AF-Mamba model uses TCN and Mamba for early atrial fibrillation prediction

Researchers have developed AF-Mamba, a novel deep learning architecture designed for the early prediction of atrial fibrillation (AF) onset. This model integrates Temporal Convolutional Networks (TCNs) with Mamba, a selective state-space model, to efficiently process long sequences of RR intervals. AF-Mamba demonstrates strong predictive performance, achieving high sensitivity and specificity in predicting AF one hour in advance, outperforming existing models while offering a favorable performance-efficiency trade-off. AI

IMPACT This model could improve early detection of atrial fibrillation, potentially leading to better patient outcomes and more efficient remote monitoring.

RANK_REASON The item is a research paper detailing a new deep learning model for a specific medical prediction task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• AF-Mamba
• arXiv
• atrial fibrillation
• Mamba
• Recurrent Neural Networks
• RR intervals
• TCN
• Temporal Convolutional Networks
• transformers

• paper
• model release
• other

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