CFP last date
20 August 2024
Reseach Article

Detection of Myocardial Infarction in Electrocardiograms using Machine Learning

by Paulo Vinicius Masnik, Roberto Alexandre Dias, Mario De Noronha Neto
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 183 - Number 9
Year of Publication: 2021
Authors: Paulo Vinicius Masnik, Roberto Alexandre Dias, Mario De Noronha Neto
10.5120/ijca2021921384

Paulo Vinicius Masnik, Roberto Alexandre Dias, Mario De Noronha Neto . Detection of Myocardial Infarction in Electrocardiograms using Machine Learning. International Journal of Computer Applications. 183, 9 ( Jun 2021), 12-19. DOI=10.5120/ijca2021921384

@article{ 10.5120/ijca2021921384,
author = { Paulo Vinicius Masnik, Roberto Alexandre Dias, Mario De Noronha Neto },
title = { Detection of Myocardial Infarction in Electrocardiograms using Machine Learning },
journal = { International Journal of Computer Applications },
issue_date = { Jun 2021 },
volume = { 183 },
number = { 9 },
month = { Jun },
year = { 2021 },
issn = { 0975-8887 },
pages = { 12-19 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume183/number9/31954-2021921384/ },
doi = { 10.5120/ijca2021921384 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T01:16:18.152684+05:30
%A Paulo Vinicius Masnik
%A Roberto Alexandre Dias
%A Mario De Noronha Neto
%T Detection of Myocardial Infarction in Electrocardiograms using Machine Learning
%J International Journal of Computer Applications
%@ 0975-8887
%V 183
%N 9
%P 12-19
%D 2021
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Currently, millions of people in the world have some type of deficiency in the cardiovascular system, more specifically anomalies in the heart and its heartbeat, most of these individuals end up not discovering these problems in advance, which would have a great impact on the chance of survival. In Brazil, the number of deaths caused by heart problems exceeds 350 thousand per year. The solution found to assist in the prevention and detection of pre-existing problems starts from the approach of analyzing electrocardiograms of people with already known conditions and anomalies, starting from the machine learning method for preventing conditions with only data input to a model. The proposal of this work designs in a prototype in which, in just a few moments, it generates a prediction with a considerable success rate, capable of assisting health professionals to make decisions regarding the patient's situation, based on the analysis of waves from an electrocardiogram (ECG). During this work, it is demonstrated the entire process of data acquisition and selection, treatment and filtering of wave signals until the development of an exam prediction. The results found were correct rates in the infarction class, higher than 80, 90 and up to 95%. It is also important to understand that the increase in the hit rate of the class with the anomaly tends to decrease the hit rate of normal exams.

References
  1. Richens, J.G., Lee, C.M. and Johri, S., 2020. Improving the accuracy of medical diagnosis with causal machine learning. Nature communications, 11(1), pp.1-9.
  2. Lehoux, P., Sicotte, C., Denis, J.L., Berg, M. and Lacroix, A., 2002. The theory of use behind telemedicine: how compatible with physicians’ clinical routines?. Social science & medicine, 54(6), pp.889-904.
  3. Liu, Y., Jain, A., Eng, C., Way, D.H., Lee, K., Bui, P., Kanada, K., de Oliveira Marinho, G., Gallegos, J., Gabriele, S. and Gupta, V., 2020. A deep learning system for differential diagnosis of skin diseases. Nature Medicine, 26(6), pp.900-908.
  4. Li, Q., Rajagopalan, C. and Clifford, G.D., 2014. A machine learning approach to multi-level ECG signal quality classification. Computer methods and programs in biomedicine, 117(3), pp.435-447.
  5. Nicolau, J.C., Polanczyk, C.A., Pinho, J.A., Bacellar, M.S.D.C., Ribeiro, D.G.L., Darwich, R.N., Ribeiro, A.L.P., Dunda, M.M.E., Germiniani, H., França, F.F. and Saraiva, L., 2003. Diretriz de interpretação de eletrocardiograma de repouso. Arquivos Brasileiros de Cardiologia, 80, pp.1-18.
  6. Barold, S.S., 2003. Willem Einthoven and the birth of clinical electrocardiography a hundred years ago. Cardiac electrophysiology review, 7(1), pp.99-104.
  7. Neto, M.M.R., 1948. Conceito e valor das derivações unipolares dos membros. Revista de Medicina, 32(169-172), pp.55-73.
  8. White, H.D. and Chew, D.P., 2008. Acute myocardial infarction. The Lancet, 372(9638), pp.570-584.
  9. Makowski, D., Pham, T., Lau, Z.J., Brammer, J.C., Lespinasse, F., Pham, H., Schölzel, C. and Chen, S.A., 2021. NeuroKit2: A Python toolbox for neurophysiological signal processing. Behavior Research Methods, pp.1-8.
  10. Pan, J. and Tompkins, W.J., 1985. A real-time QRS detection algorithm. IEEE transactions on biomedical engineering, (3), pp.230-236.
  11. Álvarez, R.A., Penín, A.J.M. and Sobrino, X.A.V., 2013. A comparison of three QRS detection algorithms over a public database. Procedia Technology, 9, pp.1159-1165.
  12. Bradley, A.P., 1997. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern recognition, 30(7), pp.1145-1159.
  13. Provost, F. and Kohavi, R., 1998. Glossary of terms. Journal of Machine Learning, 30(2-3), pp.271-274.
Index Terms

Computer Science
Information Sciences

Keywords

Myocardial detection electrocardiograms analysis machine learning in healthcare.