Speaker
Description
In this paper, a novel application of deep learning is proposed, to predict and optimize key parameters in cardiac Pulsed-Field Ablation (PFA) treatments. Building on our extensive experience and on a large set of experimental data, we leveraged artificial neuronal networks to accurately predict the ablated area, optimize electrode configurations, and tune various heterogeneous parameters, including signal characteristics. Tests performed on experimental data available in the literature demonstrate that deep learning algorithms can effectively predict PFA treatment parameters using both single-target and multi-target networks with comparable performance. The overall accuracy of the predictions confirms the potential of this approach for optimizing PFA treatments. The promising results underscore the power of deep learning in leveraging extensive PFA clinical data and guiding future applications. This approach indeed represents a significant advancement toward developing patient-specific PFA protocols.
