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

in Scientific reports by Yali Zheng, Hongda Huang, Jiasheng Gao, Jingyuan Hong, Shenghao Wu, Yuanting Zhang, Qing Liu

TLDR

  • A novel, calibration-free model called UTransBPNet is introduced for cuffless blood pressure estimation, outperforming existing models in tracking blood pressure variations 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-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.

Overview

  • The study introduces a novel, calibration-free model for cuffless blood pressure estimation called UTransBPNet.
  • The model uses a squeeze-and-excitation-enhanced U-net architecture for short-range feature extraction and a transformer and cross attention module to capture long-range dependencies from high-resolution, multi-channel physiological signals.
  • The primary objective of the study is to develop a robust, cuffless blood pressure estimation model that can track blood pressure variations under dynamic conditions.

Comparative Analysis & Findings

  • The study demonstrates that UTransBPNet outperformed existing models in tracking blood pressure variations under dynamic conditions.
  • The model achieved individual Pearson's correlation coefficients of 0.61 ± 0.17 and 0.62 ± 0.13 for systolic and diastolic blood pressure in Dataset_Drink, 0.82 ± 0.11 and 0.72 ± 0.18 in Dataset_Exercise, and low mean absolute differences of 4.38 and 2.25 mmHg in Dataset_MIMIC.
  • The analysis highlights the impact of dataset characteristics, such as distribution shift, distribution imbalance, and individual blood pressure variability, on model performance, emphasizing the need for well-curated data to ensure generalizability.

Implications and Future Directions

  • The study advances the development of robust, cuffless blood pressure estimation models for real-world applications.
  • Future research directions may involve refining the model to improve its performance on diverse datasets and developing clinical applications for cuffless blood pressure monitoring.
  • The study's findings also underscore the importance of considering dataset characteristics and well-curated data in the development of machine learning models for real-world applications.
Read Full Article