A.I. Vlasov1, S.E. Gyulmalieva2, Y.S. Liber3, S. Abdulkade4
1–4 Bauman Moscow State Technical University (Moscow, Russia)
The work carried out a review of the current state and prospects for the development of artificial intelligence systems in electrocardiography. The article analyzed the prospects of using machine learning methods to analyze the bioelectric activity of the heart. Examples of solutions for diagnosing different cardiovascular diseases are briefly considered.
The purpose of the work is to systematize and generalize the methods of using artificial intelligence systems for the analysis of electrocardiograms.
Based on the results of the analysis, a classification of methods for obtaining information on cardiac activity is proposed. The main focus is on the computer processing of the results of analysis of cardiac activity by various methods. Principles of building databases containing cardiac diagnostic results for patients with various deviations and possibilities of their use for training of neural networks were analyzed.
The results of the work can be used to create various types of neural networks for automated analysis of electrocardiograms and the formation of a diagnostic conclusion.
Vlasov A.I., Gyulmalieva S.E., Liber Y.S., Abdulkade S. Application of artificial intelligence systems in electrocardiography. Neurocomputers. 2022. V. 24. № 1. Р. 36-52. DOI: https://doi.org/10.18127/j19998554-202201-04 (In Russian).
- Orlov V.N. Rukovodstvo po elektrokardiografii. 9-e izd., ispr. M.: Meditsinskoye informatsionnoye agentstvo. 2017. 560 s. (in Russian).
- Galanin V.V. Fizicheskiye osnovy elektrografii. Vestnik meditsinskogo instituta «REAVIZ»: reabilitatsiya. vrach i zdorovye. 2013.
№ 4(12). S. 35–41. (in Russian). - Vlasov A.I., Konkova A.F. Mediko-diagnosticheskiye ekspertnyye sistemy dlya otsenki adekvatnosti adaptivnoy reaktsii organizma na vozdeystviye ekstremalnykh faktorov. Konversiya. 1995. № 9–10. S. 18–21. (in Russian).
- Mustafayev A.G. Ispolzovaniye neyrosetevykh metodov dlya avtomaticheskogo analiza elektrokardiogramm pri diagnostike zabolevaniy serdechno-sosudistoy sistemy. Kibernetika i programmirovaniye. 2019. № 1. S. 66–74. (in Russian).
- Revenko S.V. Garmonicheskiye perspektivy reografii. Nervno-myshechnyye bolezni. 2012. № 4. S. 8–18. (in Russian).
- Atzler E., Lehmann G. Űberein Neues Verfahrenzur Darstellung der Hertztätigkeit (Dielektrographie). Arbeitsphysiol 1931/32. V. 6.
P. 636–680. - Mann H. Study of peripheral circulation by means of alternating current bridge. Proc. Soc. Exp. Biol. Med. 1937. № 36. P. 670–673.
- Rosa L. Diagnostische Anwendung des Kurzwellenfeldes in der Herz und Kreislaufpathologie (Radiokardiographie). Z. Kreislaufforsch. 1940. № 32. P. 118–135.
- Nyboer J., Bango S., Barnett A., Halsey R.H. Radiocardiograms: the electrical impedance changes of the heart in relation to electrocardiograms and heart sounds. J. Clin. Invest. 1940. № 19(5). P.773–778.
- Kedrov A.A. O novom metode opredeleniya pulsovykh kolebaniy krovenapolneniya sosudov v razlichnykh uchastkakh chelovechesko-go tela. Klin. med. 1941. № 19(1). S. 71–80. (in Russian).
- Kedrov A.A. Popytka kolichestvennoy otsenki tsentralnogo i perifericheskogo krovoobrashcheniya elektrometricheskim putem. Klin. med. 1948. № 26(5). S. 32–51. (in Russian).
- Kedrov A.A., Liberman T.Yu. O tak nazyvayemoy reokardiografii. Klin. med. 1949. № 27(3). S. 40–46. (in Russian).
- Holtzer W., Polzer K., Mario A. RKG Rheography. A Method of Circulation Investigation and Diagnosis in Circular Motion. Vienna: Wilhelm Maudrich. 1946.
- Nyboer J. Regional pulse volume and perfusion flow electrical impedance plethysmography. Arc. Intern. Med. 1960. № 105(9). P. 264–276.
- Nyboer J. Highlights in electrical impedance plethysmography or pulse volume and flow indices derived from segmental electrical characteristics. Data Acquisition and Processing in Biology and Medicine. Oxford. 1962. P. 133–145.
- Nyboer J. Electrical Impedance Plethysmography. Springfield. 1970.
- Pratesi F., Deidda C., Nuti A., Caramelli L. Selective rheography of the vertebral arteries and carotids in encephalic vascular diseases. Ann. N.-Y. Acad. Sci. 1970. V.170 (Part 2). P. 627–644.
- Schuhfried O., Wiesinger G., Kollmitzer J. et al. Fourier analysis of impedance rheography for peripheral arterial occlusive disease. Eur. J. Appl. Physiol. 2003. № 89. P. 384–638.
- Pushkar Yu.T. Issledovaniye sokratitelnoy funktsii serdtsa pri serdechno-sosudistykh zabolevaniyakh pri pomoshchi reografii aorty i legkikh. Ter. arkh. 1961. № 3(1). S. 88–96. (in Russian).
- Pushkar Yu.T., Tolpekhin V.E. Opyt primeneniya razdelnoy reografii aorty i legkogo u bolnykh tetradoy Fallo. Kardiologiya. 1967.
№ 7(2). S. 42–46. (in Russian). - Petrash V.V., Lazarev S.M., Danilov E.N. Mekhanizmy formirovaniya intravaskulyarnoy reopletizmogrammy v sisteme legochnoy arterii. Vest. khirurgii. 1981. № 126(6). S. 6–10. (in Russian).
- Frolkis A.V., Borisova G.V. Ispolzovaniye matematicheskikh metodov pri analize formy reogramm pecheni. Voprosy patologii pecheni i podzheludochnoy zhelezy. 1968. S. 42–43. (in Russian).
- Frolkis A.V., Borisova G.V. Opyt ispolzovaniya garmonicheskogo analiza dlya kolichestvennoy otsenki formy reogramm pecheni. Sov. med. 1973. № 36(3). S. 33–37. (in Russian).
- Frolkis A.V., Borisova G.V. Kolichestvennaya otsenka formy reogramm metodom garmonicheskogo analiza. Kardiologiya. 1974.
№ 14(4). S. 130–133. (in Russian). - Streletskiy G.N., Vasilenko I.S. Reografiya pecheni pri differentsialnoy diagnostike obstruktivnoy zheltukhi. Khirurgiya. 1975. № 9.
S. 96–101. (in Russian). - Nikolayev D.V., Smirnov A.V., Bobrinskaya I.G., Rudnev S.G. Bioimpedansnyy analiz sostava tela cheloveka. M.: Nauka. 2009. 392 s. (in Russian).
- Zairova A.R., Rogoza A.N. Obyemnaya sfigmografiya segodnya. Meditsinskiy alfavit. 2018. № 4(36). S. 8–18. (in Russian).
- Savitskiy N.N. Biofizicheskiye osnovy krovoobrashcheniya i klinicheskiye metody issledovaniya gemodinamiki. L.: Meditsina. 1974. 309 s. (in Russian).
- Blinova E.V., Sakhnova T.A., Yurasova E.S., Komlev A.E., Imayev T.E. Fonokardiografiya: novyye vozmozhnosti v svete tsifrovykh tekhnologiy. Kardiologicheskiy vestnik. 2018. T. 13. № 2. S. 15–21. (in Russian).
- Kipenskiy A.V., Shamardina V.N., Deyneko D.M. Elektrokardiografiya: Uchebno-metodicheskoye posobiye. Kharkov: NTU «KhPI». 2002. 52 s. (in Russian).
- Zaretskiy A.P., Mityagin K.S., Tarasov V.S., Moroz D.N. Otsenka parametrov dykhatelnoy aktivnosti patsiyenta na osnove dannykh fotopletizmografii. Trudy Moskovskogo fiziko-tekhnicheskogo instituta (natsionalnogo issledovatelskogo universiteta). 2019. T. 11.
№ 3(43). S. 61–69. (in Russian). - Murashko V.V., Strutynskiy A.V. Elektrokardiografiya. 6-e izd. M.: MEDpressinform. 2004. 320 s. (in Russian).
- Geselovits D. B. K teorii elektrokardiogrammy. Proc IEEE. T. 77. № 857. 1989. 446 s. (in Russian).
- Dubrovin V.I., Tverdokhleb Yu.V. Usovershenstvovaniye metodov analiza EKG-signalov na osnove veyvlet-preobrazovaniya v si-steme elektrokardiografii vysokogo razresheniya. Radioelektronika. informatika. upravleniye. 2011. № 1(24). S. 91–98. (in Russian).
- Ebert G.-Kh. Prostoy analiz EKG: interpretatsiya. differentsialnyy diagnoz. Per. s angl. pod red. Kokorina V.A. M.: Lo-gosfera. 2010. 280 s. (in Russian).
- Eliseyeva L.N., Sirunyants A.A., Samorodskaya N.A., Baste Z.A. Osnovy elektrokardiografii dlya studentov meditsinskikh vuzov (obuchayushchiy material i atlas uchebnykh elektrokardiogramm). Mezhdunarodnyy zhurnal eksperimentalnogo obrazovaniya. 2012. № 10. S. 98–99. (in Russian).
- Naumenko A.I., Skotnikov V.V. Osnovy elektropletizmografii. L.: Meditsina. 1975. 216 s. (in Russian).
- Isakov R.V. Algoritmy predvaritelnoy obrabotki elektrokardiosignala dlya neyrosetevogo analiza. Sbornik trudov nauchnoy shkoly po biomeditsinskoy inzhenerii. SPb.: Izd-vo SPGTU. 2009. S. 82–87. (in Russian).
- Prudius A.A., Karpunin A.A., Vlasov A.I. Analysis of machine learning methods to improve efficiency of big data processing in industry 4.0. Journal of Physics: Conference Series. 2019. № 032065.
- Adamova A.A., Zaykin V.A., Gordeyev D.V. Metody i tekhnologii mashinnogo obucheniya i neyrosetevykh tekhnologiy v zadachakh kompyuternogo zreniya. Neyrokompyutery: razrabotka. primeneniye. 2021. T. 23. № 4. S. 25–39. (in Russian).
- Yuldashev M.N., Vlasov A.I., Novikov A.N. Energy-efficient algorithm for classification of states of wireless sensor network using machine learning methods. Journal of Physics: Conference Series. 2018. V. 1015. № 032153.
- Geltser B. I., Tsivanyuk M. M., Shakhgeldyan K. I., Rublev V. Yu. Metody mashinnogo obucheniya kak instrument diagnosticheskikh i prognosticheskikh issledovaniy pri ishemicheskoy bolezni serdtsa. Rossiyskiy kardiologicheskiy zhurnal. 2020. T. 25. № 12. DOI:10.15829/1560-4071-2020-3999 (in Russian).
- Verma L, Srivastava S, Negi P.C. A Hybrid Data Mining Model to Predict Coronary Artery Disease Cases Using Non-Invasive Clinical Data. J. Med. Syst. 2016. V. 40(7). P. 178.
- Kozlova E.V., Starostin I.V., Bulkina O.S. et al. Evaluation of the prevalence of cardiovascular events and mortality in stable coronary heart disease patients depending on baselinecoronary collateral blood flow (five-year follow-up). Russian Journal of Cardiology. 2018. V. 3. P.11–16.
- Sridhar C., Acharya U.R., Bairy G.M. Automated diagnosis of Coronary Artery Diseaseusing nonlinear features extracted from ECG signals. IEEE International Conference on Systems, Man, and Cybernetics (SMC). Budapest, 2016. P. 000545-000549.
- Gusev A.V., Dobridnyuk S.L. Iskusstvennyy intellekt v meditsine i zdravookhranenii. Informatsionnoye obshchestvo. 2017. № 4–5.
S. 78–93. (in Russian). - Pereverzev I.A., Kvasnitskiy V.N. Effektivnyye algoritmy postroyeniya neyronnoy seti na osnovanii otsenki vkhodnykh parametrov (Glubokoye mashinnoye obucheniye). Vestnik Moskovskogo finansovo-yuridicheskogo universiteta. 2016. № 1. S. 253–261. (in Russian).
- Tikhonov A.A. Bolshiye dannyye i glubokoye mashinnoye obucheniye v iskusstvennykh neyronnykh setyakh. Nauka i obrazovaniye segodnya. 2018. № 6 (29). S. 35–38. (in Russian).
- Kodirov E.S.U., Khalilov Z.Sh. Vzaimosvyazi i razlichiya mezhdu “Deep Learning” i “Machine Learning”. Universum: tekhnicheskiye nauki. 2020. № 7-1 (76). S. 23–25. (in Russian).
- Bizopoulos P., Koutsouris D. Deep Learning in Cardiology. IEEE Rev Biomed Eng. 2019. V. 12. P. 168–193. DOI: 10.1109/RBME.2018.2885714
- Al Rahhal M.M., Bazi Y., Al Hichri H., Alajlan N., Melgani F., Yager R.R. Deep learning approach for active classification ofelectrocardiogram signals. Information Sciences. 2016. V. 345. P. 340–354.
- Shakhnov V.A., Vlasov A.I., Polyakov Yu.A., Kuznetsov A.S. Neyrokompyutery: arkhitektura i skhemotekhnika. M.: Izd-vo Mashinostroyeniye. 2000. 64 s. (in Russian).
- Vlasov A.I., Papulin S.Yu. Analiz dannykh s ispolzovaniyem gistogrammnoy modeli kombinatsii priznakov. Neyrokompyute-ry: razrabotka. primeneniye. 2019. T. 21. № 5. S. 18–27. (in Russian).
- Averianikhin A.E., Vlasov A.I., Evdokimova E.V. Ierarkhicheskaya piramidalnaya subdiskretizatsiya v glubokikh svertochnykh setyakh dlya raspoznavaniya vizualnykh obrazov. Neyrokompyutery: razrabotka. primeneniye. 2021. T. 23. № 1. S. 17–31. (in Russian).
- Viryasova A.Yu., Vlasov A.I., Gladkikh A.A. Neyrosetevyye metody defektoskopii integralnykh struktur. Neyrokompyutery: razrabotka. primeneniye. 2019. № 2. S. 54–67. (in Russian).
- Vlasov A.I. Apparatnaya realizatsiya neyrovychislitelnykh upravlyayushchikh sistem. Pribory i sistemy. Upravleniye. kontrol. diagnostika. 1999. № 2. S. 61–65. (in Russian).
- Adamova A.A., Shvedova A.G., Firsov A.A. Analiz primeneniya elekrofizicheskikh metodov i sredstv v psikhiatrii i nevrologii. Tekhnologii inzhenernykh i informatsionnykh sistem. 2019. № 3. S. 53–62. (in Russian).
- Juarez-Orozco L.E., Saraste A., Capodanno D. et al. Impact of a decreasing pre-test probability on the performance of diagnostic tests for coronary artery disease. Eur. Heart J. Cardiovasc. Imaging. 2019. V. 20(11). P. 1198–1207. DOI: 10.1093/ehjci/jez054
- Knuuti J., Wijns W., Saraste A., et al. 2019 ESC Guidelines on the diagnosis and management of chronic coronary syndromes: The Task Force for diagnosis and management of chronic coronary syndromes of the European Society of Cardiology (ESC). Eur. Heart J. 2019. V. 41(3). P. 407–477. DOI:10.1093/eurheartj/ehz425
- Bae Y., Kang S-J., Kim G., et al. Prediction of coronary thin-cap fibroatheroma by intravascular ultrasound-based machine learning. Atherosclerosis. 2019. V. 288. P. 168–174. DOI: 10.1016/j.atherosclerosis.2019.04.228
- Ahmadi E., Weckman G.R., Masel D.T. Decision making model to predict presence of coronary artery disease using neural network and C5.0 decision tree. J. Ambient. Intell. Human Comput. 2017. V. 9(4). P. 999–1011. DOI: 10.1007/s12652-017-0499-z
- Acharya U.R., Sudarshan V.K., Koh J.E.W., et al. Application of higher-order spectra for the characterization of Coronary artery disease using electrocardiogram signals. Biomedical Signal Processing and Control. 2017. V. 31. P. 31–43. DOI: 10.1016/j.bspc.2016.07.003
- Jiang C., Song S., Meng M. Q.-H. Heartbeat classification system based on modified stacked denoisingautoen coders and neuralnetworks. Information and Automation (ICIA). 2017 IEEE International Conference on IEEE. 2017. P. 511–516.
- Yang J., Bai Y., Lin F., Liu M., Hou Z., and Liu X. A novelelectro cardiogram arrhythmia classification method based on stackedsparse auto-encoders and softmax regression. International Journal of Machine Learning and Cybernetics. 2017. P. 1–8.
- Rajpurkar P., Hannun A.Y., Haghpanahi M., Bourn C., Ng A.Y. Cardiologist-level arrhythmia detection with convolutional neuralnetworks. arXiv preprint arXiv:1707.01836. 2017.
- Schwab P., Scebba G. C., Zhang J., Delai M., Karlen W. Beat bybeat: Classifying cardiac arrhythmias with recurrent neural networks. Computing. 2017. V. 44. P. 1.
- Yao Z., Zhu Z., and Chen Y. Atrial fibrillation detection by multiscale convolutional neural networks. Information Fusion (Fusion) 20th International Conference on IEEE. 2017. P. 1–6.
- Xiong P., Wang H., Liu M., Liu X. Denoising autoencoder for eletrocardiogram signal enhancement. Journal of Medical Imaging and Health Informatics. 2015. V. 5. № 8. P. 1804–1810.
- Wu J., Bao Y., Chan S.-C., Wu H., Zhang L., Wei X.-G. Myocardial infarction detection and classification - a new multi-scale deep feature learning approach. Digital Signal Processing (DSP), 2016 IEEE International Conference on. IEEE. 2016. P. 309–313.
- Zubair M., Kim J., Yoon C. An automated ECG beat classification system using convolutional neural networks. IT Convergence and Security (ICITCS), 2016 6th International Conference on. IEEE. 2016. P. 1–5.