Dynamic Beat-to-Beat Blood Pressure Estimation using a Multi-modal Wearable Deep Learning Approach.

Cuffless blood pressure (BP) monitoring technologies, primarily based on pulse transit time (PTT) or photoplethysmography (PPG), frequently suffer from calibration drift due to their reliance on blood volume surrogates rather than direct pressure measurement. To address this physiological limitation, this study presents a multi-modal deep learning framework that integrates superficial temporal artery tonometry (STAT), which captures high-fidelity pressure waveform morphology, with electrocardiography (ECG) and PPG signals. Approach: A custom wearable device was developed to simultaneously acquire these signals during dynamic perturbations. Extracted features included heart rate (HR) from ECG, PTT from ECG-PPG pairs, and BP-related metrics derived from PTT and STAT. Signal quality indices for ECG, PPG, and STAT signals were also computed to assess signal reliability. A temporal convolutional network (TCN) model was designed to capture the complex, non-linear dependencies between these multi-modal features and beat-to-beat BP. Main results: The approach was rigorously validated using Leave-One-Subject-Out Cross-Validation (LOSOCV) on 29 recordings from ten healthy volunteers undergoing isometric handgrip exercises. The proposed TCN model significantly outperformed traditional PTT and STAT-only baselines, achieving a Mean Absolute Difference (MAD) of 5.58 mmHg for Systolic BP (SBP), 4.39 mmHg for mean BP (MBP) and 4.34 mmHg for diastolic BP (DBP). Notably, the TCN model exhibited significantly lower errors (p < 0.05, Wilcoxon Test) during dynamic BP fluctuations compared to baseline models. Significance: The study demonstrates that fusing tonometry-derived pressure morphology with hemodynamic timing features effectively mitigates the limitations of conventional PTT methods. This approach offers a robust solution for continuous, calibration-resilient BP estimation. .