Key result
Deep learning-based DEAP mapping reconstructs membrane potentials to improve substrate characterization in non-paroxysmal AF.
Why the study?
Catheter ablation for non-paroxysmal atrial fibrillation is limited by inadequate identification of arrhythmogenic substrates due to reliance on manual annotation of excitation timing in electrogram-based mapping.
Does deep learning-based membrane potential reconstruction improve the identification of arrhythmogenic substrates compared to existing manual annotation mapping in patients with non-paroxysmal atrial fibrillation?
Does deep learning-based membrane potential reconstruction improve the identification of arrhythmogenic substrates compared to existing manual annotation mapping in patients with non-paroxysmal atrial fibrillation?
A deep learning-based mapping tool (DEAP mapping) is proposed to overcome the limitations of manual electrogram annotation in identifying complex arrhythmogenic substrates for non-paroxysmal atrial fibrillation ablation.
Current mapping may miss substrates in non-PAF ablation; leaves open automated annotation for complex rhythms.
Catheter ablation for non-paroxysmal atrial fibrillation (non-PAF) remains limited by inadequate identification of arrhythmogenic substrates. Existing electrogram-based mapping relies on manual annotation of excitation timing, which degrades under complex fibrillatory conduction patterns and fails to reveal key conduction abnormalities.
No takes yet. Share an insight, caveat, or question.
Seno et al. (2026) studied this question. Deep learning-based DEAP mapping reconstructs membrane potentials from annotation-free unipolar electrograms to improve substrate characterization in non-paroxysmal atrial fibrillation.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: