scholarly journals Estimating pulse wave velocity from the radial pressure wave using machine learning algorithms

PLoS ONE ◽  
2021 ◽  
Vol 16 (6) ◽  
pp. e0245026
Author(s):  
Weiwei Jin ◽  
Philip Chowienczyk ◽  
Jordi Alastruey
Keyword(s):  
Machine Learning ◽  
Cardiovascular Risk ◽  
Pulse Wave Velocity ◽  
Wave Velocity ◽  
Pressure Wave ◽  
Pulse Wave ◽  
Radial Pressure ◽  
Vascular Ageing ◽  
Peripheral Pulse ◽  
The Mean

One of the European gold standard measurement of vascular ageing, a risk factor for cardiovascular disease, is the carotid-femoral pulse wave velocity (cfPWV), which requires an experienced operator to measure pulse waves at two sites. In this work, two machine learning pipelines were proposed to estimate cfPWV from the peripheral pulse wave measured at a single site, the radial pressure wave measured by applanation tonometry. The study populations were the Twins UK cohort containing 3,082 subjects aged from 18 to 110 years, and a database containing 4,374 virtual subjects aged from 25 to 75 years. The first pipeline uses Gaussian process regression to estimate cfPWV from features extracted from the radial pressure wave using pulse wave analysis. The mean difference and upper and lower limits of agreement (LOA) of the estimation on the 924 hold-out test subjects from the Twins UK cohort were 0.2 m/s, and 3.75 m/s & -3.34 m/s, respectively. The second pipeline uses a recurrent neural network (RNN) to estimate cfPWV from the entire radial pressure wave. The mean difference and upper and lower LOA of the estimation on the 924 hold-out test subjects from the Twins UK cohort were 0.05 m/s, and 3.21 m/s & -3.11m/s, respectively. The percentage error of the RNN estimates on the virtual subjects increased by less than 2% when adding 20% of random noise to the pressure waveform. These results show the possibility of assessing the vascular ageing using a single peripheral pulse wave (e.g. the radial pressure wave), instead of cfPWV. The proposed code for the machine learning pipelines is available from the following online depository (https://github.com/WeiweiJin/Estimate-Cardiovascular-Risk-from-Pulse-Wave-Signal).

scholarly journals Estimating pulse wave velocity from the radial pressure wave using machine learning algorithms

2020 ◽  
Author(s):  
Weiwei Jin ◽  
Philip Chowienczyk ◽  
Jordi Alastruey
Keyword(s):  
Machine Learning ◽  
Cardiovascular Risk ◽  
Pulse Wave Velocity ◽  
Wave Velocity ◽  
Pressure Wave ◽  
Pulse Wave ◽  
Radial Pressure ◽  
Vascular Ageing ◽  
Peripheral Pulse ◽  
The Mean

AbstractThe European gold standard measurement of vascular ageing, a risk factor for cardiovascular disease, is the carotid-femoral pulse wave velocity (cfPWV), which requires an experienced operator to measure pulse waves at multiple sites. In this work, two machine learning pipelines have been proposed to estimate cfPWV from a peripheral pulse wave measured at a single site, the radial pressure wave measured by applanation tonometry. The study populations were the Twins UK cohort containing 3,082 subjects aged from 18 to 110 years, and a database containing 4,374 virtual subjects aged from 25 to 75 years. The first pipeline uses Gaussian process regression to estimate cfPWV from features extracted from the radial pressure wave using pulse wave analysis. The mean difference and upper and lower limit of agreement (LOA) of the estimation on the 924 hold-out test subjects from the Twins UK cohort were 0.2 m/s, and 3.75 m/s & -3.34 m/s, respectively. The estimation also included a 95% confidence interval for each estimation, which covered 98% of the measured data. The second pipeline uses a recurrent neural network (RNN) to estimate cfPWV from the entire radial pressure wave. The mean difference and upper and lower LOA of the estimation on the 924 hold-out test subjects from the Twins UK cohort were 0.05 m/s, and 3.21 m/s & -3.11m/s, respectively. Further test on the noise sensitivity of the estimation using the RNN on the database of virtual subjects shows that the percentage error increased by less than 2% when adding 20% noise to the waveform. These results have shown the possibility of replacing cfPWV with a peripheral pulse wave (e.g. the radial pressure wave), for vascular ageing assessment. The code for the machine learning pipelines proposed is available from the following online depository (https://github.com/WeiweiJin/Estimate-Cardiovascular-Risk-from-Pulse-Wave-Signal).

Cardiovascular Risk Factors and Disease Characteristics Are Consistently Associated with Arterial Function in Rheumatoid Arthritis

2017 ◽  
Vol 44 (8) ◽  
pp. 1125-1133 ◽  
Author(s):  
Sule Gunter ◽  
Chanel Robinson ◽  
Gavin R. Norton ◽  
Angela J. Woodiwiss ◽  
Linda Tsang ◽  
...  
Keyword(s):  
Risk Factors ◽  
Cardiovascular Risk ◽  
Pulse Wave Velocity ◽  
Cardiovascular Risk Factors ◽  
Wave Velocity ◽  
Pulse Pressure ◽  
Wave Reflection ◽  
Pulse Wave ◽  
Wave Pressure ◽  
Peripheral Pulse

Objective.Arterial properties influence cardiovascular disease (CVD) risk. We identified potential determinants of arterial function in patients with rheumatoid arthritis (RA).Methods.Relationships of traditional cardiovascular risk factors and RA characteristics with arterial stiffness (pulse wave velocity), wave reflection (augmentation index, reflected wave pressure, and reflection magnitude), and pressure pulsatility (central systolic and pulse pressure, peripheral pulse pressure, pulse pressure amplification, and forward wave pressure) were identified in multivariable backward regression models among 177 patients without established CVD (118 white, 32 Asian, 22 black, 5 mixed ancestry).Results.Recorded characteristics explained 37% (pulse wave velocity) to 71% (reflected wave pressure) of the variability in arterial function. These factors were particularly associated with wave reflection and pressure pulsatility: RA duration (p = 0.04), rheumatoid factor status (p = 0.01 to 0.03), leukocyte counts (p = 0.02 to 0.05), and total cholesterol (p < 0.01 to 0.03). Body mass index (p < 0.01 to 0.02) and insulin resistance (p < 0.01 to 0.01) were related to reduced wave reflection and peripheral pulse pressure. Exercise (p = 0.02) and alcohol consumption (p < 0.01) were associated with increased pulse pressure amplification and decreased peripheral pulse pressure, respectively. Tumor necrosis factor-α inhibition (p < 0.01) was related to reduced pulse wave velocity, and tetracycline use (p = 0.02) to decreased peripheral pulse pressure.Conclusion.Traditional cardiovascular risk factors and disease characteristics are consistently associated with vascular hemodynamic alterations in RA. The relative effect of arterial stiffness, wave reflection, and pressure pulsatility on CVD risk in RA needs further study.

Relationship between Job Stress and Pulse Wave Velocity as a Cardiovascular Risk Factor

2004 ◽  
Vol 16 (4) ◽  
pp. 450 ◽  
Author(s):  
Jung Ok Kong ◽  
Sang Baek Koh ◽  
Sei Jin Chang ◽  
Bong Suk Cha ◽  
Ho Keun Chung ◽  
...  
Keyword(s):  
Risk Factor ◽  
Cardiovascular Risk ◽  
Pulse Wave Velocity ◽  
Job Stress ◽  
Wave Velocity ◽  
Cardiovascular Risk Factor ◽  
Pulse Wave

scholarly journals Elevated levels of urine isocitrate, hydroxymethylglutarate, and formiminoglutamate are associated with arterial stiffness in Korean adults

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ji-Hee Haam ◽  
Young-Sang Kim ◽  
Doo-Yeoun Cho ◽  
Hyejin Chun ◽  
Sang-Woon Choi ◽  
...  
Keyword(s):  
Risk Factors ◽  
Cardiovascular Risk ◽  
Arterial Stiffness ◽  
Pulse Wave Velocity ◽  
Cardiovascular Risk Factors ◽  
Wave Velocity ◽  
Pulse Wave ◽  
Urinary Metabolites ◽  
Metabolic Disturbances ◽  
Liquid Chromatograph

AbstractRecent evidence suggests that cellular perturbations play an important role in the pathogenesis of cardiovascular diseases. Therefore, we analyzed the association between the levels of urinary metabolites and arterial stiffness. Our cross-sectional study included 330 Korean men and women. The brachial-ankle pulse wave velocity was measured as a marker of arterial stiffness. Urinary metabolites were evaluated using a high-performance liquid chromatograph-mass spectrometer. The brachial-ankle pulse wave velocity was found to be positively correlated with l-lactate, citrate, isocitrate, succinate, malate, hydroxymethylglutarate, α-ketoisovalerate, α-keto-β-methylvalerate, methylmalonate, and formiminoglutamate among men. Whereas, among women, the brachial-ankle pulse wave velocity was positively correlated with cis-aconitate, isocitrate, hydroxymethylglutarate, and formiminoglutamate. In the multivariable regression models adjusted for conventional cardiovascular risk factors, three metabolite concentrations (urine isocitrate, hydroxymethylglutarate, and formiminoglutamate) were independently and positively associated with brachial-ankle pulse wave velocity. Increased urine isocitrate, hydroxymethylglutarate, and formiminoglutamate concentrations were associated with brachial-ankle pulse wave velocity and independent of conventional cardiovascular risk factors. Our findings suggest that metabolic disturbances in cells may be related to arterial stiffness.

scholarly journals POS-296 CARDIOVASCULAR RISK PREDICTION WITH AORTIC PULSE WAVE VELOCITY: A CARTAGENE STUDY

2021 ◽  
Vol 6 (4) ◽  
pp. S127
Author(s):  
S. Veillette ◽  
F. Lamarche ◽  
M. Agharazii ◽  
S. Wassertheurer ◽  
B. Hametner ◽  
...  
Keyword(s):  
Cardiovascular Risk ◽  
Pulse Wave Velocity ◽  
Risk Prediction ◽  
Wave Velocity ◽  
Pulse Wave ◽  
Aortic Pulse Wave Velocity ◽  
Cardiovascular Risk Prediction

4.5 CARDIAC OUTPUT ESTIMATION FROM BEAT-TO-BEAT RADIAL PRESSURE AND PULSE WAVE VELOCITY: A MODEL-BASED STUDY

2018 ◽  
Vol 24 (C) ◽  
pp. 76
Author(s):  
Vasiliki Bikia ◽  
Stamatia Pagoulatou ◽  
Theodore G. Papaioannou ◽  
Nikolaos Stergiopulos
Keyword(s):  
Cardiac Output ◽  
Pulse Wave Velocity ◽  
Wave Velocity ◽  
Pulse Wave ◽  
Radial Pressure ◽  
Model Based

Carotid–femoral pulse wave velocity acquisition methods and their associations with cardiovascular risk factors and subclinical biomarkers of vascular health

2021 ◽  
Vol Publish Ahead of Print ◽  
Author(s):  
Kunihiko Aizawa ◽  
Phillip E. Gates ◽  
David M. Mawson ◽  
Salim Elyas ◽  
Francesco Casanova ◽  
...  
Keyword(s):  
Risk Factors ◽  
Cardiovascular Risk ◽  
Pulse Wave Velocity ◽  
Cardiovascular Risk Factors ◽  
Wave Velocity ◽  
Pulse Wave ◽  
Vascular Health

A high ankle-brachial index is associated with increased aortic pulse wave velocity: the Czech post-MONICA study

2011 ◽  
Vol 18 (6) ◽  
pp. 790-796 ◽  
Author(s):  
Peter Wohlfahrt ◽  
Daniel Palouš ◽  
Michaela Ingrischová ◽  
Alena Krajčoviechová ◽  
Jitka Seidlerová ◽  
...  
Keyword(s):  
Cardiovascular Risk ◽  
Pulse Wave Velocity ◽  
Wave Velocity ◽  
Aortic Stiffness ◽  
Pulse Wave ◽  
Population Sample ◽  
Ankle Brachial Index ◽  
Aortic Pulse Wave Velocity ◽  
Left Ventricular ◽  
History Of

Background: Ankle brachial index (ABI) has been increasingly used in general practice to identify individuals with low ABI at high cardiovascular risk. However, there has been no consensus on the clinical significance of high ABI. The aim of our study was to compare aortic stiffness as a marker of cardiovascular risk in individuals with low (<1.0), normal (1.0–1.4), and high ABI (>1.4). Methods: A total of 911 individuals from the Czech post-MONICA study (a randomly selected 1% representative population sample, aged 54 ± 13.5 years, 47% of men) were examined. ABI was measured using a handheld Doppler and aortic pulse wave velocity (aPWV) using the Sphygmocor device. Results: Of the 911 individuals, 28 (3.1%) had low ABI and 23 (2.5%) high ABI. There was a U-shaped association between aPWV and ABI. aPWV was significantly higher in individuals with low and high ABI compared with the normal ABI group (11.1 ± 2.8, 8.3 ± 2.3, p < 0.001; 10.8 ± 2.5, 8.3 ± 2.3 m/s, p < 0.001, respectively). In a model adjusted for age, sex, systolic, diastolic, mean blood pressure and examiner, aPWV remained increased in both extreme ABI groups compared with the normal ABI group. In logistic regression analysis, aPWV together with glucose level, male sex, and a history of deep venous thrombosis were independent predictors of high ABI, while cholesterol was not. Conclusion: This is the first study showing increased aortic stiffness in individuals with high ABI, presumably responsible for increased left ventricular mass described previously in this group. These findings suggest increased cardiovascular risk of high ABI individuals.

scholarly journals Differential Associations for Salivary Sodium, Potassium, Calcium, and Phosphate Levels with Carotid Intima Media Thickness, Heart Rate, and Arterial Stiffness

2018 ◽  
Vol 2018 ◽  
pp. 1-12 ◽  
Author(s):  
Carlos Labat ◽  
Silke Thul ◽  
John Pirault ◽  
Mohamed Temmar ◽  
Simon N. Thornton ◽  
...  
Keyword(s):  
Heart Rate ◽  
Cardiovascular Risk ◽  
Pulse Wave Velocity ◽  
Wave Velocity ◽  
Risk Evaluation ◽  
Pulse Wave ◽  
Intima Media Thickness ◽  
Sodium Potassium ◽  
Media Thickness ◽  
Salivary Electrolytes

Salivary biomarkers may offer a noninvasive and easy sampling alternative in cardiovascular risk evaluation. The aim of the present study was to establish associations of salivary potassium, sodium, calcium, and phosphate levels with the cardiovascular phenotype determined by carotid ultrasound and carotid-femoral pulse wave velocity and to identify possible covariates for these associations. N=241 samples of nonstimulated whole buccal saliva were obtained from subjects with (n=143; 59%) or without (n=98; 41%) hypertension. The potassium concentrations were 10-fold higher in saliva compared with plasma, whereas sodium concentrations exhibited the reverse relation between saliva and blood. There were no significant correlations between the levels of sodium, potassium, or calcium in saliva and plasma. All salivary electrolytes, except sodium, were significantly associated with age. In age-adjusted analyses, salivary potassium was significantly associated with carotid artery intima media thickness (cIMT) and carotid-femoral pulse wave velocity, and these associations were at the limit of significance in multivariate analyses including prevalent cardiovascular disease and risk factors. Body mass index was a significant confounder for salivary potassium. Salivary phosphate was significantly associated with cIMT in the multivariate analysis. Salivary potassium, calcium, and phosphate levels were significantly associated with heart rate in the univariate age-adjusted as well as in two different multivariate models, whereas no significant associations between sodium and heart rate were observed. In conclusion, the differential association of salivary electrolytes with cardiovascular phenotypes indicates that these electrolytes should be further studied for their predictive value as noninvasive biomarkers for cardiovascular risk evaluation.

Sign in / Sign up

Export Citation Format

Share Document