The Rapid Prediction of Focal Wavefront Origins

Saluja, Deepak; Bar-On, Tal; Hayam, Gal; Kassotis, John; Kostis, William J.; Coromilas, James

doi:10.1016/j.jacep.2020.05.024

Cited by 1 publication

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The principle finding of this study was that a GCN could be trained to predict isthmus areas in SRRATs to as close as a centroid-centroid distance of 8.2 (3.5, 14.4) mm in the training group and 7.3 (2.5, 16.1) mm in the test group, a degree of precision which is comparable to an algorithm reported in the prediction of focal arrhythmia origin. 18 Similar results between the training and test groups suggest that the network adequately extrapolates learned data to unknown data and avoids overfitting, a common limitation in DLNs. To our knowledge, this is the first reported application of a DLN for isthmus prediction and demonstrates the potential utility of DLNs in atrial arrhythmia mapping.…”

Section: Isthmus Predictionsmentioning

confidence: 65%

Automated prediction of isthmus areas in scar‐related atrial tachycardias using artificial intelligence

Saluja,

Huang,

Majumder

et al. 2024

Cardiovasc electrophysiol

Self Cite

View full text Add to dashboard Cite

IntroductionAblation of scar‐related reentrant atrial tachycardia (SRRAT) involves identification and ablation of a critical isthmus. A graph convolutional network (GCN) is a machine learning structure that is well‐suited to analyze the irregularly‐structured data obtained in mapping procedures and may be used to identify potential isthmuses.MethodsElectroanatomic maps from 29 SRRATs were collected, and custom electrogram features assessing key tissue and wavefront properties were calculated for each point. Isthmuses were labeled off‐line. Training data was used to determine the optimal GCN parameters and train the final model. Putative isthmus points were predicted in the training and test populations and grouped into proposed isthmus areas based on density and distance thresholds. The primary outcome was the distance between the centroids of the true and closest proposed isthmus areas.ResultsA total of 193 821 points were collected. Thirty isthmuses were detected in 29 tachycardias among 25 patients (median age 65.0, 5 women). The median (IQR) distance between true and the closest proposed isthmus area centroids was 8.2 (3.5, 14.4) mm in the training and 7.3 (2.8, 16.1) mm in the test group. The mean overlap in areas, measured by the Dice coefficient, was 11.5 ± 3.2% in the training group and 13.9 ± 4.6% in the test group.ConclusionA GCN can be trained to identify isthmus areas in SRRATs and may help identify critical ablation targets.

show abstract

Section: Isthmus Predictionsmentioning

confidence: 65%