E. A. Denisova1, A. A. Kordyukova2, D. O. Shevyakov3, B. S. Gurevich4

1–4 Institute for Analytical Instrumentation of the Russian Academy of Sciences (St. Petersburg, Russia)
1 tiranderel@yandex.ru, 2 annygm00@mail.ru, 3 sevakovdaniil@gmail.com, 4 bgurevich48@gmail.com

The development of modern technologies and the tendency to increase the information content of electrocardiosignals (ECS) for the early diagnosis of cardiac ischemia has led to the development of a new method of ultra-high resolution electrocardiography (UHR ECG), the main feature of which is the expansion of the amplitude and frequency ranges of recording and recording ECG data. Known standard methods are ineffective for processing UHR ECS. This determines the need to improve and expand the range of technologies used to detect early signs of the development of cardiac pathologies using UHR ECG to obtain additional diagnostic information about the functional state of a biological object.

The aim of the study is to develop a decision-making system for the presence of early signs of acute myocardial infarction based on UHR ECS in experiments on rats using neural network technologies. To achieve this goal, a scientific substantiation was carried out for the possibility of assessing the likelihood of developing myocardial infarction at an early stage using UHR ECS obtained in experiments on rats using neural network technologies. The structure of the decision-making system on the presence of early signs of acute myocardial infarction has been developed.

The use of the developed concept of building a decision-making system on the presence of early signs of acute myocardial infarction in experiments on rats is the basis for creating a new generation of medical models that provide the ability to obtain diagnostic data on early signs of pathology using the new method of UHR ECG.

Denisova E.A., Kordyukova A.A., Shevyakov D.O., Gurevich B.S. A decision-making system for the presence of early signs of acute myocardial infarction in experiments on rats. Biomedicine Radioengineering. 2025. V. 28. № 5. P. 154–157. DOI: https://doi.org/10. 18127/j15604136-202505-31 (In Russian)

1. Virani S. American Heart Association Council on Epidemiology and Prevention Statistics Committee and Stroke Statistics Subcommittee. Heart Disease and Stroke Statistics-2020. Circulation. 2020. V. 141. № 9. P. 139–596.
2. Gulyaev Y. Ultra-high resolution electrocardiography. Tasks. Problems. The prospects. Biomed. Radioelectron. 2013. V. 9. P. 5–15.
3. Zaichenko K., Afanasenko A., Denisova E., Kordyukova A., Shevyakov D. Utilizing the convolutional neural network AlexNet to classify ultra-high resolution Electrocardiosignals. Physics and Mathematics. 2024. V. 17. P. 292–296.
4. Zaichenko K., Kordyukova A., Sonin D., Galagudza M. Ultra-High-Resolution Electrocardiography Enables Earlier Detection of Transmural and Subendocardial Myocardial Ischemia Compared to Conventional Electrocardiography. Diagnostics (Basel). 2023. V. 13. P. 2795.
5. Jurak P., Halamek J., Leinveber P. Ultra-highfrequency ECG measurement. Computing in Cardiology. 2013. V. 40. P. 783–786.