SIFPBPNet: A Dual-Path Network for Wearable and Cuffless Blood Pressure Estimation via Individualized Steady-state Representation

• URL: http://arxiv.org/abs/2609.12690v1
• Date: Fri, 11 Sep 2026 10:36:46 GMT
• Title: SIFPBPNet: A Dual-Path Network for Wearable and Cuffless Blood Pressure Estimation via Individualized Steady-state Representation
• Abstract summary: Continuous and cuffless blood pressure (BP) monitoring is of great interest for low-cost and personalized cardiovascular health management.<n>We propose a dual-path architecture termed SIFPBPNet, which separately represents steady-state and instantaneous features.<n> Experiments on a large-scale wearable dataset demonstrate that SIFPBPNet achieves a Mean Absolute Error (MAE) of 8.57 and 5.97 mmHg for systolic and diastolic BP, respectively.
• Score: 7.798066931950822
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continuous and cuffless blood pressure (BP) monitoring using photoplethysmography (PPG) is of great interest for low-cost and personalized cardiovascular health management. However, significant population heterogeneity and the "one-to-many mapping" problem, where similar waveforms across individuals correspond to different BP levels, limit the accuracy of conventional population-based models. To address this challenge, we propose a dual-path architecture termed SIFPBPNet, which separately represents steady-state and instantaneous features, through a Steady-state Feature Path (SFP) and an Instantaneous Feature Path (IFP). The SFP employs a Graph Attention Network (GAT) to extract individual-specific and long-term characteristics from multi-day historical PPG trajectories. In parallel, the IFP captures short-term dynamics from current PPG segments and incorporates the steady-state prior via a cross-attention mechanism. Experiments on a large-scale wearable dataset demonstrate that SIFPBPNet achieves a Mean Absolute Error (MAE) of 8.57 and 5.97 mmHg for systolic and diastolic BP, respectively, outperforming state-of-the-art models. Furthermore, the SFP module consistently improves performance when integrated into various backbone architectures, yielding 2.8-13.1% relative MAE reductions for systolic BP. These results highlight the strong generalizability and plug-and-play transferability of the SFP module, underscoring its great potential for accurate cuffless BP monitoring.

Related papers

• Single-Beat Cuffless Blood Pressure Estimation Using Ear-PPG and ECG with a Lightweight Hybrid Learning Framework [0.7015649288674913]
  Continuous cuffless blood pressure (BP) monitoring is challenging due to motion artifacts, physiological variability, and the limited robustness of conventional pulse transit time (PTT) models under dynamic conditions.<n>Here, we show that discriminative BP-related information is preserved at the single-beat level and present a lightweight multi-modal wearable framework for continuous BP estimation.
  arXiv  Detail & Related papers  (2026-07-29T16:00:39Z)
• DMT: Demographic Conditioning, Morphology-Enhanced Transformer for Cuffless Blood Pressure Estimation from PPG Signals [4.839226773937583]
  Blood pressure (BP) is a key marker for cardiovascular risk assessment and therapeutic decision-making.<n>Photoplethysmography ( PPG) enables low-cost, wearable-friendly cuffless BP estimation.<n>We propose a Transformer-based network for cuffless BP estimation from PPG signal.
  arXiv  Detail & Related papers  (2026-06-09T17:23:07Z)
• Spectral- and Energy-efficient Multi-BS Multi-RIS Pinching-antenna Systems: A GNN-based Approach [62.31891278787162]
  This paper investigates coordinated downlink transmission in a multi-base station (multi-BS) multi-reconfigurable intelligent surface (multi-RIS)-assisted pinching-antenna (PA) system.<n>We formulate sum rate (SR) and energy efficiency (EE) problems by jointly optimizing PA placement, RIS phase shifts, transmit beamforming, and BS-UE association.<n>We propose a three-stage graph neural network (GNN) that integrates heterogeneous and homogeneous graph representations and is trained end-to-end in an unsupervised manner.
  arXiv  Detail & Related papers  (2026-05-02T07:30:37Z)
• scPPDM: A Diffusion Model for Single-Cell Drug-Response Prediction [44.96130504547205]
  This paper introduces scPPDM, the first diffusion-based framework for single-cell drug-response prediction from scRNA-seq data.<n>scPPDM couples two condition channels, pre-perturbation state and drug with dose, in a unified latent space via non-concatenative GD-Attn.
  arXiv  Detail & Related papers  (2025-10-08T16:17:39Z)
• PHASE-Net: Physics-Grounded Harmonic Attention System for Efficient Remote Photoplethysmography Measurement [63.007237197267834]
  Existing deep learning methods are mostly physiological monitoring and lack theoretical robustness.<n>We propose a physics-informed r paradigm derived from the Navier-Stokes equations of hemodynamics, showing that the pulse signal follows a second-order system.<n>This provides a theoretical justification for using a Temporal Conal Network (TCN)<n>Phase-Net achieves state-of-the-art performance with strong efficiency, offering a theoretically grounded and deployment-ready r solution.
  arXiv  Detail & Related papers  (2025-09-29T14:36:45Z)
• BalancedDPO: Adaptive Multi-Metric Alignment [44.051100004689296]
  We present BalancedDPO, a novel extension of Direct Preference Optimization (DPO)<n>We simultaneously align T2I diffusion models with multiple metrics, including human preference, CLIP score, and aesthetic quality.<n>Our evaluations show that BalancedDPO achieves state-of-the-art results, outperforming existing approaches across all major metrics.
  arXiv  Detail & Related papers  (2025-03-16T17:06:00Z)
• Finetuning and Quantization of EEG-Based Foundational BioSignal Models on ECG and PPG Data for Blood Pressure Estimation [46.36100528165335]
  Photoplethysmography and electrocardiography can potentially enable continuous blood pressure (BP) monitoring.<n>Yet accurate and robust machine learning (ML) models remains challenging due to variability in data quality and patient-specific factors.<n>In this work, we investigate whether a model pre-trained on one modality can effectively be exploited to improve the accuracy of a different signal type.<n>Our approach achieves near state-of-the-art accuracy for diastolic BP and surpasses by 1.5x the accuracy of prior works for systolic BP.
  arXiv  Detail & Related papers  (2025-02-10T13:33:12Z)
• TransfoRhythm: A Transformer Architecture Conductive to Blood Pressure Estimation via Solo PPG Signal Capturing [5.255373360156652]
  The paper introduces the TransfoRhythm framework, a Transformer-based architecture built upon the recently released physiological database, MIMIC-IV.<n>To our knowledge, this paper represents the first study to apply the MIMIC IV dataset for cuff-less BP estimation.
  arXiv  Detail & Related papers  (2024-04-15T00:36:33Z)
• Consistency Regularization for Deep Face Anti-Spoofing [69.70647782777051]
  Face anti-spoofing (FAS) plays a crucial role in securing face recognition systems. Motivated by this exciting observation, we conjecture that encouraging feature consistency of different views may be a promising way to boost FAS models. We enhance both Embedding-level and Prediction-level Consistency Regularization (EPCR) in FAS.
  arXiv  Detail & Related papers  (2021-11-24T08:03:48Z)
• A Deep Learning Approach to Predict Blood Pressure from PPG Signals [10.028103259763352]
  Blood Pressure (BP) is one of the four primary vital signs indicating the status of the body's vital (life-sustaining) functions. We propose an advanced data-driven approach that uses a three-layer deep neural network to estimate BP based on PPG signals.
  arXiv  Detail & Related papers  (2021-07-30T22:45:34Z)
• PPG2ABP: Translating Photoplethysmogram (PPG) Signals to Arterial Blood Pressure (ABP) Waveforms using Fully Convolutional Neural Networks [1.0045192779791103]
  We develop a method to predict the continuous arterial blood pressure (ABP) waveform through a non-invasive approach using photoplethysmogram signals. We present, PPG2ABP, a deep learning based method, that manages to predict the continuous ABP waveform from the input PPG signal, with a mean absolute error of 4.604 mmHg. The more astounding success of PPG2ABP turns out to be that the computed values of DBP, MAP and SBP from the predicted ABP waveform outperforms the existing works under several metrics.
  arXiv  Detail & Related papers  (2020-05-04T17:22:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.