O.H.Ya. Al-Hamami1, V.V. Alekseev2
1, 2 Tambov State Technical University (Tambov, Russia)
1 Northern Technical University (Mosul, Iraq)
2 Peoples' Friendship University of Russia named after Patrice Lumumba (Moscow, Russia)

1 omer_h_yahya@ntu.edu.iq

When developing a model for processing cardiovascular data, the problems of the reliability of the diagnostic process and the integrity of biomedical data of patients are relevant. It is important to consider maintaining the privacy of analyzing cardiovascular data since they contain sensitive information about an individual’s health status. Also, it is necessary when implementing diagnosis models to consider the compliance with healthcare regulations such as the Health Insurance Portability and Accountability Act.

The aim of the article is to increase the efficiency of processing cardiovascular data using a novel approach for electrocardiogram-based biometric authorized access using one-dimensional convolutional neural networks to provide reliable access to sensitive cardiovascular information.

Deep neural networks and preprocessing models have been considered. It has been determined how and why they are used in processing cardiovascular data. The types of different neural network layers have been studied. Their differences and properties have been indicated. The principles of modifying the deep convolutional network layers to interpolate the features of electrocardiogram signals have been highlighted, and the tasks of comparing the features vectors have been implemented. Deep neural networks and preprocessing models facilitate the process of creating cardiovascular data processing models that support patient privacy and consider the compliance with healthcare regulations. That allows creating robust models with less cost and complexity by using the same neural network model of processing cardiovascular data to control the access of the model.

The developed model ensures the confidentiality of patient data and the integrity of stored electrocardiogram information.

Al-Hamami O.H.Ya., Alekseev V.V. Neural network model for supporting diagnostic decision-making based on processing electrocardiogram data on the human cardiovascular system. Neurocomputers. 2025. V. 27. № 5. P. 40–47. DOI: https://doi.org/10.18127/ j19998554-202505-05 (in Russian)

1. Razin V.V., Krasnov A.A. Using artificial intelligence in the tasks of disease diagnostics by ECG on the PTB-XL dataset. Path to science: applied mathematics, computer science and information technology. 2023. P. 93–96.
2. Rodionov D.M. i dr. Diagnostika sinusovogo ritma i mertsatel'noj aritmii sredstvami iskusstvennogo intellekta. Problemy informatiki. 2022. № 1 (54). S. 77–88. (in Russian)
3. Okoneshnikova E.F. Modifikatsiya algoritma izvlecheniya priznakov elektrokardiogrammy pri diagnostike aritmii na osnove svertochnoj nejronnoj seti. Magisterskaya dissertatsiya. 2023. (in Russian)
4. Sidorkin A.D. Issledovanie effektivnosti siamskikh nejronnykh setej dlya biometricheskoj autentifikatsii po EKG dlya signalov s neperiodicheskoj serdechnoj aritmiej. Inzhenernyj vestnik Dona. 2023. № 4 (100). S. 142–156. (in Russian)
5. Zorin A.L. i dr. Rassmotrenie protsessa identifikatsii lichnosti po elektrokardiogramme. Nauchnye issledovaniya i innovatsii. 2021. № 1. S. 17–23. (in Russian)
6. Chekhomov I., Al Mashhadani A.F. U-Net with extreme learner approach in retinal vessel image segmentation. IEEE Ural-Siberian Conference on Biomedical Engineering, Radio Electronics and Information Technology (USBEREIT). 2024. P. 322–325.
7. Nemirko A.P., Salem B.M.A., Manilo L.A. Raspoznavanie opasnykh aritmij po skalogrammam EKG. Komp'yuternaya optika. 2024. T. 48. № 1. S. 149–156. (in Russian)
8. Yahya O.H., Alekseev V.V., Lakomov D.V., et al. Deep learning approach for detecting cardiovascular arrhythmias in seven lead ECG signal from Holter. International Journal of Online & Biomedical Engineering. 2023. № 19 (14).
9. Konnova N.S., Safina A.D. Ispol'zovanie nejrosetevykh metodov i atomarnykh funktsij v zadache biometricheskoj autentifikatsii po EKG. Bezopasnye informatsionnye tekhnologii. 2021. S. 165–172. (in Russian)
10. Rahul J., Sora M., Sharma L. Baseline correction of ECG using regression estimation method. 2019 4th International Conference on Internet of Things: Smart Innovation and Usages (IoT-SIU). IEEE. 2019. P. 1–5.
11. Beardsley X.W., Field B., Xiao M. Mean-variance-skewness-kurtosis portfolio optimization with return and liquidity. Communications in Mathematical Finance. 2012. № 1 (1). P. 13–49.
12. Sharma T., Singh A., Raj G., et al. AES vs AES_GCM for data protection: A comprehensive security comparison. 2024 OPJU International Technology Conference (OTCON) on Smart Computing for Innovation and Advancement in Industry 4.0. IEEE. 2024. P. 1–7.
13. Yang Z., Liao W., Wang H., et al. Improved Euclidean distance-based pilot protection for lines with renewable energy sources. IEEE Transactions on Industrial Informatics. 2022. V. 18. № 12. P. 8551–8562.