New CVAF-Net model estimates cardiac output from PPG signals

Researchers have developed a novel deep learning model called the Cross-View Attention Fusion Network (CVAF-Net) for estimating cardiac output (CO) from short photoplethysmography (PPG) signals. This model processes both raw PPG data and a feature sequence map (FSM) derived from physiological priors, fusing them using cross-view attention. CVAF-Net demonstrated strong performance across multiple datasets, achieving a mean absolute error of 0.19 L/min on simulated data and outperforming several benchmark methods. Notably, it is significantly more computationally efficient than existing Transformer-based models, reducing FLOPs by twelvefold while maintaining high accuracy and physiological consistency. AI

IMPACT This novel deep learning approach offers a more computationally efficient method for continuous, wearable-based cardiac output monitoring.

RANK_REASON The cluster contains a research paper detailing a new model. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Cross-View Attention Fusion Network
• CVAF-Net
• transformer
• Yaowen Zhang

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →