The Program of the Cardiovascular Disease Risk Prediction System

The purpose of research is to develop a system for predicting the risks of cardiovascular diseases based on EDF format files and images of cardiac signals.

Methods. To implement the software system, the Python programming language version 3.10 was used. The prediction of the risks of cardiovascular diseases occurs using neural networks, the architecture of which was chosen with the structure of a multilayer perceptron with one hidden layer. When developing the application, the following libraries were used: PyEDFlib, Scikit-learn, SQLite3, PyQtGraph, Pandas, PyWavelets, Scipy, Pillow, OpenCV, Matplotlib. The input data of the program are EDF files and images of cardiac signals in png, jpg, jpeg, bmp and svg formats.

Results. As a result of the development of the software product, the interface and architecture of the program were developed. Two neural networks with a common structure have been developed and trained. Their training was carried out by the method of back propagation of the error. A database has been developed to store information about patients, diseases and thresholds. Algorithms of forecasting, neural network training, division of a cardiac signal into PQRST complexes, reading of a cardiac signal from an image and an EDF file are implemented.

Conclusion. A software system has been developed that allows predicting the risks of cardiovascular diseases, which will allow doctors to speed up the diagnosis of CVD and reduce the time spent on providing medical services to patients, as well as improve the results of managing patients at high risk. In the future, the developed software product can be improved and refined with new functions: adding new ones for the cardiovascular diseases software system and working with them, improving the accuracy of forecasting, improving the quality of reading data from images.

1. Orlov V. N. Rukovodstvo po e'lektrokardiografii [Manual of electrocardiography]. 9th ed. Moscow, Medicinskoe informacionnoe agentstvo Publ., 2017. 560 p.

2. Kisilev A. V., Shatalova O. V., Protasova Z. U., Filist S. A., eds. Modeli latentny'x prediktorov v intellektual'ny'x sistemax prognozirovaniya sostoyaniya zhivy'x system [Models of latent predictors in intelligent systems for predicting the state of living systems]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel'naya tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: Control, Computer Engineering, Information Science. Medical Instruments Engineering, 2020, vol. 10, no. 1, рр. 114-133.

3. Koltun M. A., Sapon K. S. Nekotory'e problemy' avtomatizacii zadach v sfere zdravooxraneniya [Some problems of automation of tasks in the field of healthcare]. Alleya nauki = Alley of Science, 2018, no. 1, рр. 838-840.

4. Tomakova R. A. Programmnoe obespechenie analiza ploxostrukturirovanny'x izobrazhenij v pakete MATLAB dlya medicinskix prilozhenij [Software for the analysis of poorly structured images in the MATLAB package for medical applications]. Ucheny'e zapiski Rossijskogo gosudarstvennogo social'nogo universiteta = Scientific Notes of the Russian State Social University, 2012, no. 2 (102), рр. 350-354.

5. Sheraliev I. I. Informacionny'e texnologii i ix primenenie v sovremennoj medicine [Information technologies and their application in modern medicine]. ACADEMY, 2020, no. 3(54), pp. 861-63.

6. Gudfellou Ya. Glubokoe obuchenie [Forecasting the risk of developing cardiovascular diseases using a fully connected deep neural network]. 2nd ed. Moscow, DMK Press, 2018. 652 р.

7. Enikeeva Z. A., Rafikov D. S. Prognozirovaniya riska razvitiya serdechno-sosudisty'x zabolevanij s pomoshh'yu polnosvyaznoj glubokoj nejronnoj seti [Forecasting the risk of developing cardiovascular diseases using a fully connected deep neural network]. StudNet, 2022, no. 7, рр. 7274-7283.

8. Gusev A. V., Kuzneczova T. Yu., Korsakov I. N. Iskusstvenny'j intellekt v ocenke riskov razvitiya serdechno-sosudisty'x zabolevanij [Artificial intelligence in assessing the risks of developing cardiovascular diseases]. Rossijskij zhurnal telemediciny' i e'lektronnogo zdravooxraneniya = Russian Journal of Telemedicine and E-Health, 2018, no. 3, рр. 85-90.

9. Kisilev A. V., Petrova T. V., Degtyarev S. V., Ry'bochkin A. F., Filist S. A., Shatalova O. V., Mishustin V. N. Nejrosetevy'e moduli s virtual'ny'mi potokami dlya klassifikacii i prognozirovaniya funkcional'nogo sostoyaniya slozhny'x system [Neural network modules with virtual flows for classification and prediction of the functional state of complex systems]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceedings of the Southwest State University, 2018, no. 4 (79), рр. 123-134.

10. Kisilev A. V., Filist S. A., Shatalova O. V. [Method of synthesis of heterogeneous mathematical models for predicting recurrence of myocardial infarction in the rehabilitation period]. Intellektual'no-informacionny'e texnologii i intellektual'ny'j biznes (INFOS-2019). Sbornik materialov desyatoj mezhdunarodnoj nauchno-texnicheskoj konferencii [Intellectual and information technologies and intellectual business (INFOS-2019). Collection of materials of the tenth International Scientific-technical conference]. Vologda, Vologda State University Publ., 2019, рр. 28-31. (In Russ.)

11. Efremov M. A., Filist S. A., Shatalova O. V., eds. Gibridnye nechetki modeli dlya prognozirovaniya vozniknoveniya i oslozhnenii arterial'noi gipertenzii s uchetom energeticheskikh kharakteristik bioaktivnykh tochek [Hybrid fuzzy models for predicting the occurrence and complications of arterial hypertension taking into account the energy characteristics of bioactive points]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel'naya tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: Control, Computer Engineering, Information Science. Medical Instruments Engineering, 2018, vol. 8, no. 4 (29), pp. 104-119.

12. Petrova T. V., Filist S. A., Degtyarev S. V., Kiselev A. V., eds. Prediktory sinkhronnosti sistemnykh ritmov zhivykh sistem dlya klassi-fikatorov ikh funktsional'nykh sostoyanii [Predictors of synchronicity of systemic rhythms of living systems for classifiers of their functional states]. Sistemnyi analiz i upravlenie v biomeditsinskikh sistemakh = System Analysis and Management in Biomedical Systems, 2018, vol. 17, no. 3, pp. 693-700.

13. Tomakova R., Komkov V., Emelianov E., Tomakov V. The use of Fourier Descriptors for the Classification and Analysis of Peripheral blood Smears Image. Applications of Mathematics, 2017, vol. 8, рр. 1563.

14. Dzhulli A. Biblioteka Keras - instrument glubokogo obucheniya. Realizatsiya neironnykh setei s pomoshch'yu bibliotek Theano i tensorFlow [The Keras Library is a deep learning tool. Implementation of neural networks using Theano and TensorFlow libraries]. Moscow, DMK Press, 2019. 448 p.

15. Borisovskij S. A., Brezhneva A. N., Tomakova R. A. Nejrosetevy'e modeli s ierarxicheskim prostranstvom informativny'x priznakov dlya segmentacii ploxostrukturirovanny'x izobrazhenij [Neural network models with a hierarchical space of informative features for segmentation of poorly structured images]. Biomedicinskaya radioe'lektronika = Biomedical Radioelectronics, 2010, no. 2, рр. 49-53.

16. Dzhoshi P. Iskusstvennyi intellekt s primerami na Python [Artificial intelligence with examples in Python]. St. Petersburg, Dialectics Publ., 2019. 448 p.

17. Dyudin M. V., Povalyaev A. D., Podval'ny'j E. S., Tomakova R. A. Metody' i algo- ritmy' konturnogo analiza dlya zadach klassifikacii slozhnostrukturiruemy'x izobrazhenij [Methods and algorithms of contour analysis for classification problems of complex structured images]. Vestnik Voronezhskogo gosudarstvennogo texnicheskogo universiteta = Bulletin of the Voronezh State Technical University, 2014, vol. 10, no. 3-1, рр. 54-59.

18. Tomakova R. A., Filist S. A., Pykhtin A. I. Development and Research of Methods and Algorithms for Intelligent Systems for Complex Structured Images Classification. Journal of Engineering and Applied Sciences, 2017, vol. 12, no. 22, pp. 6039-6041.

19. Lyubanovich B. Prostoj Python. Sovremenny'j stil' programmirovaniya [Simple Python. Modern programming style]. St. Petersburg, Piter Publ., 2021. 592 p.

20. Belik A. G. Proektirovanie i arxitektura programmny'x sistem [Design and architecture of software systems]. Omsk, OmGTU Publ., 2016. 96 р.