Key result
A machine learning pipeline using body surface potential maps achieved classification accuracies mostly above 84% for localizing atrial ectopic foci, even in the presence of fibrosis.
Why the study?
Can a machine learning pipeline accurately localize atrial ectopic foci from multi-electrode signals in the presence of atrial fibrosis?
Can a machine learning pipeline accurately localize atrial ectopic foci from multi-electrode signals in the presence of atrial fibrosis?
A machine learning pipeline can accurately localize focal atrial tachycardia sources from body surface potential maps even in the presence of atrial fibrosis, though high fibrosis levels reduce spatial precision.
No takes yet. Share an insight, caveat, or question.
May aid noninvasive atrial ectopy localization; leaves open human validation before clinical use.
Godoy et al. (2018) studied Focal Atrial Tachycardia. Machine learning pipeline using body surface potential maps was evaluated on Classification accuracy of ectopic foci localization. A machine learning pipeline using body surface potential maps achieved classification accuracies mostly above 84% for localizing atrial ectopic foci, even in the presence of fibrosis.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: