TY - JOUR
T1 - Personalized Continuous Blood Pressure Tracking through Single channel PPG in Wearable Scenarios
AU - Zhang, Yiming
AU - Zhou, Congcong
AU - Ren, Xianglin
AU - Wang, Qing
AU - Wang, Hongwei
AU - Xiang, Ting
AU - Qiu, Shirong
AU - Zhang, Yuan-Ting
AU - Ye, Xuesong
PY - 2025/1/28
Y1 - 2025/1/28
N2 - The real-time tracking of human physiopathology states can significantly enhance the quality of personalized healthcare services. Photoplethysmography (PPG) detection is a rapid, portable and non-invasive method for measuring blood flow volume, widely used for monitoring blood pressure (BP) and cardiovascular status. However, continuous BP monitoring technologies based on PPG face numerous challenges in real-world wearable scenarios, such as poor signal quality, complex model computation, and the need for frequent calibration. This work proposed a personalized continuous BP tracking pipeline that performed automatic PPG signal quality grading to reduce the difficulty of model fitting, introduced a lightweight BP model (SCI-GTCN) to alleviate computational complexity, and employed an adaptive calibration strategy to achieve long-term BP monitoring performance under different scenarios. The proposed pipeline was validated using data from 134 subjects in various monitoring scenarios (daytime, nighttime, and abnormal states), assessing the model's performance during rapid BP changes, circadian rhythm fluctuations, and long-term monitoring. The ME±SD was 0.99±7.91-0.36±5.43 mmHg. Overall, the results of our method are within the accuracy requirements of the Association for the Advancement of Medical Instrumentation (AAMI) standards, though the subject distribution differs. The method demonstrated good robustness and applicability, making it convenient for deployment on wearable devices and promising in the healthcare field. © 2025 IEEE.
AB - The real-time tracking of human physiopathology states can significantly enhance the quality of personalized healthcare services. Photoplethysmography (PPG) detection is a rapid, portable and non-invasive method for measuring blood flow volume, widely used for monitoring blood pressure (BP) and cardiovascular status. However, continuous BP monitoring technologies based on PPG face numerous challenges in real-world wearable scenarios, such as poor signal quality, complex model computation, and the need for frequent calibration. This work proposed a personalized continuous BP tracking pipeline that performed automatic PPG signal quality grading to reduce the difficulty of model fitting, introduced a lightweight BP model (SCI-GTCN) to alleviate computational complexity, and employed an adaptive calibration strategy to achieve long-term BP monitoring performance under different scenarios. The proposed pipeline was validated using data from 134 subjects in various monitoring scenarios (daytime, nighttime, and abnormal states), assessing the model's performance during rapid BP changes, circadian rhythm fluctuations, and long-term monitoring. The ME±SD was 0.99±7.91-0.36±5.43 mmHg. Overall, the results of our method are within the accuracy requirements of the Association for the Advancement of Medical Instrumentation (AAMI) standards, though the subject distribution differs. The method demonstrated good robustness and applicability, making it convenient for deployment on wearable devices and promising in the healthcare field. © 2025 IEEE.
KW - continuous blood pressure
KW - deep learning
KW - Real-world application
KW - single-channel PPG
KW - wearable scenarios
UR - http://www.scopus.com/inward/record.url?scp=85217065136&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85217065136&origin=recordpage
U2 - 10.1109/JBHI.2025.3535788
DO - 10.1109/JBHI.2025.3535788
M3 - RGC 21 - Publication in refereed journal
SN - 2168-2194
JO - IEEE Journal of Biomedical and Health Informatics
JF - IEEE Journal of Biomedical and Health Informatics
ER -