Cuff-less methods, especially pulse wave analysis (PWA) techniques with PPG/mmWave sensing, have shown great potential for non-intrusive blood pressure (BP) monitoring. However, the state-of-the-art solutions are only validated on small-scale healthy subjects, neglecting patients with abnormal BP and thus a more urgent need for BP monitoring. To bridge the gap, we first build the largest mmWave-BP dataset to our knowledge, including 930 real patients with cardiovascular diseases, and perform extensive experiments, which reveals that all existing PWA methods exhibit far less satisfactory performance with standard deviation errors (STD) exceeding 16 mmHg for systolic BP (SBP) and 11mmHg for diastolic BP (DBP). An in-depth investigation shows that physiological factors have complex effect on vascular elasticity and structure, thus people with very different BP values may exhibit extremely similar pulse waveform, which leads to confusion in model learning. In this work, we propose BP3, which fuses physiological factors into sensing-data-driven deep-learning framework, so as to capture the intricate effect of physiological factors during the whole process of learning pulse waveforms. Evaluation results show that BP3 achieves the mean errors of-1.57 mmHg and -0.34 mmHg, STD of 9.77 mmHg and 7.93 mmHg for SBP and DBP, respectively. Moreover importantly, BP3 shows remarkable gain particularly for subjects with abnormal BP, achieving mean errors that are only 0.48% ~ 20.86% of the state-of-the-art solutions.

This study proposes a linear time-invariant (LTI) system based assessment approach for coronary heart disease (CHD) risk. Unlike traditional risk regression models, the new approach considers accumulated effects of CHD factors with time and can thus perform time-based simulation and real time assessment for the progression of coronary heart disease. There are several LTI-based models achieved in this study via black box system identification process on a 1,549-men cohort. These models have good fitting on the sample data and can adequately reproduce results of the current dominant risk models. Our findings verified that the LTI-based modeling approach works for time-based CHD assessment — such models can be used for time-based simulation and real time evaluation if sufficient sample data is observed.