A Two-Branch ResNet-BiLSTM Deep Learning Framework for Extracting Multimodal Features Applied to PPG-Based Cuffless Blood Pressure Estimation

Liu, Zenan; Qiao, Minghong; Liu, Yezi; Zhang, Jing; He, Ling

doi:10.3390/s25133975

Open AccessArticle

A Two-Branch ResNet-BiLSTM Deep Learning Framework for Extracting Multimodal Features Applied to PPG-Based Cuffless Blood Pressure Estimation

by

Zenan Liu

,

Minghong Qiao

,

Yezi Liu

,

Jing Zhang

and

Ling He

^*

College of Biomedical Engineering, Sichuan University, Chengdu 610065, China

^*

Author to whom correspondence should be addressed.

Sensors 2025, 25(13), 3975; https://doi.org/10.3390/s25133975

Submission received: 12 May 2025 / Revised: 24 June 2025 / Accepted: 25 June 2025 / Published: 26 June 2025

(This article belongs to the Section Biomedical Sensors)

Download

Browse Figures

Versions Notes

Abstract

Cardiovascular disease is a major health threat closely associated with blood pressure levels. While continuous monitoring is essential, traditional cuff-based devices are inconvenient for long-term use. Current methods often fail to balance deep learning capabilities with interpretability, limiting further accuracy improvements. To address this problem, we propose a novel two-branch deep learning framework combining Residual Networks (ResNet) and Bidirectional Long Short-Term Memory (BiLSTM) for photoplethysmography (PPG)-based cuffless blood pressure estimation. The ResNet branch processes 60 features selected by Support Vector Machine-Recursive Feature Elimination (SVM-RFE) from manually extracted features, including our newly proposed trend features, while the BiLSTM branch processes complete PPG waveforms. Testing on 220 waveform segments from 218 patients in the MIMIC-IV dataset, our method achieves mean absolute errors of 3.47 mmHg and 2.81 mmHg, with standard deviations of 5.06 mmHg and 4.11 mmHg for systolic and diastolic blood pressure. This performance meets the Association for the Advancement of Medical Instrumentation (AAMI) standards and achieves an A rating according to British Hypertension Society (BHS) standards.

Keywords: cuffless blood pressure estimating; photoplethysmography (PPG); physiological signals; deep learning; feature extraction

Share and Cite

MDPI and ACS Style

Liu, Z.; Qiao, M.; Liu, Y.; Zhang, J.; He, L. A Two-Branch ResNet-BiLSTM Deep Learning Framework for Extracting Multimodal Features Applied to PPG-Based Cuffless Blood Pressure Estimation. Sensors 2025, 25, 3975. https://doi.org/10.3390/s25133975

AMA Style

Liu Z, Qiao M, Liu Y, Zhang J, He L. A Two-Branch ResNet-BiLSTM Deep Learning Framework for Extracting Multimodal Features Applied to PPG-Based Cuffless Blood Pressure Estimation. Sensors. 2025; 25(13):3975. https://doi.org/10.3390/s25133975

Chicago/Turabian Style

Liu, Zenan, Minghong Qiao, Yezi Liu, Jing Zhang, and Ling He. 2025. "A Two-Branch ResNet-BiLSTM Deep Learning Framework for Extracting Multimodal Features Applied to PPG-Based Cuffless Blood Pressure Estimation" Sensors 25, no. 13: 3975. https://doi.org/10.3390/s25133975

APA Style

Liu, Z., Qiao, M., Liu, Y., Zhang, J., & He, L. (2025). A Two-Branch ResNet-BiLSTM Deep Learning Framework for Extracting Multimodal Features Applied to PPG-Based Cuffless Blood Pressure Estimation. Sensors, 25(13), 3975. https://doi.org/10.3390/s25133975

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

A Two-Branch ResNet-BiLSTM Deep Learning Framework for Extracting Multimodal Features Applied to PPG-Based Cuffless Blood Pressure Estimation

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI