (2004) “A wavelet-based ecg delineator evaluation on standard databases”, IEEE Transactions on Biomedical Engineering, v. 51, p. 570–581.
Mohamad, F. N.; Megat Ali, M. S. A.; Jahidin, A. H.; Saaid, M. F.; Noor, M. Z. H. (2013) “Principal Component Analysis and Arrhythmia Recognition Using Elman Neural Network”, 4th Control and System Graduate Research Colloquium, Shah Alam, Malásia.
Pan, J.; Tompkins, W.J. (1985) “A real-time QRS detection algorithm”, IEEE Trans. Biomed Engineering, vol. 32, p.230-236.
Physionet (2000) “Physionet o recurso de pesquisa para sinais fisiológicos complexos”, http://www.physionet.org, janeiro de 2014.
She, L.; Song, Y.; Zhang, S.; Xu, Z. (2010) “A Precise Ambulatory ECG Arrhythmia Intelligent Analysis Algorithm Based On Support Vector Machine Classifiers” 3rd International Conference on Biomedical Engineering and Informatics.
SMITH, L. I. (2002) “A Tutorial on Principal Component Analysis”.
Sparenberg, A.;Fetter, G.. (2012) “A Public Telecardiology Network in Southern Brazil: Results of Phase II (1st Year)”, Global Telemedicine and eHealth Updates: Knowledge Resources, Vol. 5, p. 598-602.
Zhang, Z.; Dong, J.; Luo, X.; Choi, K.; Wu, X. (2013) “Heartbeat classification using disease-specific feature selection” Computers in Biology and Medicine, vol. 46, p. 79–89.
