Estimating Blood Pressure from the Photoplethysmogram Signal and Demographic Features Using Machine Learning Techniques

Sensors, Journal Year: 2020, Volume and Issue: 20(11), P. 3127 - 3127

Published: June 1, 2020

Hypertension is a potentially unsafe health ailment, which can be indicated directly from the Blood pressure (BP). always leads to other complications. Continuous monitoring of BP very important; however, cuff-based measurements are discrete and uncomfortable user. To address this need, cuff-less, continuous non-invasive measurement system proposed using Photoplethysmogram (PPG) signal demographic features machine learning (ML) algorithms. PPG signals were acquired 219 subjects, undergo pre-processing feature extraction steps. Time, frequency time-frequency domain extracted their derivative signals. Feature selection techniques used reduce computational complexity decrease chance over-fitting ML The then train evaluate best regression models selected for Systolic (SBP) Diastolic (DBP) estimation individually. Gaussian Process Regression (GPR) along with ReliefF algorithm outperforms algorithms in estimating SBP DBP root-mean-square error (RMSE) 6.74 3.59 respectively. This model implemented hardware systems continuously monitor avoid any critical conditions due sudden changes.

Language: Английский

---

Photoplethysmogram Analysis and Applications: An Integrative Review

Frontiers in Physiology, Journal Year: 2022, Volume and Issue: 12

Published: March 1, 2022

Beyond its use in a clinical environment, photoplethysmogram (PPG) is increasingly used for measuring the physiological state of an individual daily life. This review aims to examine existing research on concerning generation mechanisms, measurement principles, applications, noise definition, pre-processing techniques, feature detection and post-processing techniques processing, especially from engineering point view. We performed extensive search with PubMed, Google Scholar, Institute Electrical Electronics Engineers (IEEE), ScienceDirect, Web Science databases. Exclusion conditions did not include year publication, but articles published English were excluded. Based 118 articles, we identified four main topics enabling PPG: (A) PPG waveform, (B) features applications including basic based original combined PPG, derivative (C) motion artifact baseline wandering hypoperfusion, (D) signal processing preprocessing, peak detection, quality index. The application field has been extending mobile environment. Although there no standardized pipeline as data are acquired accumulated various ways, recently proposed machine learning-based method expected offer promising solution.

Language: Английский

---

PP-Net: A Deep Learning Framework for PPG-Based Blood Pressure and Heart Rate Estimation

IEEE Sensors Journal, Journal Year: 2020, Volume and Issue: 20(17), P. 10000 - 10011

Published: April 30, 2020

This paper presents a deep learning model 'PP-Net' which is the first of its kind, having capability to estimate physiological parameters: Diastolic blood pressure (DBP), Systolic (SBP), and Heart rate (HR) simultaneously from same network using single channel PPG signal. The proposed designed by exploiting framework Long-term Recurrent Convolutional Network (LRCN), exhibiting inherent ability feature extraction, thereby, eliminating cost effective steps selection making less-complex for deployment on resource constrained platforms such as mobile platforms. performance demonstration PP-Net done larger publically available MIMIC-II database. We achieved an average NMAE 0.09 (DBP) 0.04 (SBP) mmHg BP, 0.046 bpm HR estimation total population 1557 critically ill subjects. accurate BP compared existing methods, demonstrated effectiveness our framework. evaluation huge with CVD complications, validates robustness in pervasive healthcare monitoring especially cardiac stroke rehabilitation monitoring.

Language: Английский

---

Non-invasive blood glucose monitoring using PPG signals with various deep learning models and implementation using TinyML

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 2, 2025

Language: Английский

---

Monitoring of heart rate, blood oxygen saturation, and blood pressure using a smartphone

Biomedical Signal Processing and Control, Journal Year: 2020, Volume and Issue: 59, P. 101928 - 101928

Published: March 6, 2020

Language: Английский

---

An Unobtrusive and Calibration-free Blood Pressure Estimation Method using Photoplethysmography and Biometrics

Scientific Reports, Journal Year: 2019, Volume and Issue: 9(1)

Published: June 13, 2019

We introduce a novel paradigm to unobtrusively and optically measure blood pressure (BP) without calibration. The algorithm combines photoplethysmography (PPG) waveform analysis biometrics estimate BP, was evaluated in subjects with various age, height, weight BP levels (n = 1249). In the young population (<50 years old) low, medium high systolic pressures (SBP, <120 mmHg; 120-139 ≥140 mmHg), fitting errors are 6.3 ± 7.2, -3.9 7.2 -20.2 14.2 mmHg for SBP respectively; older (>50 same categories, 12.8 9.0, 0.5 8.2 -14.6 11.5 respectively. A simple personalized calibration reduces significantly 147), good peripheral perfusion helps improve accuracy. conclusion, PPG may be used calculate certain populations. When calibrated, it shows great potential serially monitor fluctuation, which can bring tremendous economic health benefits.

Language: Английский

---

Cuffless Blood Pressure Monitoring

Clinical Journal of the American Society of Nephrology, Journal Year: 2020, Volume and Issue: 15(10), P. 1531 - 1538

Published: July 17, 2020

Current BP measurements are on the basis of traditional cuff approaches. Ambulatory monitoring, at 15- to 30-minute intervals usually over 24 hours, provides sufficiently continuous readings that superior office-based snapshot, but this system is not suitable for frequent repeated use. A true measurement could collect passively and frequently would require a cuffless method be worn by patient, with data stored electronically much same way heart rate rhythm already done routinely. Ideally, should measured continuously during diverse activities both daytime nighttime in subject means novel devices. There increasing excitement newer methods measure sensors algorithm development. As new devices refined their accuracy improved, it will possible better assess masked hypertension, nocturnal severity variability BP. In review, we discuss progression field, particularly last 5 years, ending sensor-based approaches incorporate machine learning algorithms personalized medicine.

Language: Английский

---

Assessing hemodynamics from the photoplethysmogram to gain insights into vascular age: a review from VascAgeNet

AJP Heart and Circulatory Physiology, Journal Year: 2021, Volume and Issue: 322(4), P. H493 - H522

Published: Dec. 24, 2021

The photoplethysmogram (PPG) signal is widely measured by clinical and consumer devices, it emerging as a potential tool for assessing vascular age. shape timing of the PPG pulse wave are both influenced normal aging, changes in arterial stiffness blood pressure, atherosclerosis. This review summarizes research into age from PPG. Three categories approaches described:

Language: Английский

---

PPG2ABP: Translating Photoplethysmogram (PPG) Signals to Arterial Blood Pressure (ABP) Waveforms

Bioengineering, Journal Year: 2022, Volume and Issue: 9(11), P. 692 - 692

Published: Nov. 15, 2022

Cardiovascular diseases are one of the most severe causes mortality, annually taking a heavy toll on lives worldwide. Continuous monitoring blood pressure seems to be viable option, but this demands an invasive process, introducing several layers complexities and reliability concerns due non-invasive techniques not being accurate. This motivates us develop method estimate continuous arterial (ABP) waveform through approach using Photoplethysmogram (PPG) signals. We explore advantage deep learning, as it would free from sticking ideally shaped PPG signals only by making handcrafted feature computation irrelevant, which is shortcoming existing approaches. Thus, we present PPG2ABP, two-stage cascaded learning-based that manages ABP input signal with mean absolute error 4.604 mmHg, preserving shape, magnitude, phase in unison. However, more astounding success PPG2ABP turns out computed values Diastolic Blood Pressure (DBP), Mean Arterial (MAP), Systolic (SBP) estimated outperform works under metrics (mean 3.449 ± 6.147 2.310 4.437 5.727 9.162 respectively), despite explicitly trained do so. Notably, both for DBP MAP, achieve Grade A BHS (British Hypertension Society) Standard satisfy AAMI (Association Advancement Medical Instrumentation) standard.

Language: Английский

---

A hybrid neural network for continuous and non-invasive estimation of blood pressure from raw electrocardiogram and photoplethysmogram waveforms

Computer Methods and Programs in Biomedicine, Journal Year: 2021, Volume and Issue: 207, P. 106191 - 106191

Published: May 21, 2021

Background and objectives: Continuous non-invasive blood pressure monitoring would revolutionize healthcare. Currently, (BP) can only be accurately monitored using obtrusive cuff-based devices or invasive intra-arterial monitoring. In this work, we propose a novel hybrid neural network for the accurate estimation of electrocardiogram (ECG) photoplethysmogram (PPG) waveforms as inputs. Methods: This work proposes combines feature detection abilities temporal convolutional layers with strong performance on sequential data offered by long short-term memory layers. Raw are concatenated used The was developed TensorFlow framework. Our scheme is analysed compared to literature in terms well known standards set British Hypertension Society (BHS) Association Advancement Medical Instrumentation (AAMI). Results: achieves extremely low mean absolute errors (MAEs) 4.41 mmHg SBP, 2.91 DBP, 2.77 MAP. A level agreement between our gold-standard shown through Bland Altman regression plots. Additionally, standard BP established AAMI met scheme. We also achieve grade 'A' based criteria outlined BHS protocol devices. Conclusions: CNN-LSTM outperforms current state-of-the-art schemes measurement from PPG ECG waveforms. These results provide an effective machine learning approach that could readily implemented into wearable use continuous clinical at-home

Language: Английский

---