Noncontact Blood Pressure Estimation Using BP-Related Cardiovascular Knowledge: An Uncalibrated Method Based on Consumer-Level Camera

Objective: The tiny change of skin color, caused by a heartbeat, can be captured with consumer-level cameras by using the imaging photoplethysmography (iPPG) technique, offering a noncontact way of extracting pulse signals. Pulse signals have been demonstrated to contain information on human physiological characteristics and have been used for blood pressure (BP) estimation in recent years. According to BP-related cardiovascular knowledge, this article presents a new method for BP estimation based on the iPPG pulse signals, featured by incorporating cardiovascular characteristics including heart rate (HR), stroke volume (SV), the elasticity of vessel walls (EVW), and peripheral vascular resistance (PVR). Correlations between the systolic BP (SBP), diastolic BP (DBP), pulse pressure (PP), and cardiovascular characteristics are extracted, which facilitates the selection of pulse features consistent with BP properties. Based on the selected features, two Bayesian neural network (BNN) models are constructed for the estimation of SBP and DBP, respectively, where the machine learning (ML) uncertainty of the estimation is also evaluated. This method is uncalibrated which means it can work without additional information except for the videos from the camera. The proposed method has been tested on 220 patients with a history of cardiovascular diseases. Errors of the BP estimation are 9 +/- 13 (MAE +/- STD) mmHg for SBP, 7 +/- 10 (MAE +/- STD) mmHg for DBP, and the ML uncertainty of the estimation indicates the reliability of the proposed method.

Automated summary

The article introduces a new method for estimating blood pressure based on the iPPG pulse signals, which captures the tiny change of skin color caused by a heartbeat using consumer-level cameras. It incorporates cardiovascular characteristics such as heart rate, stroke volume, the elasticity of vessel walls, and peripheral vascular resistance. Bayesian neural network models are constructed for the estimation of systolic and diastolic blood pressure, and the machine learning uncertainty is evaluated. The uncalibrated method has been tested on 220 patients with a history of cardiovascular diseases, demonstrating its reliability with low estimation errors.