10.14489/td.2026.10.pp.054-065

2026, 10 October

DOI: 10.14489/td.2026.10.pp.054-065

Golunov A. S.
A COMPLEX MODEL FOR PREDICTING BLOOD PRESSURE BASED ON PHYSIOLOGICAL AND BEHAVIORAL DATA
(pp. 54-65)

Abstract. The article presents a mathematical model of blood pressure (BP) designed to predict and analyze the influence of physiological and behavioral factors on systolic (SBP) and diastolic (DBP) pressure. The model takes into account a wide range of parameters, including age, sleep quality and duration, physical activity level, stress, anthropometric data, heart rate (HR), step count, and the presence of sleep disorders. Several algorithms were tested, including linear regression, Lasso, Ridge, Random Forest, and Gradient Boosting. The Ridge Regression model demonstrated the best results, showing a mean absolute error of 6.56 mm Hg for SBP and 7.13 mm Hg for DBP. The relevance of the study is due to the need for a complex approach to BP assessment, which complements existing non-invasive methods based mainly on the analysis of physiological signals, with lifestyle data. The aim of the work is to develop a mathematical model that takes into account individual human characteristics. The scientific novelty of the study lies in the proposal of a new method for assessing blood pressure, which allows for expanded capabilities for monitoring the state of the cardiovascular system.

Keywords: blood pressure, cuff-free methods, linear regression, mathematical model, machine learning, personalized assessment.

+ - About the Authors Click to collapse

A. S. Golunov (Sarov Institute of Physics and Technology, Sarov, Russia) E-mail: Данный адрес e-mail защищен от спам-ботов, Вам необходимо включить Javascript для его просмотра.

+ - References Click to collapse

1. Escobar, B., & Torres, R. (2014). Feasibility of non-invasive blood pressure estimation based on pulse arrival time: A MIMIC database study. In Computing in Cardiology (pp. 1113–1116).
2. Kachuee, M., Kiani, M. M., Mohammadzade, H., et al. (2015). Cuff-less high-accuracy calibration-free blood pressure estimation using pulse transit time. In IEEE International Symposium on Circuits and Systems (ISCAS) (pp. 1006–1009). https://doi.org/10.1109/ISCAS.2015.7168806
3. Feng, J., Huang, Z., Congcong, Z., & Ye, X. (2018). Study of continuous blood pressure estimation based on pulse transit time, heart rate and photoplethysmography derived hemodynamic covariates. Australasian Physical & Engineering Sciences in Medicine, 41(2), 403–413. https://doi.org/10.1007/s13246-018-0637-8
4. Wang, J., Yeh, M.-H., Chao, P., et al. (2020). A fast digital chip implementing a real-time noise-resistant algorithm for estimating blood pressure using a non invasive, cuffless PPG sensor. Microsystem Technologies, 26(3), 3501–3516. https://doi.org/10.1007/s00542-020-04946-y
5. Kyung, J., Yang, J.-Y., Choi, J. H., et al. (2023). Deep-learning-based blood pressure estimation using multi-channel photoplethysmogram and finger pressure with attention mechanism. Scientific Reports, 13(1), Article 9311. https://doi.org/10.1038/s41598-023-36068-6
6. Topouchian, J., Hakobyan, Z., Asmar, J., et al. (2018). Clinical accuracy of the Omron M3 Comfort and the Omron Evolv for self-blood pressure measurements in pregnancy and pre-eclampsia – validation according to the Universal Standard Protocol. Vascular Health and Risk Management, 14, 189–197. https://doi.org/10.2147/VHRM.S165524

+ - Purchase digital version of a single article Click to collapse

This article is available in electronic format (PDF).

DOI: 10.14489/td.2026.10.pp.054-065

Copy the article DOI and follow the link https://id-spektr.ru/product/pokupka-elektronnoy-stati-iz-zhurnala-kontrol-diagnostika

Please specify the article DOI in the order comments.