Key result
A cloud-based AI system analyzing 6,391 lesions from 62 patients identified that minimum contact force, duration, and ablation index predicted the need for additional touchup ablation (P<0.01).
Why the study?
Data created from catheter ablation lesions are typically lost due to logistical challenges with storage, retrieval, and analysis, which cloud technology may alleviate.
Does a cloud-based lesion data collection software identify predictors of the need for touchup ablation during pulmonary vein isolation in patients undergoing first-time AF ablation?
Population
62 patients undergoing first-time AF RF ablation (6391 PVI lesions)
Design
Observational cohort study
Authors
Loading...
May aid real-time ablation monitoring in PVI; leaves open whether targeting identified predictors improves outcomes.
Observational (n=62)
No
Does a cloud-based lesion data collection software identify predictors of the need for touchup ablation during pulmonary vein isolation in patients undergoing first-time AF ablation?
p-value: p=<0.01
A novel cloud-based machine learning system can effectively analyze detailed catheter ablation data to monitor protocol adherence and identify procedural predictors for touchup ablation during pulmonary vein isolation.
Kreidieh et al. (2022) conducted an observational in Atrial fibrillation (n=62). Cloud-based lesion data collection software (CARTONET) vs. Regions of first-pass isolation (RFPI) was evaluated on Predictors of additional (touchup) ablation in a segment (p=<0.01). A cloud-based AI system analyzing 6,391 lesions from 62 patients identified that minimum contact force, duration, and ablation index predicted the need for additional touchup ablation (P<0.01).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: