Non-Contact Blood Pressure Monitoring Using Radar Signals: A Dual-Stage Deep Learning Network.

Abstract

Emerging radar sensing technology is revolutionizing cardiovascular monitoring by eliminating direct skin contact. This approach captures vital signs through electromagnetic wave reflections, enabling contactless blood pressure (BP) tracking while maintaining user comfort and privacy. We present a hierarchical neural framework that synergizes spatial and temporal feature learning for radar-driven, contactless BP monitoring. By employing advanced preprocessing techniques, the system captures subtle chest wall vibrations and their second-order derivatives, feeding dual-channel inputs into a hierarchical neural network. Specifically, Stage 1 deploys convolutional depth-adjustable lightweight residual blocks to extract spatial features from micro-motion characteristics, while Stage 2 employs a transformer architecture to establish correlations between these spatial features and BP periodic dynamic variations. Drawing on the intrinsic link between systolic (SBP) and diastolic (DBP) blood pressures, early estimates from Stage 2 are used to expand the feature set for the second-stage network, boosting its predictive power. Validation achieved clinically acceptable errors (SBP: -1.09 ± 5.15 mmHg, DBP: -0.26 ± 4.35 mmHg). Notably, this high degree of accuracy, combined with the ability to estimate BP at 2 s intervals, closely approximates real-time, beat-to-beat monitoring, representing a pivotal breakthrough in non-contact BP monitoring.