DOI: 10.17587/prin.15.199-205

Regression and Neural Network Analysis of the System of Cardiorespiratory Synchronism Parameters to Predict the Minimum Limit of the Synchronization Range

O. V. Rudenko, Ph.D. in Engineering Science, Associate Professor, olga_ned@mail.ru, Kuban State University, Krasnodar, 350040, Russian Federation, T. V. Shkirya, Programmer, shkiryatv@yandex.ru, Kuban State Medical University, Krasnodar, 350063, Russian Federation

Corresponding author: Tatyana V. Shkirya, Programmer, Kuban State Medical University, 350063, Krasnodar, Russian Federation, E-mail: shkiryatv@yandex.ru

In order to improve the existing step-by-step principle of determining the limits of the range of cardiorespiratory synchronization (CRS) and the regulatory and adaptive capabilities of the human body, a regression analysis of measurements of the CRS parameters system was carried out. Statistical prediction of the minimum limit of the synchronization range in the CRS method was performed using linear, nonlinear multiple regression models, as well as neural network regression. The following parameters were used as the basis for predicting the minimum limit of the synchronization range: initial heart rate, initial respiratory rate, age and gender. The variable initial heart rate contributed the most to all regression models. A comparative analysis of the quality indicators of all models showed that the prediction of the minimum limit of the synchronization range can be carried out both by linear multiple regression and using neural network regression implemented by means of a 3-4-1 multilayer perceptrons. However, having already had a NN-regression forecast of maximum limit of the synchronization range, as well as a NN-classification of the level of regulatory-adaptive status, the use of NN-regression will be proposed as the main forecasting method for its implementation in the software of the CRS measurement system.

Keywords: neural network, regression analysis, simulation, cardiorespiratory synchronization, neural network sensitivity analysis, statistical prediction, linear regression, nonlinear regression, initial heart rate, minimum limit of the synchronization range

pp. 199–205

For citation:
Rudenko O. V., Shkirya T. V. Regression and Neural Network Analysis of the System of Cardiorespiratory Synchronism Parameters to Predict the Minimum Limit of the Synchronization Range, Programmnaya Ingeneria, 2024, vol. 15, no. 4, pp. 199-205. DOI: 10.17587/prin.15.199-205 (in Russian).

References:

• Ren Y., Zhang J. Increased cardiorespiratory synchronization evoked by a breath controller based on heartbeat detection, BioMed Eng OnLine, 2019, vol. 18, no. 1, article 61. DOI: 10.1186/s12938-019-0683-9.
• Pokrovskii V. М. Cardiorespiratory synchronism used for estimation of regulatory-adaptive possibilities of organism. Krasnodar, Kuban-Kniga, 2010, 243 р. (in Russian).
• Noskin L. A., Rubinskiy A. V., Romanchuk A. P. et al. Study of cardiovascular and respiratory synchronization in different types of breathing, Pathogenesis, 2018, vol. 16, no. 4, pp. 90-96 (in Russian).
• Pokrovsky V. M., Usatikov S. V., Shkirya T. V., Polishchuk L. V. Statistical forecasting in the creation of an express methodology for determining the level of regulatory-adaptive status of the human body, Kub. Scientific Medical Bulletin, 2014, no. 6, pp. 65-70 (in Russian).
• Pokrovsky V. M., Usatikov S. V., Shkirya T. V., Polishchuk L. V. Statistical forecasting of the maximum limit of the cardiorespiratory synchronization range, Kub. Scientific Medical Bulletin, 2015, no. 3, pp. 83-87. DOI: 10.25207/1608-6228-2015-3-83-87 (in Russian).
• Usatikov S. V., Shkirya T. V. Algorithms for a decision support system when assessing the regulatory and adaptive capabilities of the human body using a hardware and software appliance, Scientific Works of the Kuban State Technological University, 2016, no. 16, pp. 20-24 (in Russian).
• Polishchuk V. V., Shkirya T. V., Polishchuk S. V., Pokrovsky V. M. Program for determining the parameters of cardiorespiratory synchronization in humans / Certificate of official registration of computer program No. 2021611568 Russian Federation. Appl. 11.01.2021; reg. 01.02.2021. 1 p.