Key result
An artificial neural network reconstructed cardiac activation maps directly from body surface potentials with a mean absolute activation time error of 4.69 ms and a correlation coefficient of 97.8%.
Why the study?
Does an artificial neural network accurately reconstruct cardiac activation maps directly from body surface potentials in simulated atrial data?
Does an artificial neural network accurately reconstruct cardiac activation maps directly from body surface potentials in simulated atrial data?
p-value: p=≤0.0001
An artificial neural network can accurately and robustly reconstruct atrial activation maps directly from body surface potentials in a simulated model, offering a potential non-invasive alternative to traditional electrocardiographic imaging.
Demonstrates feasibility of neural network-based mapping in simulated atrial models; leaves open human validation before clinical use.
Cardiac mapping is an important diagnostic tool to understand cardiac arrhythmias caused by an electrical disorder.
No takes yet. Share an insight, caveat, or question.
Karoui et al. (2019) studied Cardiac activation mapping (n=101). Artificial neural network vs. Reference simulated activation maps was evaluated on Mean absolute activation time error (AATE) (p=≤0.0001). An artificial neural network reconstructed cardiac activation maps directly from body surface potentials with a mean absolute activation time error of 4.69 ms and a correlation coefficient of 97.8%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: