Cuff-less high-accuracy calibration-free blood pressure estimation using pulse transit time

Abstract

Recently a few methods have been proposed in the literature for non-invasive cuff-less estimation of systolic and diastolic blood pressures. One of the most prominent methods is to use the Pulse Transit Time (PTT). Although it is proven that PTT has a strong correlation with the systolic and diastolic blood pressures, this relation is highly dependent to each individuals physiological properties. Therefore, it requires per person calibration for accurate and reliable blood pressure estimation from PTT, which is a big drawback. To alleviate this issue, in this paper, a novel method is proposed for accurate and reliable estimation of blood pressure that is calibration-free. This goal is accomplished by extraction of several physiological parameters from Photoplethysmography (PPG) signal as well as utilizing signal processing and machine learning algorithms. The results show that the accuracy of the proposed method achieves grade B for the estimation of the diastolic blood pressure and grade C for the estimation of the mean arterial pressure under the standard British Hypertension Society (BHS) protocol.978-1-4799-8391-9/15/$31.00 ©2015 IEEE

Continuous Blood Pressure Measurement From Invasive to Unobtrusive: Celebration of 200th Birth Anniversary of Carl Ludwig

“…Machine learning methods such as linear regression, neural network, Bayesian network, and support vector machine can be used to develop the BP model. [99]. Overall, existing BP models using machine learning methods demonstrate promising estimation accuracy [105]; however, the potential mechanism behind the patterns should be further studied.…”

“…With the ever-increasing computational power and development of big data technology, big data analysis using the machine learning method for cuffless BP measurement has gained increasing attention [99][100][101][102][103]. The general idea with this technique is to initially extract surrogate cardiovascular indexes from physiological signals, then use machine learning to train this data to adapt to the system, and finally predict BP using the trained model.…”

Nonlinear Cuffless Blood Pressure Estimation of Healthy Subjects Using Pulse Transit Time and Arrival Time

“…Usually, in the literature, electrocardiogram (ECG) is used as a proximal timing reference and the photoplethysmogram (PPG) is used as a distal timing reference for PTT measurement [7], [8], [9], [10] [11]. However, using ECG and PPG signals leads to the measurement of another cardiovascular parameter that is pulse arrival time (PAT).…”

Blood pressure estimation from photoplethysmogram and electrocardiogram signals using machine learning

“…Other cuff-less blood pressure estimation designs in literature, such as using PTT alone to predict blood pressure, suffer from different drawbacks such as requiring calibration for each person. Table 4 gives continuous, cuff-less blood pressure measurement method results obtained by Kachuee et al in 2015 [16]. In their research, blood pressure was estimated by extracting several morphological features from the PPG signal, and then applying signal processing and machine learning algorithms.…”

“…This study aims to explore whether the combination of PTT with both PPG and ECG features can improve the accuracy of the prediction of blood pressure, compared with a study based on the combination of PTT with PPG features only [16]. The implemented flowchart is shown in Fig.1, containing two main phases -data collection and signal analysis.…”