Estimation of pulse transit time from radial pressure waveform alone by artificial neural network

Hanguang Xiao, Mark Butlin, Isabella Tan, Ahmad Qasem, Alberto Avolio

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Objective: To validate the feasibility of the estimation of pulse transit time (PTT) by artificial neural network (ANN) from radial pressure waveform alone. Methods: A cascade ANN with ten-fold cross validation was applied to invasively and simultaneously recorded aortic and radial pressure waveforms during rest and nitroglycerin infusion (n=62) for the estimation of mean and beat-to-beat PTT. The results of the ANN models were compared to a multiple linear regression (LR) model when the features of radial arterial pressure waveform in time and frequency domains were used as the predictors of the models. Results: For the estimation of mean PTT and beat-to-beat PTT by ANN (PTTANN), the correlation coefficient between the PTTANN and the measured PTT (PTTmeasured) (mean: r=0.73; beat-to-beat: r=0.85) is higher than that between the PTT estimated by LR (PTTLR) and PTTmeasured (mean: r=0.46; beat-to-beat: r=0.79). The standard deviation (SD) of the difference between the PTTANN and PTTmeasured (mean: SD=10 ms; beat-to-beat: SD=8 ms) is significantly less than that between the PTTLR and PTTmeasured (mean: SD=17 ms; beat-to-beat: 10 ms), but no significant difference exists between their mean (p=0.92). The lack of frequency features of radial pressure waveform caused obvious reduction in the correlation coefficient (Δr=0.16) and SD of the difference (ΔSD=6 ms) between the PTTANN and PTTmeasured. The performance of the ANN was improved by increasing the sample number but not by increasing the neuron number. Conclusion: ANN is a potential method of PTT estimation from a single pressure measurement at radial artery.

LanguageEnglish
Pages1140-1147
Number of pages8
JournalIEEE Journal of Biomedical and Health Informatics
Volume22
Issue number4
Early online date31 Aug 2017
DOIs
Publication statusPublished - Jul 2018

Fingerprint

Pulse Wave Analysis
Neural networks
Pressure
Linear Models
Linear regression
Arterial Pressure
Radial Artery
Pressure measurement
Neural Networks (Computer)
Nitroglycerin
Neurons

Keywords

  • arterial pressure
  • artificial neural network
  • pulse wave velocity
  • pulse transit time

Cite this

@article{1b2b17c53b634e419e29fefa71278cfd,
title = "Estimation of pulse transit time from radial pressure waveform alone by artificial neural network",
abstract = "Objective: To validate the feasibility of the estimation of pulse transit time (PTT) by artificial neural network (ANN) from radial pressure waveform alone. Methods: A cascade ANN with ten-fold cross validation was applied to invasively and simultaneously recorded aortic and radial pressure waveforms during rest and nitroglycerin infusion (n=62) for the estimation of mean and beat-to-beat PTT. The results of the ANN models were compared to a multiple linear regression (LR) model when the features of radial arterial pressure waveform in time and frequency domains were used as the predictors of the models. Results: For the estimation of mean PTT and beat-to-beat PTT by ANN (PTTANN), the correlation coefficient between the PTTANN and the measured PTT (PTTmeasured) (mean: r=0.73; beat-to-beat: r=0.85) is higher than that between the PTT estimated by LR (PTTLR) and PTTmeasured (mean: r=0.46; beat-to-beat: r=0.79). The standard deviation (SD) of the difference between the PTTANN and PTTmeasured (mean: SD=10 ms; beat-to-beat: SD=8 ms) is significantly less than that between the PTTLR and PTTmeasured (mean: SD=17 ms; beat-to-beat: 10 ms), but no significant difference exists between their mean (p=0.92). The lack of frequency features of radial pressure waveform caused obvious reduction in the correlation coefficient (Δr=0.16) and SD of the difference (ΔSD=6 ms) between the PTTANN and PTTmeasured. The performance of the ANN was improved by increasing the sample number but not by increasing the neuron number. Conclusion: ANN is a potential method of PTT estimation from a single pressure measurement at radial artery.",
keywords = "arterial pressure, artificial neural network, pulse wave velocity, pulse transit time",
author = "Hanguang Xiao and Mark Butlin and Isabella Tan and Ahmad Qasem and Alberto Avolio",
year = "2018",
month = "7",
doi = "10.1109/JBHI.2017.2748280",
language = "English",
volume = "22",
pages = "1140--1147",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers",
number = "4",

}

Estimation of pulse transit time from radial pressure waveform alone by artificial neural network. / Xiao, Hanguang; Butlin, Mark; Tan, Isabella; Qasem, Ahmad; Avolio, Alberto.

In: IEEE Journal of Biomedical and Health Informatics, Vol. 22, No. 4, 07.2018, p. 1140-1147.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Estimation of pulse transit time from radial pressure waveform alone by artificial neural network

AU - Xiao, Hanguang

AU - Butlin, Mark

AU - Tan, Isabella

AU - Qasem, Ahmad

AU - Avolio, Alberto

PY - 2018/7

Y1 - 2018/7

N2 - Objective: To validate the feasibility of the estimation of pulse transit time (PTT) by artificial neural network (ANN) from radial pressure waveform alone. Methods: A cascade ANN with ten-fold cross validation was applied to invasively and simultaneously recorded aortic and radial pressure waveforms during rest and nitroglycerin infusion (n=62) for the estimation of mean and beat-to-beat PTT. The results of the ANN models were compared to a multiple linear regression (LR) model when the features of radial arterial pressure waveform in time and frequency domains were used as the predictors of the models. Results: For the estimation of mean PTT and beat-to-beat PTT by ANN (PTTANN), the correlation coefficient between the PTTANN and the measured PTT (PTTmeasured) (mean: r=0.73; beat-to-beat: r=0.85) is higher than that between the PTT estimated by LR (PTTLR) and PTTmeasured (mean: r=0.46; beat-to-beat: r=0.79). The standard deviation (SD) of the difference between the PTTANN and PTTmeasured (mean: SD=10 ms; beat-to-beat: SD=8 ms) is significantly less than that between the PTTLR and PTTmeasured (mean: SD=17 ms; beat-to-beat: 10 ms), but no significant difference exists between their mean (p=0.92). The lack of frequency features of radial pressure waveform caused obvious reduction in the correlation coefficient (Δr=0.16) and SD of the difference (ΔSD=6 ms) between the PTTANN and PTTmeasured. The performance of the ANN was improved by increasing the sample number but not by increasing the neuron number. Conclusion: ANN is a potential method of PTT estimation from a single pressure measurement at radial artery.

AB - Objective: To validate the feasibility of the estimation of pulse transit time (PTT) by artificial neural network (ANN) from radial pressure waveform alone. Methods: A cascade ANN with ten-fold cross validation was applied to invasively and simultaneously recorded aortic and radial pressure waveforms during rest and nitroglycerin infusion (n=62) for the estimation of mean and beat-to-beat PTT. The results of the ANN models were compared to a multiple linear regression (LR) model when the features of radial arterial pressure waveform in time and frequency domains were used as the predictors of the models. Results: For the estimation of mean PTT and beat-to-beat PTT by ANN (PTTANN), the correlation coefficient between the PTTANN and the measured PTT (PTTmeasured) (mean: r=0.73; beat-to-beat: r=0.85) is higher than that between the PTT estimated by LR (PTTLR) and PTTmeasured (mean: r=0.46; beat-to-beat: r=0.79). The standard deviation (SD) of the difference between the PTTANN and PTTmeasured (mean: SD=10 ms; beat-to-beat: SD=8 ms) is significantly less than that between the PTTLR and PTTmeasured (mean: SD=17 ms; beat-to-beat: 10 ms), but no significant difference exists between their mean (p=0.92). The lack of frequency features of radial pressure waveform caused obvious reduction in the correlation coefficient (Δr=0.16) and SD of the difference (ΔSD=6 ms) between the PTTANN and PTTmeasured. The performance of the ANN was improved by increasing the sample number but not by increasing the neuron number. Conclusion: ANN is a potential method of PTT estimation from a single pressure measurement at radial artery.

KW - arterial pressure

KW - artificial neural network

KW - pulse wave velocity

KW - pulse transit time

UR - http://www.scopus.com/inward/record.url?scp=85029164425&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2017.2748280

DO - 10.1109/JBHI.2017.2748280

M3 - Article

VL - 22

SP - 1140

EP - 1147

JO - IEEE Journal of Biomedical and Health Informatics

T2 - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 4

ER -