Cuffless Blood Pressure Estimation Using Calibrated Cardiovascular Dynamics in the Photoplethysmogram

Abstract

An important means for preventing and managing cardiovascular disease is the non-invasive estimation of blood pressure. There is particular interest in developing approaches that provide accurate cuffless and continuous estimation of this important vital sign. This paper proposes a method that uses dynamic changes of the pulse waveform over short time intervals and calibrates the system based on a mathematical model that relates reflective PTT (R-PTT) to blood pressure. An advantage of the method is that it only requires collecting the photoplethysmogram (PPG) using one optical sensor, in addition to initial non-invasive measurements of blood pressure that are used for calibration. This method was applied to data from 30 patients, resulting in a mean error (ME) of 0.59 mmHg, a standard deviation of error (SDE) of 7.07 mmHg, and a mean absolute error (MAE) of 4.92 mmHg for diastolic blood pressure (DBP) and an ME of 2.52 mmHg, an SDE of 12.15 mmHg, and an MAE of 8.89 mmHg for systolic blood pressure (SBP). These results demonstrate the possibility of using the PPG signal for the cuffless continuous estimation of blood pressure based on the analysis of calibrated changes in cardiovascular dynamics, possibly in conjunction with other methods that are currently being researched.

A PPG-Based Calibration-Free Cuffless Blood Pressure Estimation Method Using Cardiovascular Dynamics

“…Figure 1 shows a high-level flowchart for the proposed methodology for cuffless blood pressure estimation, which uses information related to cardiovascular dynamics and morphology, both derived from a PPG signal recorded with a single sensor. Information related to cardiovascular dynamics is extracted based on our previous work [11], and the ones related to PPG morphology are inspired by the proposed methodologies in two previous studies [10,20]. This figure shows a general design that is used during the design development and evaluation, as well as the testing phase with new data.…”

“…In recent years, cuffless blood pressure measurement methods, a generic term for blood pressure monitoring techniques that do not use a cuff, have seen increased interest due to limitations that other methods impose such as discomfort, inconvenience, high cost, complexity and lack of ability to provide continuous measurement [11]. One of the approaches that is used by many for this purpose is based on the pulse transit time (PTT), which corresponds to the time delay for a pulse wave to travel from one arterial site to another.…”

“…Studies have shown that there are similarities between PPG and the arterial blood pressure (ABP) waveform in terms of morphology [16] and dynamics [17], and therefore, extracted features from PPG will carry valuable information regarding the BP [16]. Features that are mostly generated from pulse morphology within individual beats are most commonly used in various machine learning models to estimate blood pressure [11]. Sulochana [18] provides a recent review of PPG-based methods that have been used in different studies.…”

“…In previous work, we investigated BP estimation based on information from dynamic changes in PPG signal while a mathematical model was used for calibration stage [11]. In this work, we investigated the possibility of replacing the calibration stage with information from PPG morphology in order to provide a calibration-free method for BP estimation.…”

Cuff-Less Blood Pressure Prediction Based on Photoplethysmography and Modified ResNet

“…Thus, the PPG signal contains a considerable amount of cardiovascular physiological information, and it has been adopted to evaluate a wide variety of physiological parameters (e.g., blood oxygen, heart rate, respiratory rate, and blood glucose) [ 9 , 10 , 11 , 12 ]. Furthermore, PPG has been studied in the field of continuous blood pressure measurement [ 13 , 14 ]. Existing research has suggested that the PPG signal contains factors related to blood pressure, and it is a promising candidate for continuous blood pressure estimation.…”