DEVISING A METHOD FOR PREDICTING A BLOOD PRESSURE LEVEL BASED ON ELECTROCARDIOGRAM AND PHOTOPLETHYSMOGRAM SIGNALS

Savostin A. Tuleshov A. Koshekov K. Savostina G. Largin A.
2022 Technology Center

Eastern-European Journal of Enterprise Technologies
2022 #5 Issue 2-119 62 - 74 pp.

Determining the level of blood pressure (BP) in a non-invasive way and without a sphygmomanometer cuff is of great relevance when conducting continuous monitoring or screening studies. In this regard, a method for predicting BP parameters based on the signals of the photoplethysmogram (PPG) and electrocardiogram (ECG) signals has been developed. It is proposed to use, as informative features, the time of pulse wave propagation (PTT) and a set of calculated pulse parameters of PPG. PTT is defined as the time intervals between the R-wave of the ECG and the corresponding characteristic points on the PPG acquired optically from the finger. As parameters of the PPG pulse, the known characteristics of this signal described in the literature are used, as well as additional informative features selected during the study. In accordance with the above, the tools of machine learning theory were used to construct a classifier model and regression models. The approach described in this paper to determine BP makes it possible to use 10-second ECG signals in any of the 12 common leads and PPG signals from any optical type of sensor. The built model of the classifier detects three levels of BP: low, normal, and high, at the accuracy metric=0.8494. The regression models predict systolic, diastolic, and mean BP parameters in accordance with the requirements of the British Hypertension Society (BHS) standard by the magnitude of the absolute error. The proposed method for assessing the level of BP involves real-time measurements and can be used in the design of measuring equipment for screening studies, as well as in continuous monitoring tasks within the framework of BHS requirements

Bioelectric signals , Blood pressure , Machine learning , Photoplethysmogram , Pulse wave propagation time

Text of the article Перейти на текст статьи

Department of Energetic and Radioelectronics, Manash Kozybayev North Kazakhstan University, Pushkin str.,86, Petropavlovsk, 150000, Kazakhstan
Laboratory of Intelligent Robotic Systems, U. Joldasbekov Institute of Mechanics and Engineering, Shevscenko str.,28, Almaty, 050010, Kazakhstan
Department of Science and International Cooperation, Academy Civil Aviation, Akhmetova str.,44, Almaty, 050039, Kazakhstan

Department of Energetic and Radioelectronics
Laboratory of Intelligent Robotic Systems
Department of Science and International Cooperation

10 лет помогаем публиковать статьи Международный издатель

Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026