Central aortic blood pressure waveform estimation with a temporal convolutional network

Wenyan Liu; Shuo Du; Na Pang; Liangyu Zhang; Guozhe Sun; Hanguang Xiao; Qi Zhao; Lisheng Xu; Yudong Yao; Jordi Alastruey; Alberto Avolio

doi:10.1109/JBHI.2023.3268886

Central aortic blood pressure waveform estimation with a temporal convolutional network

Wenyan Liu, Shuo Du, Na Pang, Liangyu Zhang, Guozhe Sun, Hanguang Xiao, Qi Zhao, Lisheng Xu, Yudong Yao, Jordi Alastruey, Alberto Avolio

Biomedical Engineering Department

Research output: Contribution to journal › Article › peer-review

2 Citations (Scopus)

Abstract

A novel temporal convolutional network (TCN) model is utilized to reconstruct the central aortic blood pressure (aBP) waveform from the radial blood pressure waveform. The method does not need manual feature extraction as traditional transfer function approaches. The data acquired by the SphygmoCor CVMS device in 1,032 participants as a measured database and a public database of 4,374 virtual healthy subjects were used to compare the accuracy and computational cost of the TCN model with the published convolutional neural network and bi-directional long short-term memory (CNN-BiLSTM) model. The TCN model was compared with CNN-BiLSTM in the root mean square error (RMSE). The TCN model generally outperformed the existing CNN-BiLSTM model in terms of accuracy and computational cost. For the measured and public databases, the RMSE of the waveform using the TCN model was 0.55 ± 0.40 mmHg and 0.84 ± 0.29 mmHg, respectively. The training time of the TCN model was 9.63 min and 25.51 min for the entire training set; the average test time was around 1.79 ms and 8.58 ms per test pulse signal from the measured and public databases, respectively. The TCN model is accurate and fast for processing long input signals, and provides a novel method for measuring the aBP waveform. This method may contribute to the early monitoring and prevention of cardiovascular disease.

Original language	English
Pages (from-to)	3622-3632
Number of pages	11
Journal	IEEE Journal of Biomedical and Health Informatics
Volume	27
Issue number	7
DOIs	https://doi.org/10.1109/JBHI.2023.3268886
Publication status	Published - 1 Jul 2023

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/JBHI.2023.3268886

Cite this

@article{54d179f1b9e847d1b10a2740b72fb755,

title = "Central aortic blood pressure waveform estimation with a temporal convolutional network",

abstract = "A novel temporal convolutional network (TCN) model is utilized to reconstruct the central aortic blood pressure (aBP) waveform from the radial blood pressure waveform. The method does not need manual feature extraction as traditional transfer function approaches. The data acquired by the SphygmoCor CVMS device in 1,032 participants as a measured database and a public database of 4,374 virtual healthy subjects were used to compare the accuracy and computational cost of the TCN model with the published convolutional neural network and bi-directional long short-term memory (CNN-BiLSTM) model. The TCN model was compared with CNN-BiLSTM in the root mean square error (RMSE). The TCN model generally outperformed the existing CNN-BiLSTM model in terms of accuracy and computational cost. For the measured and public databases, the RMSE of the waveform using the TCN model was 0.55 ± 0.40 mmHg and 0.84 ± 0.29 mmHg, respectively. The training time of the TCN model was 9.63 min and 25.51 min for the entire training set; the average test time was around 1.79 ms and 8.58 ms per test pulse signal from the measured and public databases, respectively. The TCN model is accurate and fast for processing long input signals, and provides a novel method for measuring the aBP waveform. This method may contribute to the early monitoring and prevention of cardiovascular disease.",

author = "Wenyan Liu and Shuo Du and Na Pang and Liangyu Zhang and Guozhe Sun and Hanguang Xiao and Qi Zhao and Lisheng Xu and Yudong Yao and Jordi Alastruey and Alberto Avolio",

note = "Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2023",

month = jul,

day = "1",

doi = "10.1109/JBHI.2023.3268886",

language = "English",

volume = "27",

pages = "3622--3632",

journal = "IEEE Journal of Biomedical and Health Informatics",

issn = "2168-2194",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "7",

}

TY - JOUR

T1 - Central aortic blood pressure waveform estimation with a temporal convolutional network

AU - Liu, Wenyan

AU - Du, Shuo

AU - Pang, Na

AU - Zhang, Liangyu

AU - Sun, Guozhe

AU - Xiao, Hanguang

AU - Zhao, Qi

AU - Xu, Lisheng

AU - Yao, Yudong

AU - Alastruey, Jordi

AU - Avolio, Alberto

PY - 2023/7/1

Y1 - 2023/7/1

N2 - A novel temporal convolutional network (TCN) model is utilized to reconstruct the central aortic blood pressure (aBP) waveform from the radial blood pressure waveform. The method does not need manual feature extraction as traditional transfer function approaches. The data acquired by the SphygmoCor CVMS device in 1,032 participants as a measured database and a public database of 4,374 virtual healthy subjects were used to compare the accuracy and computational cost of the TCN model with the published convolutional neural network and bi-directional long short-term memory (CNN-BiLSTM) model. The TCN model was compared with CNN-BiLSTM in the root mean square error (RMSE). The TCN model generally outperformed the existing CNN-BiLSTM model in terms of accuracy and computational cost. For the measured and public databases, the RMSE of the waveform using the TCN model was 0.55 ± 0.40 mmHg and 0.84 ± 0.29 mmHg, respectively. The training time of the TCN model was 9.63 min and 25.51 min for the entire training set; the average test time was around 1.79 ms and 8.58 ms per test pulse signal from the measured and public databases, respectively. The TCN model is accurate and fast for processing long input signals, and provides a novel method for measuring the aBP waveform. This method may contribute to the early monitoring and prevention of cardiovascular disease.

AB - A novel temporal convolutional network (TCN) model is utilized to reconstruct the central aortic blood pressure (aBP) waveform from the radial blood pressure waveform. The method does not need manual feature extraction as traditional transfer function approaches. The data acquired by the SphygmoCor CVMS device in 1,032 participants as a measured database and a public database of 4,374 virtual healthy subjects were used to compare the accuracy and computational cost of the TCN model with the published convolutional neural network and bi-directional long short-term memory (CNN-BiLSTM) model. The TCN model was compared with CNN-BiLSTM in the root mean square error (RMSE). The TCN model generally outperformed the existing CNN-BiLSTM model in terms of accuracy and computational cost. For the measured and public databases, the RMSE of the waveform using the TCN model was 0.55 ± 0.40 mmHg and 0.84 ± 0.29 mmHg, respectively. The training time of the TCN model was 9.63 min and 25.51 min for the entire training set; the average test time was around 1.79 ms and 8.58 ms per test pulse signal from the measured and public databases, respectively. The TCN model is accurate and fast for processing long input signals, and provides a novel method for measuring the aBP waveform. This method may contribute to the early monitoring and prevention of cardiovascular disease.

UR - http://www.scopus.com/inward/record.url?scp=85153798755&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2023.3268886

DO - 10.1109/JBHI.2023.3268886

M3 - Article

SN - 2168-2194

VL - 27

SP - 3622

EP - 3632

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

IS - 7

ER -

Central aortic blood pressure waveform estimation with a temporal convolutional network

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this