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

Abstract

This paper presents a novel blood pressure (BP) estimation method based on pulse transit time (PTT) and pulse arrival time (PAT) to estimate the systolic blood pressure (SBP) and diastolic blood pressure (DBP). A data acquisition hardware is designed for high-resolution sampling of phonocardiogram (PCG), photoplethysmogram (PPG) and electrocardiogram (ECG). PCG and ECG perform as the proximal timing reference to obtain PTT and PAT indexes, respectively. In order to derive a BP estimator model, a calibration procedure including a supervised physical exercise is conducted for each individual which causes changes in their BP and then, a number of reference BPs are measured alongside the acquisition of the signals per subject. It is suggested to use a force-sensing resistor (FSR) that is placed under the cuff of the BP reference device to mark the exact moments of reference BP measurements, which are corresponding to the inflation of the cuff. Additionally, a novel BP estimator nonlinear model, based on the theory of elastic tubes, is introduced to estimate the BP using PTT/PAT values precisely. The proposed method is evaluated on 32 subjects. Using the PTT index, the correlation coefficients for SBP and DBP estimation are 0.89 and 0.84, respectively. Using the PAT index, the correlation coefficients for SBP and DBP estimation are 0.95 and 0.84, respectively. The results show that the proposed method, exploiting the introduced nonlinear model with the use of PAT index or PTT index, provides a reliable estimation of SBP and DBP.Index Terms-cuff-less blood pressure, mobile health (mHealth), pulse transit time (PTT), pulse arrival time (PAT), vital signals

Unobtrusive Measurement of Blood Pressure During Lifestyle Interventions

“…In this paper we could show that features derived from the photoplethysmography (PPG) signal have potential to be used as estimators for blood pressure since our MAE for systolic blood pressure (4.05) was lower than the best one reported by Esmaili et al [3] (4.71) using non-linear equations and it is closer to the one found by Kurylyak et al [8] (3.8) using neural networks. Moreover, even without doing an extensive search on the hyperparameters of GBM it already produces decent prediction results.…”

“…As next steps, firstly we will execute the short and long protocols in a new group of healthy subjects for testing Mobil-o-Graph ® . Secondly, we will train and test models again with new data such as the one made available by Esmaili et al [3] 4 and we intend to test new features from both the ECG and PPG signals.…”

“…The second objective is to apply different methods to estimate BP using features extracted from PPG and ECG signals. There is evidence in literature that measures such as systolic upstroke time (SUT) and pulse arrival time (PAT) can be good predictors of systolic blood pressure (SBP) and diastolic blood pressure (DBP) [3,8].…”

“…For this experiment we selected the following devices: Faros TM 180, a chest ECG from Bittium 1 , Empatica 2 's wristband E4 and Everion, an armband from Biovotion 3 . The sensors present in each device are described in Table 1 together with their sampling frequency range.…”

Wearable Sensing and Telehealth Technology with Potential Applications in the Coronavirus Pandemic

“…The advantage of this method is that the R-peak of the ECG signal is easy to detect, especially during resting conditions. Several studies use alternative cardiac signals for ECG, such as impedance plethysmography (IPG) [99,100], phonocardiogram (PCG) [101,102], or ballistocardiogram (BCG) [103,104]. To improve the user comfort, a peripheral PTT-based multi-wavelength method has been proposed using two or multiple PPG sensors [105][106][107].…”