Overview
Continuous cuffless blood pressure (BP) monitoring using photoplethysmography (PPG) offers a promising solution for personalized healthcare. However, existing methods have two major limitations. Handcrafted feature-based approaches rely on precise fiducial point detection and are limited to short-term analysis, while deep learning models, despite their accuracy, often operate as black boxes with limited physiological interpretability.
Proposed Framework
To address these challenges, the authors propose a physiology-guided hybrid framework for personalized BP estimation that couples:
- A convolutional neural network (CNN) branch capturing global and local waveform dynamics
- A morphology-prior branch that explicitly encodes person-specific vascular characteristics
By embedding a morphology-based feature set that explicitly encodes individual vascular characteristics, the proposed framework enhances personalization and reduces dependence on large-scale training datasets.
Results
Evaluated on a subset of the MIMIC-III database under a subject-specific (personalized) testing protocol, the proposed personalized physiology-guided hybrid approach achieved:
- Mean absolute error (MAE) of 3.77 mmHg for systolic BP
- MAE of 2.36 mmHg for diastolic BP
These correspond to relative improvements of 43.7% and 32.4% over a subject-specific (personalized) CNN-only baseline.
Interpretability
SHAP-based analysis confirmed that the introduced morphology-prior features align with individual vascular characteristics, reinforcing per-subject interpretability.
Significance
These findings highlight the potential of personalized, physiology-guided hybrid learning with novel morphological descriptors for accurate and explainable BP monitoring in real-world settings.
Publication Details
- arXiv ID: arXiv:2609.13190 [cs.CV]
- Submitted: 11 Aug 2026
- Authors: Myung-Kyu Yi, Jongshill Lee, Jeyeon Lee, In Young Kim
- Subject: Computer Vision and Pattern Recognition (cs.CV)
- DOI: https://doi.org/10.48550/arXiv.2609.13190
via ArXiv CV