UTransBPNet for cuffless and calibration-free blood pressure estimation under dynamic conditions

Abstract Accurate cuffless blood pressure (BP) estimation remains challenging, particularly under dynamic conditions with significant intra-individual BP variations. This study introduces UTransBPNet, a novel, calibration-free model for cuffless BP estimation. It integrates a squeeze-and-excitation-...

Full description

Saved in:
Bibliographic Details
Main Authors: Yali Zheng, Hongda Huang, Jiasheng Gao, Jingyuan Hong, Shenghao Wu, Yuanting Zhang, Qing Liu
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-02963-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850127950476738560
author Yali Zheng
Hongda Huang
Jiasheng Gao
Jingyuan Hong
Shenghao Wu
Yuanting Zhang
Qing Liu
author_facet Yali Zheng
Hongda Huang
Jiasheng Gao
Jingyuan Hong
Shenghao Wu
Yuanting Zhang
Qing Liu
author_sort Yali Zheng
collection DOAJ
description Abstract Accurate cuffless blood pressure (BP) estimation remains challenging, particularly under dynamic conditions with significant intra-individual BP variations. This study introduces UTransBPNet, a novel, calibration-free model for cuffless BP estimation. It integrates a squeeze-and-excitation-enhanced Unet architecture for short-range feature extraction with a transformer and cross attention module to capture long-range dependencies from high-resolution, multi-channel physiological signals, further refined through an optimized fine-tuning scheme. Comprehensive validations were conducted across multiple dynamic datasets—Dataset_Drink, Dataset_Exercise, and Dataset_MIMIC—in both scenario-specific and cross-scenario settings. Results demonstrate that UTransBPNet outperformed existing models in tracking BP variations under dynamic conditions, achieving individual Pearson’s correlation coefficients of 0.61 ± 0.17 and 0.62 ± 0.13 for systolic BP (SBP) and diastolic BP (DBP) in Dataset_Drink, 0.82 ± 0.11 and 0.72 ± 0.18 in Dataset_Exercise, and low mean absolute differences (MADs) of 4.38 and 2.25 mmHg in Dataset_MIMIC. The analysis also highlights the impact of dataset characteristics on model performance, such as distribution shift, distribution imbalance and individual BP variability, highlighting the need for well-curated data to ensure generalizability. This study advances the development of robust, cuffless BP estimation models for real-world applications.
format Article
id doaj-art-2e2d5a59fd0a425aa063371a18a7194f
institution OA Journals
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-2e2d5a59fd0a425aa063371a18a7194f2025-08-20T02:33:31ZengNature PortfolioScientific Reports2045-23222025-05-0115111210.1038/s41598-025-02963-3UTransBPNet for cuffless and calibration-free blood pressure estimation under dynamic conditionsYali Zheng0Hongda Huang1Jiasheng Gao2Jingyuan Hong3Shenghao Wu4Yuanting Zhang5Qing Liu6 Department of Biomedical Engineering, College of Health Science and Environmental Engineering, ShenzhenTechnology University Department of Biomedical Engineering, College of Health Science and Environmental Engineering, ShenzhenTechnology University Department of Biomedical Engineering, College of Health Science and Environmental Engineering, ShenzhenTechnology University School of Imaging Sciences and Biomedical Engineering, King’s College London Department of Biomedical Engineering, College of Health Science and Environmental Engineering, ShenzhenTechnology UniversityChinese University of Hong KongDepartment of Communication and Networking, Xi’an Jiaotong-Liverpool UniversityAbstract Accurate cuffless blood pressure (BP) estimation remains challenging, particularly under dynamic conditions with significant intra-individual BP variations. This study introduces UTransBPNet, a novel, calibration-free model for cuffless BP estimation. It integrates a squeeze-and-excitation-enhanced Unet architecture for short-range feature extraction with a transformer and cross attention module to capture long-range dependencies from high-resolution, multi-channel physiological signals, further refined through an optimized fine-tuning scheme. Comprehensive validations were conducted across multiple dynamic datasets—Dataset_Drink, Dataset_Exercise, and Dataset_MIMIC—in both scenario-specific and cross-scenario settings. Results demonstrate that UTransBPNet outperformed existing models in tracking BP variations under dynamic conditions, achieving individual Pearson’s correlation coefficients of 0.61 ± 0.17 and 0.62 ± 0.13 for systolic BP (SBP) and diastolic BP (DBP) in Dataset_Drink, 0.82 ± 0.11 and 0.72 ± 0.18 in Dataset_Exercise, and low mean absolute differences (MADs) of 4.38 and 2.25 mmHg in Dataset_MIMIC. The analysis also highlights the impact of dataset characteristics on model performance, such as distribution shift, distribution imbalance and individual BP variability, highlighting the need for well-curated data to ensure generalizability. This study advances the development of robust, cuffless BP estimation models for real-world applications.https://doi.org/10.1038/s41598-025-02963-3Cuffless blood pressure estimationCross-scenarioModel generalizabilityCalibration-freeDistribution shiftDistribution imbalance
spellingShingle Yali Zheng
Hongda Huang
Jiasheng Gao
Jingyuan Hong
Shenghao Wu
Yuanting Zhang
Qing Liu
UTransBPNet for cuffless and calibration-free blood pressure estimation under dynamic conditions
Scientific Reports
Cuffless blood pressure estimation
Cross-scenario
Model generalizability
Calibration-free
Distribution shift
Distribution imbalance
title UTransBPNet for cuffless and calibration-free blood pressure estimation under dynamic conditions
title_full UTransBPNet for cuffless and calibration-free blood pressure estimation under dynamic conditions
title_fullStr UTransBPNet for cuffless and calibration-free blood pressure estimation under dynamic conditions
title_full_unstemmed UTransBPNet for cuffless and calibration-free blood pressure estimation under dynamic conditions
title_short UTransBPNet for cuffless and calibration-free blood pressure estimation under dynamic conditions
title_sort utransbpnet for cuffless and calibration free blood pressure estimation under dynamic conditions
topic Cuffless blood pressure estimation
Cross-scenario
Model generalizability
Calibration-free
Distribution shift
Distribution imbalance
url https://doi.org/10.1038/s41598-025-02963-3
work_keys_str_mv AT yalizheng utransbpnetforcufflessandcalibrationfreebloodpressureestimationunderdynamicconditions
AT hongdahuang utransbpnetforcufflessandcalibrationfreebloodpressureestimationunderdynamicconditions
AT jiashenggao utransbpnetforcufflessandcalibrationfreebloodpressureestimationunderdynamicconditions
AT jingyuanhong utransbpnetforcufflessandcalibrationfreebloodpressureestimationunderdynamicconditions
AT shenghaowu utransbpnetforcufflessandcalibrationfreebloodpressureestimationunderdynamicconditions
AT yuantingzhang utransbpnetforcufflessandcalibrationfreebloodpressureestimationunderdynamicconditions
AT qingliu utransbpnetforcufflessandcalibrationfreebloodpressureestimationunderdynamicconditions