dsaitЦифровые решения и технологии искусственного интеллектаDigital Solutions and Artificial Intelligence Technologies3033-7097Финансовый университет при Правительстве Российской Федерацииdsait-10Research ArticleТЕМА НОМЕРА: Искусственный интеллект и машинное обучениеCOVER STORY: Artificial intelligence and machine learningВыявление сердечно-сосудистых заболеваний по сигналу ЭКГ с использованием методов машинного обученияDetecting Cardiovascular Diseases by ECG Signal Using Machine-learning methodshttps://orcid.org/0000-0003-2397-8119АвраменкоА. Д.AvramenkoA. D.

Александр Дмитриевич Авраменко - аспирант, ассистент кафедры информационных технологий факультета информационных технологий и анализа больших данных

Москва

Alexander D. Avramenko - Postgraduate Student, Assistant, Department of Information Technology, Faculty of Information Technology and Big Data Analysis

Moscow

ADAvramenko@fa.ruhttps://orcid.org/0000-0002-1658-1941СудаковВ. А.SudakovV. A.

Владимир Анатольевич Судаков - доктор технических наук, доцент, ведущий научный сотрудник

Москва

Vladimir A. Sudakov - Dr. Sci. (Tech.), Assoc. Prof., Leading Researcher

Moscow

sudakov@ws-dss.comФинансовый университет при Правительстве Российской ФедерацииFinancial University under the Government of the Russian FederationФинансовый университет при Правительстве Российской Федерации; Институт прикладной математики им. М.В. Келдыша РАНFinancial University under the Government of the Russian Federation; The M.V. Keldysh Institute of Applied Mathematics of the Russian Academy of Sciences202520112025122631Copyright © Авраменко А.Д., Судаков В.А., 20252025Авраменко А.Д., Судаков В.А.Avramenko A.D., Sudakov V.A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.digitarin.ru/jour/article/view/10

В статье рассматривается актуальная проблема автоматической диагностики сердечно-сосудистых заболеваний на основе анализа электрокардиографических (ЭКГ) сигналов. Основной целью исследования является повышение эффективности диагностического процесса с применением современных методов машинного обучения. В ходе работы проведен комплексный анализ существующих научных исследований в данной области. Особое внимание уделено систематизации наиболее эффективных методов и подходов к обработке ЭКГ и ЭЭГ-сигналов. В результате исследования выявлены перспективные направления применения капсульных нейронных сетей, генеративно-состязательных сетей и вейвлет-преобразования для решения задач диагностики. Отдельное внимание уделено диагностике вибраций оборудования, искажающих сигнал ЭКГ. Практическая значимость работы заключается в представлении современных методов автоматического выявления сердечно-сосудистых заболеваний на основе данных ЭКГ. На основе проведенного анализа сформулированы рекомендации по применению различных методов машинного обучения и определены перспективные направления дальнейших исследований.

The problem of automatic diagnostic of diseases, in particular cardiovascular diseases by ECG signal (Electrocardiography). Goal. Improve diagnostic efficiency by using modern machine learning methods. Results. The results of the article review are presented in a systematic form, the most effective methods and approaches are highlighted, as well as their applicability to solving specific problems of diagnosing cardiovascular diseases. Based on the analysis of existing works, conclusions are made about the prospects of using machine learning methods in the field of diagnosis of cardiovascular diseases based on ECG data and suggest possible directions for future research in this field. Practical significance. The article highlights modern methods and approaches used in modern research aimed at automatic detection of cardiovascular diseases using ECG data.

капсульные нейронные сетиданные ЭКГвейвлет-преобразованиегенеративно-состязательные сетидиагностика оборудованиясердечно-сосудистые заболеванияcapsule neural networks (CapsNet)ECGWavelet transformgenerative-adversarial networks (GAN)equipment diagnosticscardiovascular diseasesReferencesButun E., Yildirim O., Talo M., Tan R. 1D-CADCapsNet: One dimensional deep capsule networks for coronary artery disease detection using ECG signals. Physica Medica. 2020;70:39–48 URL: https://www.sciencedirect.com/science/article/pii/S 1120179720300077. DOI: 10.1016/j.ejmp.2020.01.007Butun E., Yildirim O., Talo M., Tan R. 1D-CADCapsNet: One dimensional deep capsule networks for coronary artery disease detection using ECG signals. Physica Medica. 2020;70:39–48 URL: https://www.sciencedirect.com/science/article/pii/S 1120179720300077. DOI: 10.1016/j.ejmp.2020.01.007El Boujnouni I., Zili H., Tali A., Tali T., Laaziz Y. A wavelet-based capsule neural network for ECG biometric identification. Biomedical Signal Processing and Control. 2022;76:103692. URL: https://www.sciencedirect.com/science/article/pii/S 1746809422002142 DOI: 10.1016/j.bspc.2022.103692El Boujnouni I., Zili H., Tali A., Tali T., Laaziz Y. A wavelet-based capsule neural network for ECG biometric identification. Biomedical Signal Processing and Control. 2022;76:103692. URL: https://www.sciencedirect.com/science/article/pii/S 1746809422002142 DOI: 10.1016/j.bspc.2022.103692El Boujnouni I., Harouchi B., Tali A., Rachafi S., Laaziz Y. Automatic diagnosis of cardiovascular diseases using wavelet feature extraction and convolutional capsule network. Biomedical Signal Processing and Control. 2023;81:104497. URL: https://www.sciencedirect.com/science/article/pii/S 174680942200951X DOI: 10.1016/j.bspc.2022.104497El Boujnouni I., Harouchi B., Tali A., Rachafi S., Laaziz Y. Automatic diagnosis of cardiovascular diseases using wavelet feature extraction and convolutional capsule network. Biomedical Signal Processing and Control. 2023;81:104497. URL: https://www.sciencedirect.com/science/article/pii/S 174680942200951X DOI: 10.1016/j.bspc.2022.104497Sonawane R., Patil H. Automated heart disease prediction model by hybrid heuristic-based feature optimization and enhanced clustering. Biomedical Signal Processing and Control. 2022;72:103260. URL: https://www.sciencedirect.com/science/article/abs/pii/S 0925231221005270 DOI: 10.1016/j.bspc.2021.103260Sonawane R., Patil H. Automated heart disease prediction model by hybrid heuristic-based feature optimization and enhanced clustering. Biomedical Signal Processing and Control. 2022;72:103260. URL: https://www.sciencedirect.com/science/article/abs/pii/S 0925231221005270 DOI: 10.1016/j.bspc.2021.103260Li C., Wang B., Zhang S., Liu Y., Song R., Cheng J., Chen X. Emotion recognition from EEG based on multi-task learning with capsule network and attention mechanism. Computers in Biology and Medicine. 2022;143:105303. URL: https://www.sciencedirect.com/science/article/pii/S 0010482522000956 DOI: 10.1016/j.compbiomed.2022.105303Li C., Wang B., Zhang S., Liu Y., Song R., Cheng J., Chen X. Emotion recognition from EEG based on multi-task learning with capsule network and attention mechanism. Computers in Biology and Medicine. 2022;143:105303. URL: https://www.sciencedirect.com/science/article/pii/S 0010482522000956 DOI: 10.1016/j.compbiomed.2022.105303Wei Y., Liu Y., Li C., Cheng J., Song R., Chen X. TC-Net: A Transformer Capsule Network for EEG-based emotion recognition. Computers in Biology and Medicine. 2023;152:106463. URL: https://www.sciencedirect.com/science/article/pii/S 0010482522011714 DOI: 10.1016/j.compbiomed.2022.106463Wei Y., Liu Y., Li C., Cheng J., Song R., Chen X. TC-Net: A Transformer Capsule Network for EEG-based emotion recognition. Computers in Biology and Medicine. 2023;152:106463. URL: https://www.sciencedirect.com/science/article/pii/S 0010482522011714 DOI: 10.1016/j.compbiomed.2022.106463Zhou J., Chu S., Li X., Xiao F., Sun L. An EEG emotion recognition method based on transfer learning and echo state network for HilCPS. Microprocessors and Microsystems. 2021;87:103381. URL: https://www.sciencedirect.com/science/article/pii/S 0141933120305391 DOI: 10.1016/j.micpro.2020.103381.Zhou J., Chu S., Li X., Xiao F., Sun L. An EEG emotion recognition method based on transfer learning and echo state network for HilCPS. Microprocessors and Microsystems. 2021;87:103381. URL: https://www.sciencedirect.com/science/article/pii/S 0141933120305391 DOI: 10.1016/j.micpro.2020.103381.Hou F., Gao Q., Song Y., Wang Z., Bai Z., Yang Y., Tian Z. Deep feature pyramid network for EEG emotion recognition. Measurement. 2022;201:111724. URL: https://www.sciencedirect.com/science/article/pii/S 0263224122009290 DOI: 10.1016/j.measurement.2022.111724Hou F., Gao Q., Song Y., Wang Z., Bai Z., Yang Y., Tian Z. Deep feature pyramid network for EEG emotion recognition. Measurement. 2022;201:111724. URL: https://www.sciencedirect.com/science/article/pii/S 0263224122009290 DOI: 10.1016/j.measurement.2022.111724Hu J., Wang C., Jia Q., Bu Q., Sutcliffe R., Feng J. ScalingNet: Extracting features from raw EEG data for emotion recognition. Neurocomputing. 2021;463:177–184. URL: https://www.sciencedirect.com/science/article/pii/S 0925231221012029 DOI: 10.1016/j.neucom.2021.08.018Hu J., Wang C., Jia Q., Bu Q., Sutcliffe R., Feng J. ScalingNet: Extracting features from raw EEG data for emotion recognition. Neurocomputing. 2021;463:177–184. URL: https://www.sciencedirect.com/science/article/pii/S 0925231221012029 DOI: 10.1016/j.neucom.2021.08.018Dong H., Chen D., Zhang L., Ke H., Li X. Subject sensitive EEG discrimination with fast reconstructable CNN driven by reinforcement learning: A case study of ASD evaluation. Neurocomputing. 2021;449:136–145. URL: https://www.sciencedirect.com/science/article/pii/S 0925231221005270 DOI: 10.1016/j.neucom.2021.04.009Dong H., Chen D., Zhang L., Ke H., Li X. Subject sensitive EEG discrimination with fast reconstructable CNN driven by reinforcement learning: A case study of ASD evaluation. Neurocomputing. 2021;449:136–145. URL: https://www.sciencedirect.com/science/article/pii/S 0925231221005270 DOI: 10.1016/j.neucom.2021.04.009Liang P., Deng C., Yuan X., Zhang L. A deep capsule neural network with data augmentation generative adversarial networks for single and simultaneous fault diagnosis of wind turbine gearbox. ISA Transactions. 2022. URL: https://www.sciencedirect.com/science/article/pii/S 0019057822005365 DOI: 10.1016/j.isatra.2022.10.008Liang P., Deng C., Yuan X., Zhang L. A deep capsule neural network with data augmentation generative adversarial networks for single and simultaneous fault diagnosis of wind turbine gearbox. ISA Transactions. 2022. URL: https://www.sciencedirect.com/science/article/pii/S 0019057822005365 DOI: 10.1016/j.isatra.2022.10.008Zhang Q., Li J., Ding W., Ye Z., Meng Z. Mechanical fault intelligent diagnosis using attention-based dualscale feature fusion capsule network. Measurement. 2023;207:112345. URL: https://www.sciencedirect.com/science/article/pii/S 026322412201541X DOI: 10.1016/j.measurement.2022.112345Zhang Q., Li J., Ding W., Ye Z., Meng Z. Mechanical fault intelligent diagnosis using attention-based dualscale feature fusion capsule network. Measurement. 2023;207:112345. URL: https://www.sciencedirect.com/science/article/pii/S 026322412201541X DOI: 10.1016/j.measurement.2022.112345Liu J., Zhang C., Jiang X. Imbalanced fault diagnosis of rolling bearing using improved MsR-GAN and feature enhancement-driven CapsNet. Mechanical Systems and Signal Processing. 2022;168:108664. URL: https://www.sciencedirect.com/science/article/pii/S 0888327021009882 DOI: 10.1016/j.ymssp.2021.108664Liu J., Zhang C., Jiang X. Imbalanced fault diagnosis of rolling bearing using improved MsR-GAN and feature enhancement-driven CapsNet. Mechanical Systems and Signal Processing. 2022;168:108664. URL: https://www.sciencedirect.com/science/article/pii/S 0888327021009882 DOI: 10.1016/j.ymssp.2021.108664

The authors declare that there are no conflicts of interest present.