Cross-View Attention Fusion Net: A Prior-Guided Dual-View Representation Learning for Cardiac Output Estimation from Short-Term PPG Signals

TL;DR

The paper introduces CVAF-Net, a dual-view deep learning model that fuses raw PPG signals and prior-guided features via cross-view attention for accurate, efficient cardiac output estimation from short-term PPG segments.

Contribution

It proposes a novel prior-guided dual-view deep learning architecture that effectively combines raw PPG data and structured prior information for improved CO estimation.

Findings

CVAF-Net outperformed most benchmark methods in CO estimation accuracy.

Achieved comparable performance to state-of-the-art Transformer models with significantly fewer FLOPs.

Demonstrated physiologically plausible CO estimates correlated with age, heart rate, and vascular resistance.

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 ($\rho = -0.274$), heart rate ($\rho = 0.894$), and systemic vascular resistance ($\rho = -0.740$). These findings indicate that CVAF-Net provides an accurate, computationally efficient, and generalizable approach for continuous wearable-based CO monitoring.