ReBP: Short-Term Blood Pressure Estimation by Reconstructing PPG Signals Based on mmWave Radar

Noncontact blood pressure (BP) monitoring offers significant potential for healthcare applications due to its convenience and comfort. However, existing methods often require prolonged signal acquisition to ensure accuracy, limiting real-time monitoring capabilities. This article proposes reconstructed BP (ReBP), a millimeter-wave radar-based system for photoplethysmogram (PPG) signal reconstruction and BP estimation, achieving high accuracy with short-duration inputs. ReBP integrates four modules: data acquisition, signal processing, waveform reconstruction, and BP estimation. First, pulse signals from wrist vasculature are captured via millimeter-wave (mmWave) radar. Then, an adaptive filtering algorithm enhances periodic characteristics by selecting segments with maximal autocorrelation. Subsequently, a cycle-consistent generative adversarial network (CycleGAN), augmented with a PPG-AWARE loss function, reconstructs PPG waveforms enriched with vascular dynamics. Finally, for BP estimation, a multifeature fusion network extracts temporal, spectral, and global features via the ResNet, gated recurrent units (GRUs), and SpectrogramLSTM, fused through a cross-modal attention mechanism. Implemented on a TI IWR6843 radar platform, ReBP was validated with 26 participants, achieving mean absolute errors (MAEs) of 3.891 [systolic BP (SBP)] and 3.646 mmHg [diastolic BP (DBP)] for 35-s inputs, 4.003 (SBP) and 3.873 mmHg (DBP) for 15-s inputs, and 4.383 (SBP) and 4.115 mmHg (DBP) for 5-s inputs, outperforming conventional methods in short-sequence scenarios.