Combined deep CNN–LSTM network-based multitasking learning architecture for noninvasive continuous blood pressure estimation using difference in ECG-PPG features

AbstractThe pulse arrival time (PAT), the difference between the R-peak time of electrocardiogram (ECG) signal and the systolic peak of photoplethysmography (PPG) signal, is an indicator that enables noninvasive and continuous blood pressure estimation. However, it is difficult to accurately measure PAT from ECG and PPG signals because they have inconsistent shapes owing to patient-specific physical characteristics, pathological conditions, and movements. Accordingly, complex preprocessing is required to estimate blood pressure based on PAT. In this paper, as an alternative solution, we propose a noninvasive continuous algorithm using the difference between ECG and PPG as a new feature that can include PAT information. The proposed algorithm is a deep CNN–LSTM-based multitasking machine learning model that outputs simultaneous prediction results of systolic (SBP) and diastolic blood pressures (DBP). We used a total of 48 patients on the PhysioNet website by splitting them into 38 patients for training and 10 patients for testing. The prediction accuracies of SBP and DBP were 0.0 ± 1.6 mmHg and 0.2 ± 1.3 mmHg, respectively. Even though the proposed model was assessed with only 10 patients, this result was satisfied with three guidelines, which are the BHS, AAMI, and IEEE standards for blood pressure measurement devices.

Download Full-text

Combined Deep CNN–LSTM Network-based Multitasking Learning Architecture for Noninvasive Continuous Blood Pressure Estimation using Difference in ECG-PPG Features

10.21203/rs.3.rs-137994/v1 ◽

2021 ◽

Author(s):

Da Un Jeong ◽

Ki Moo Lim

Keyword(s):

Blood Pressure ◽

Pulse Transit Time ◽

Patient Specific ◽

Peak Time ◽

Simultaneous Prediction ◽

Deep Cnn ◽

Pressure Estimation ◽

The Difference ◽

Blood Pressure Estimation ◽

Continuous Blood Pressure

Abstract The pulse transit time (PTT), which is the difference between the R-peak time of the electrocardiogram (ECG) signal and the systolic peak of the photoplethysmography (PPG) signal, is an indicator that enables noninvasive and continuous blood pressure estimation. However, it is difficult to accurately measure the PTT from the ECG and PPG signals because they have inconsistent shapes owing to patient-specific physical characteristics, pathological conditions, and movements. Accordingly, complex preprocessing is required to estimate blood pressure based on PTT. In this paper, as an alternative solution, we propose a noninvasive continuous algorithm using the difference between the ECG and PPG as a new feature that can include PTT information. The proposed algorithm is a deep CNN–LSTM-based multitasking machine learning model that outputs simultaneous prediction results of systolic (SBP) and diastolic blood pressures (DBP). The prediction accuracies of SBP and DBP using the proposed model were 0.017±1.624 mmHg and 0.164±1.297 mmHg, respectively. This result corresponded to Grade A according to the BHS and AAMI standards, which are the validation standards for blood pressure measuring devices.

Download Full-text

Continuous Blood Pressure Estimation Using Exclusively Photopletysmography by LSTM-Based Signal-to-Signal Translation

Sensors ◽

10.3390/s21092952 ◽

2021 ◽

Vol 21 (9) ◽

pp. 2952

Author(s):

Latifa Nabila Harfiya ◽

Ching-Chun Chang ◽

Yung-Hui Li

Keyword(s):

Blood Pressure ◽

Absolute Error ◽

Estimation Methods ◽

British Hypertension Society ◽

Arterial Blood ◽

Proposed Model ◽

Pressure Estimation ◽

Effective Signal ◽

Blood Pressure Estimation ◽

Continuous Blood Pressure

Monitoring continuous BP signal is an important issue, because blood pressure (BP) varies over days, minutes, or even seconds for short-term cases. Most of photoplethysmography (PPG)-based BP estimation methods are susceptible to noise and only provides systolic blood pressure (SBP) and diastolic blood pressure (DBP) prediction. Here, instead of estimating a discrete value, we focus on different perspectives to estimate the whole waveform of BP. We propose a novel deep learning model to learn how to perform signal-to-signal translation from PPG to arterial blood pressure (ABP). Furthermore, using a raw PPG signal only as the input, the output of the proposed model is a continuous ABP signal. Based on the translated ABP signal, we extract the SBP and DBP values accordingly to ease the comparative evaluation. Our prediction results achieve average absolute error under 5 mmHg, with 70% confidence for SBP and 95% confidence for DBP without complex feature engineering. These results fulfill the standard from Association for the Advancement of Medical Instrumentation (AAMI) and the British Hypertension Society (BHS) with grade A. From the results, we believe that our model is applicable and potentially boosts the accuracy of an effective signal-to-signal continuous blood pressure estimation.

Download Full-text