A KAIST research team led by Professor Keon Jae Lee has proposed an innovative theoretical framework and research strategies for AI-based wearable blood pressure sensors, paving the way for continuous and non-invasive cardiovascular monitoring.
Hypertension is a leading chronic disease affecting over a billion people worldwide and is a major risk factor for severe cardiovascular conditions such as myocardial infarction, stroke, and heart failure. Traditional blood pressure measurement relies on intermittent, cuff-based methods, which fail to capture real-time fluctuations and present challenges in continuous patient monitoring.
Wearable blood pressure sensors offer a non-invasive solution for continuous blood pressure monitoring, enabling real-time tracking and personalized cardiovascular health management. However, current technologies lack the accuracy and reliability required for medical applications, limiting their practical use. To address these challenges, advancements in high-sensitivity sensor technology and AI signal processing algorithms are essential.
Building on their previous study in Advanced Materials (doi.org/10.1002/adma.202301627), which validated the clinical feasibility of flexible piezoelectric blood pressure sensors, Professor Lee's team conducted an in-depth review of the latest advancements in cuffless wearable sensors, focusing on key technical and clinical challenges. Their review highlights clinical aspects of clinical implementation, real-time data transmission, signal quality degradation, and AI algorithm accuracy.
This paper systematically demonstrates the feasibility of medical-grade wearable blood pressure sensors, overcoming what was previously considered an insurmountable challenge. We propose theoretical strategies to address technical barriers, opening new possibilities for future innovations in this field. With continued advancements, we expect these sensors to gain trust and be commercialized soon, significantly improving quality of life."
Professor Keon Jae Lee, KAIST
Source:
KAIST (Korea Advanced Institute of Science and Technology)
Journal reference:
Min, S., et al. (2025). Wearable blood pressure sensors for cardiovascular monitoring and machine learning algorithms for blood pressure estimation. Nature Reviews Cardiology. doi.org/10.1038/s41569-025-01127-0.
