Cross-View Attention Fusion Net: A Prior-Guided Dual-View Representation Learning for Cardiac Output Estimation from Short-Term PPG Signals
Abstract
Accurate cardiac output (CO) estimation from photoplethysmography (PPG) is promising for unobtrusive hemodynamic monitoring, but remains difficult since CO is jointly determined by cardiac function and vascular tone. Conventional feature-based models use physiologically meaningful PPG descriptors, yet depend on accurate pulse detection and may miss latent temporal relationships. In contrast, fully end-to-end deep learning models learn directly from raw PPG but often underuse established PPG-derived prior information. Here, we introduce the Cross-View Attention Fusion Network (CVAF-Net), a prior-guided dual-view deep learning model for CO estimation from short, fixed-length PPG segments. CVAF-Net processes raw PPG as a temporal view and a feature sequence map (FSM) as a structured prior-guided view, and fuses the two representations through cross-view attention. The model was independently evaluated using 5-, 15-, and 30-s segments from three datasets: simulated pulse waves (3323 subjects), vasoconstriction provocation (79 subjects), and resting/cycling activities (10 subjects), and was compared with multiple machine learning and deep learning benchmarks. CVAF-Net outperformed most benchmark methods and achieved performance comparable to a state-of-the-art Transformer-based model, with a mean absolute error (MAE) of 0.19 L/min (MAPE: 3.95%) on simulated data and high accuracy in real-world settings (minimum MAE: 1.20 L/min). Importantly, CVAF-Net reduced FLOPs by twelvefold compared with the leading Transformer-based model. Plausibility analysis showed physiologically consistent CO estimates, with expected correlations with age (ρ= −0.274), heart rate (ρ= 0.894), and systemic vascular resistance (ρ= −0.740). These findings indicate that CVAF-Net provides an accurate, computationally efficient, and generalizable approach for continuous wearable-based CO monitoring.
Related
- Fusing Global Diagnostic Signals and Spectral Data for Electron and Ion Temperature Profile Prediction on EAST via Attention-based Neural Networks
- Geometric estimation of NV charge-state contributions from a low-dimensional spectral representation
- Compact and stable representation of real-frequency spectral functions for machine learning
- Improving Signals, Declining Encoder: A Known-Answer Test of Label-Free Monitoring in Self-Supervised Learning
- Deep Learning Detection of Beyond-General-Relativity Deviations in Gravitational-Wave Signals: A Detection-Threshold Study with Real LIGO Noise
BibTeX
@misc{zhang2026crossview,
title = {{Cross-View Attention Fusion Net: A Prior-Guided Dual-View Representation Learning for Cardiac Output Estimation from Short-Term PPG Signals}},
author = {Yaowen Zhang and Bo Cui and Libera Fresiello and Peter H. Veltink and Dirk W. Donker and Ying Wang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2605.19666},
eprint = {2605.19666},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.19666},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Cross-View Attention Fusion Net: A Prior-Guided Dual-View Representation Learning for Cardiac Output Estimation from Short-Term PPG Signals
AU - Yaowen Zhang
AU - Bo Cui
AU - Libera Fresiello
AU - Peter H. Veltink
AU - Dirk W. Donker
AU - Ying Wang
PY - 2026
DA - 2026/10/09
PB - arXiv
DO - 10.48550/arxiv.2605.19666
UR - https://arxiv.org/abs/2605.19666
AB - Accurate cardiac output (CO) estimation from photoplethysmography (PPG) is promising for unobtrusive hemodynamic monitoring, but remains difficult since CO is jointly determined by cardiac function and vascular tone. Conventional feature-based models use physiologically meaningful PPG descriptors, yet depend on accurate pulse detection and may miss latent temporal relationships. In contrast, fully end-to-end deep learning models learn directly from raw PPG but often underuse established PPG-derived prior information. Here, we introduce the Cross-View Attention Fusion Network (CVAF-Net), a prior-guided dual-view deep learning model for CO estimation from short, fixed-length PPG segments. CVAF-Net processes raw PPG as a temporal view and a feature sequence map (FSM) as a structured prior-guided view, and fuses the two representations through cross-view attention. The model was independently evaluated using 5-, 15-, and 30-s segments from three datasets: simulated pulse waves (3323 subjects), vasoconstriction provocation (79 subjects), and resting/cycling activities (10 subjects), and was compared with multiple machine learning and deep learning benchmarks. CVAF-Net outperformed most benchmark methods and achieved performance comparable to a state-of-the-art Transformer-based model, with a mean absolute error (MAE) of 0.19 L/min (MAPE: 3.95%) on simulated data and high accuracy in real-world settings (minimum MAE: 1.20 L/min). Importantly, CVAF-Net reduced FLOPs by twelvefold compared with the leading Transformer-based model. Plausibility analysis showed physiologically consistent CO estimates, with expected correlations with age (ρ= −0.274), heart rate (ρ= 0.894), and systemic vascular resistance (ρ= −0.740). These findings indicate that CVAF-Net provides an accurate, computationally efficient, and generalizable approach for continuous wearable-based CO monitoring.
ER -