Iterative Demographic Attentional Feature Fusion-based CNN and Transformer Network for Accurate Cuffless Blood Pressure Estimation

Liwen  Tang; Dingchang Zheng; Fei Chen

doi:10.1109/APSIPAASC63619.2025.10849156

Iterative Demographic Attentional Feature Fusion-based CNN and Transformer Network for Accurate Cuffless Blood Pressure Estimation

Liwen Tang
, Dingchang Zheng
, Fei Chen

Southern University of Science and Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

1 Citation (Scopus)

41 Downloads (Pure)

Abstract

Continuous cuffless blood pressure (BP) estimation is essential for cardiovascular disease monitoring. Recently, the use of deep learning models to automatically extract features and combine them with demographic features for continuous cuffless BP estimation has gained interest. Based on the observation that demographic features are highly correlated with BP estimation, this work proposes a new iterative demographic attentional feature fusion (AFF)-based CNN and Transformer network for better fusing the demographic features with the electro-cardiogram (ECG) and photoplethysmography (PPG) features, as well as accurate BP estimation. This work tested model performance using a large open BP dataset, i.e., PulseDB. The BP estimation performance of the proposed model on PluseDB dataset meets the standards of the Association for the Advancement of Medical Instrumentation (AAMI) and achieves Grade A at the British Hypertension Society (BHS) standard in the estimate of systolic blood pressure (SBP) and diastolic blood pressure (DBP). The estimations of SBP and DBP have mean absolute errors (MAE) of 3.79 mmHg and 2.37 mmHg, respectively.

Original language	English
Title of host publication	Iterative Demographic Attentional Feature Fusion-based CNN and Transformer Network for Accurate Cuffless Blood Pressure Estimation
Publisher	IEEE
Pages	(In-Press)
Number of pages	6
ISBN (Electronic)	979-8-3503-6733-1
ISBN (Print)	979-8-3503-6734-8
DOIs	https://doi.org/10.1109/APSIPAASC63619.2025.10849156
Publication status	E-pub ahead of print - 27 Jan 2025
Event	2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) - Macau, China Duration: 3 Dec 2024 → 6 Dec 2024 http://www.apsipa2024.org/

Publication series

Name	Proceedings ... Asia-Pacific Signal and Information Processing Association Annual Summit and Conference APSIPA ASC
Publisher	IEEE
ISSN (Print)	2640-009X
ISSN (Electronic)	2640-0103

Conference

Conference	2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
Country/Territory	China
City	Macau
Period	3/12/24 → 6/12/24
Internet address	http://www.apsipa2024.org/

Bibliographical note

© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Copyright © and Moral Rights are retained by the author(s) and/ or other copyright owners. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This item cannot be reproduced or quoted extensively from without first obtaining permission in writing from the copyright holder(s). The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the copyright holders.

This document is the author’s post-print version, incorporating any revisions agreed during the peer-review process. Some differences between the published version and this version may remain and you are advised to consult the published version if you wish to cite from it

Funding

This work was supported by Shenzhen Key Technology Program Funding (JSGG20220831103803006).

Funders	Funder number
Shenzhen Key Technology Program	JSGG20220831103803006

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

Accuracy
Fuses
Estimation
Transformers
Feature extraction
Photoplethysmography
Iterative methods
Reliability
Biomedical monitoring
Standards

Access to Document

10.1109/APSIPAASC63619.2025.10849156

Zheng2025AAMAccepted author manuscript, 0.98 MBLicence: Unspecified

Cite this

Tang, L., Zheng, D., & Chen, F. (2025). Iterative Demographic Attentional Feature Fusion-based CNN and Transformer Network for Accurate Cuffless Blood Pressure Estimation. In Iterative Demographic Attentional Feature Fusion-based CNN and Transformer Network for Accurate Cuffless Blood Pressure Estimation (pp. (In-Press)). (Proceedings ... Asia-Pacific Signal and Information Processing Association Annual Summit and Conference APSIPA ASC). IEEE. Advance online publication. https://doi.org/10.1109/APSIPAASC63619.2025.10849156

Iterative Demographic Attentional Feature Fusion-based CNN and Transformer Network for Accurate Cuffless Blood Pressure Estimation. / Tang, Liwen ; Zheng, Dingchang; Chen, Fei.
Iterative Demographic Attentional Feature Fusion-based CNN and Transformer Network for Accurate Cuffless Blood Pressure Estimation. IEEE, 2025. p. (In-Press) (Proceedings ... Asia-Pacific Signal and Information Processing Association Annual Summit and Conference APSIPA ASC).

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

Tang, L, Zheng, D & Chen, F 2025, Iterative Demographic Attentional Feature Fusion-based CNN and Transformer Network for Accurate Cuffless Blood Pressure Estimation. in Iterative Demographic Attentional Feature Fusion-based CNN and Transformer Network for Accurate Cuffless Blood Pressure Estimation. Proceedings ... Asia-Pacific Signal and Information Processing Association Annual Summit and Conference APSIPA ASC, IEEE, pp. (In-Press), 2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) , Macau, China, 3/12/24. https://doi.org/10.1109/APSIPAASC63619.2025.10849156

Tang L, Zheng D, Chen F. Iterative Demographic Attentional Feature Fusion-based CNN and Transformer Network for Accurate Cuffless Blood Pressure Estimation. In Iterative Demographic Attentional Feature Fusion-based CNN and Transformer Network for Accurate Cuffless Blood Pressure Estimation. IEEE. 2025. p. (In-Press). (Proceedings ... Asia-Pacific Signal and Information Processing Association Annual Summit and Conference APSIPA ASC). Epub 2025 Jan 27. doi: 10.1109/APSIPAASC63619.2025.10849156

Tang, Liwen ; Zheng, Dingchang ; Chen, Fei. / Iterative Demographic Attentional Feature Fusion-based CNN and Transformer Network for Accurate Cuffless Blood Pressure Estimation. Iterative Demographic Attentional Feature Fusion-based CNN and Transformer Network for Accurate Cuffless Blood Pressure Estimation. IEEE, 2025. pp. (In-Press) (Proceedings ... Asia-Pacific Signal and Information Processing Association Annual Summit and Conference APSIPA ASC).

@inproceedings{70669cf566cf464a882159241a32c213,

title = "Iterative Demographic Attentional Feature Fusion-based CNN and Transformer Network for Accurate Cuffless Blood Pressure Estimation",

abstract = "Continuous cuffless blood pressure (BP) estimation is essential for cardiovascular disease monitoring. Recently, the use of deep learning models to automatically extract features and combine them with demographic features for continuous cuffless BP estimation has gained interest. Based on the observation that demographic features are highly correlated with BP estimation, this work proposes a new iterative demographic attentional feature fusion (AFF)-based CNN and Transformer network for better fusing the demographic features with the electro-cardiogram (ECG) and photoplethysmography (PPG) features, as well as accurate BP estimation. This work tested model performance using a large open BP dataset, i.e., PulseDB. The BP estimation performance of the proposed model on PluseDB dataset meets the standards of the Association for the Advancement of Medical Instrumentation (AAMI) and achieves Grade A at the British Hypertension Society (BHS) standard in the estimate of systolic blood pressure (SBP) and diastolic blood pressure (DBP). The estimations of SBP and DBP have mean absolute errors (MAE) of 3.79 mmHg and 2.37 mmHg, respectively.",

keywords = "Accuracy, Fuses, Estimation, Transformers, Feature extraction, Photoplethysmography, Iterative methods, Reliability, Biomedical monitoring, Standards",

author = "Liwen Tang and Dingchang Zheng and Fei Chen",

note = "{\textcopyright} 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Copyright {\textcopyright} and Moral Rights are retained by the author(s) and/ or other copyright owners. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This item cannot be reproduced or quoted extensively from without first obtaining permission in writing from the copyright holder(s). The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the copyright holders. This document is the author{\textquoteright}s post-print version, incorporating any revisions agreed during the peer-review process. Some differences between the published version and this version may remain and you are advised to consult the published version if you wish to cite from it ; 2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) ; Conference date: 03-12-2024 Through 06-12-2024",

year = "2025",

month = jan,

day = "27",

doi = "10.1109/APSIPAASC63619.2025.10849156",

language = "English",

isbn = "979-8-3503-6734-8",

series = "Proceedings ... Asia-Pacific Signal and Information Processing Association Annual Summit and Conference APSIPA ASC",

publisher = "IEEE",

pages = "(In--Press)",

booktitle = "Iterative Demographic Attentional Feature Fusion-based CNN and Transformer Network for Accurate Cuffless Blood Pressure Estimation",

address = "United States",

url = "http://www.apsipa2024.org/",

}

TY - GEN

T1 - Iterative Demographic Attentional Feature Fusion-based CNN and Transformer Network for Accurate Cuffless Blood Pressure Estimation

AU - Tang, Liwen

AU - Zheng, Dingchang

AU - Chen, Fei

N1 - © 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Copyright © and Moral Rights are retained by the author(s) and/ or other copyright owners. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This item cannot be reproduced or quoted extensively from without first obtaining permission in writing from the copyright holder(s). The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the copyright holders. This document is the author’s post-print version, incorporating any revisions agreed during the peer-review process. Some differences between the published version and this version may remain and you are advised to consult the published version if you wish to cite from it

PY - 2025/1/27

Y1 - 2025/1/27

N2 - Continuous cuffless blood pressure (BP) estimation is essential for cardiovascular disease monitoring. Recently, the use of deep learning models to automatically extract features and combine them with demographic features for continuous cuffless BP estimation has gained interest. Based on the observation that demographic features are highly correlated with BP estimation, this work proposes a new iterative demographic attentional feature fusion (AFF)-based CNN and Transformer network for better fusing the demographic features with the electro-cardiogram (ECG) and photoplethysmography (PPG) features, as well as accurate BP estimation. This work tested model performance using a large open BP dataset, i.e., PulseDB. The BP estimation performance of the proposed model on PluseDB dataset meets the standards of the Association for the Advancement of Medical Instrumentation (AAMI) and achieves Grade A at the British Hypertension Society (BHS) standard in the estimate of systolic blood pressure (SBP) and diastolic blood pressure (DBP). The estimations of SBP and DBP have mean absolute errors (MAE) of 3.79 mmHg and 2.37 mmHg, respectively.

AB - Continuous cuffless blood pressure (BP) estimation is essential for cardiovascular disease monitoring. Recently, the use of deep learning models to automatically extract features and combine them with demographic features for continuous cuffless BP estimation has gained interest. Based on the observation that demographic features are highly correlated with BP estimation, this work proposes a new iterative demographic attentional feature fusion (AFF)-based CNN and Transformer network for better fusing the demographic features with the electro-cardiogram (ECG) and photoplethysmography (PPG) features, as well as accurate BP estimation. This work tested model performance using a large open BP dataset, i.e., PulseDB. The BP estimation performance of the proposed model on PluseDB dataset meets the standards of the Association for the Advancement of Medical Instrumentation (AAMI) and achieves Grade A at the British Hypertension Society (BHS) standard in the estimate of systolic blood pressure (SBP) and diastolic blood pressure (DBP). The estimations of SBP and DBP have mean absolute errors (MAE) of 3.79 mmHg and 2.37 mmHg, respectively.

KW - Accuracy

KW - Fuses

KW - Estimation

KW - Transformers

KW - Feature extraction

KW - Photoplethysmography

KW - Iterative methods

KW - Reliability

KW - Biomedical monitoring

KW - Standards

U2 - 10.1109/APSIPAASC63619.2025.10849156

DO - 10.1109/APSIPAASC63619.2025.10849156

M3 - Conference proceeding

SN - 979-8-3503-6734-8

T3 - Proceedings ... Asia-Pacific Signal and Information Processing Association Annual Summit and Conference APSIPA ASC

SP - (In-Press)

BT - Iterative Demographic Attentional Feature Fusion-based CNN and Transformer Network for Accurate Cuffless Blood Pressure Estimation

PB - IEEE

T2 - 2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

Y2 - 3 December 2024 through 6 December 2024

ER -

Iterative Demographic Attentional Feature Fusion-based CNN and Transformer Network for Accurate Cuffless Blood Pressure Estimation

Abstract

Publication series

Conference

Bibliographical note

Funding

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this