O.V. Nepomnyashchiy1, A.G. Khantimirov2, M.M.I. Al-sagheer3, S. Shabir4

1–4 Siberian Federal University (Krasnoyarsk, Russia)

Problem setting. It is known that in Russia about one million people die from cardiovascular diseases every year. The use of advanced technologies can help reduce mortality by early diagnosis of diseases. This process is accompanied by a large volume of biomedical information, which in turn necessitates the creation of new methods, algorithms and tools for data mining. In this regard, it seems appropriate to consider the problem of detecting anomalies in the analysis of electrocardiograms in devices for automated diagnosis of diseases of the cardiovascular system.

Target. To develop a method and a technical solution for detecting anomalies in the analysis of electrocardiograms in devices for automated diagnosis of diseases of the cardiovascular system.

Results. The well-known directions of the analysis of cardiac signals are presented. Taking into account the need for big data analysis, the general task of creating new methods for obtaining effective solutions is highlighted. The local task of increasing the accuracy of the results obtained, as well as providing diagnostics in real time, is formulated. It is shown that in the field of classification problems in image processing, good results are obtained using a convolutional neural network. To solve these problems, it is proposed to use convolutional neural networks.

Practical significance. The results of experimental studies have shown the high efficiency of the developed method in detecting arrhythmias (tachycardia, bradycardia, paroxysmal disorders, extrasystole, atrial fibrillation of the heart). The developed method can be used to create devices for automated detection of cardiovascular anomalies. The proposed device will make it possible to diagnose at the early stages of the development of the disease, which, in turn, will make it possible to make the correct diagnosis and prescribe timely treatment.

Nepomnyashchiy O.V., Khantimirov A.G., Al-sagheer M.M.I., Shabir S. The use of convolutional neural network in the analysis of electrocardiograms. Neurocomputers. 2023. V. 25. № 2. Р. 58-65. DOI: https://doi.org/10.18127/j19998554-202302-05 (In Russian)

1. Akay M. Time Frequency and Wavelets in Biomedical Signal Processing. Wiley-IEEE Press. 1997. 768 p.
2. Inoue H., Miyazaki A. A noise reduction method for ECG signals using the dyadic wavelet transform. IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences. 1998. V. E81-A. № 9. P. 1001–1007.
3. Huang J., Chen B., Yao B., He W. ECG Arrhythmia Classification Using STFT-Based Spectrogram and Convolutional Neural Network. IEEE Access. 2019. V. 7. P. 92871–92880.
4. Lakhani P., Sundaram B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology. 2017. V. 284. № 2. P.574–582. DOI: 10.1148/radiol.2017162326.
5. Acharya U.R., Fujita H., Oh S.L., Hagiwara Y., Tan J.H., Adam M. Automated Detection of Arrhythmias Using Different Intervals of Tachycardia ECG Segments with Convolutional Neural Network. Information sciences. 2017. V. 405. P. 81–90.
6. Cao J., Brown M.L., Higgins E.J., Degroot P.J. Automatic thresholds for atrial tachyarrhythmia detection in an implantable medical device. Google Patents. 2019. Electronic resource. Access mode: https://patents.google.com/patent/WO2018022558A1/en, date of reference 02.09.2022.
7. Li F., Chen K., Ling J., Zhan Y., Manogaran G. Automatic diagnosis of cardiac arrhythmia in electrocardiograms via multigranulation computing. Applied Soft Computing. 2019. V. 80. P. 400–413. DOI: 10.1016/j.asoc.2019.04.007.
8. Wu Z., Lan T., Yang C., Nie Z. A Novel Method to Detect Multiple Arrhythmias Based on Time-Frequency Analysis and Convolutional Neural Networks. IEEE Access. 2019. V. 7. P. 170820–170830. DOI: 10.1109/ACCESS.2019.2956050.
9. Kobernichenko V.G. Fundamentals of digital signal processing: textbook. Yekaterinburg: Ural Federal University. 2018. 147 р. (In Russian).
10. Alfaras M., Soriano M.C., Ortín S. A fast machine learning model for ECG-based heartbeat classification and arrhythmia detection. Frontiers in Physics. 2019. V. 7. № JULY. DOI: 10.3389/fphy.2019.00109.
11. Luz E.J., Schwartz W.R., Cámara-Chávez G., Menotti D. ECG-based heartbeat classification for arrhythmia detection: A survey. Computer Methods and Programs in Biomedicine. 2016. V. 127. P. 144–164. DOI: 10.1016/j.cmpb.2015.12.008.
12. Prakash A.J., Ari S. A system for automatic cardiac arrhythmia recognition using electrocardiogram signal. In book: Bioelectronics and Medical Devices. San Francisco: Elsevier. 2019. P. 891–911. DOI: 10.1016/B978-0-08-102420-1.00042-X.
13. Pomprapa A., Ahmed V., Stollenwerk A., Kowalewski S., Leonard S. The study of arrhythmia on an ECG recorded by contactless capacitive electrodes using convolutional neural networks. Biomedical radioelectronics. 2018. V. 6. P. 45–48. (In Russian).
14. Taleb E.M., Sushkova L.T., Al-Haidari V.A., Isakov R.V. Detection of coronary heart disease by single-channel electrocardiogram based on artificial neural networks. Biomedical radioelectronics. 2018. V. 9. P. 3–9. DOI: 10.18127/j15604136-201809-01. (In Russian).
15. De Albuquerque V.H.C., Nunes T., Pereira D., Luz E., Menotti D., Papa J., Tavares J. Robust automated cardiac arrhythmia detection in ECG beat signals. Neural Computing and Applications. 2018. V. 29. №. 3. P. 679–693. DOI:10.1007/s00521-016-2472-8
16. MIT-BIH Arrhythmia Database. Electronic resource. Access mode: https://physionet.org/content/mitdb/1.0.0/, date of reference 16.06.2022.
17. AHA Database Sample Excluded Record. Electronic resource. Access mode: https://physionet.org/content/ahadb/1.0.0/, date of reference 16.06.2022.
18. Elhaj F.A., Salim N., Ahmed T., Harris A.R., Swee T.T. Hybrid classification of Bayesian and extreme learning machine for heartbeat classification of arrhythmia detection. Materials 6th ICT International Student Project Conference (ICT-ISPC). 2017. P. 1–4.
19. Yildirim Ö., Pławiak P., Tan R.S., Acharya U.R. Arrhythmia Detection Using Deep Convolutional Neural Network With Long Duration ECG Signals. Computers in Biology and Medicine. 2018. V. 102. P. 411–420. DOI: 10.1016/j.compbiomed.2018.09.009.
20. Işın A., Özdalili S. Cardiac arrhythmia detection using deep learning. Procedia computer science. 2017. V. 120. P. 268–275. DOI: 10.1016/j.procs.2017.11.238.