Arrhythmias & electrophysiology
Artificial Intelligence–Based Feature Analysis of Pulmonary Vein Morphology on Computed Tomography Scans and Risk of Atrial Fibrillation Recurrence After Catheter Ablation: A Multi-Site Study
Authors' conclusion
This largest multi-institutional study to date revealed associations between artificial intelligence-extracted morphological features of the primary PV branches with AF recurrence in 809 patients from 3 sites.
Study context
- Population
- Patients undergoing catheter ablation of atrial fibrillation (AF) with CT imaging (Cleveland Clinic, Vanderbilt University, University Hospitals of Cleveland)
- Participants
- 809 patients3 sites
- Comparison
- AI-derived radiomic features of primary vs secondary vs combined pulmonary vein (PV) branches for predicting AF recurrence
- Outcome
- AF recurrence after catheter ablation
Methodological detailsmulti-site, 3 sites, AI-based CT segmentation, independent validation set, 48 fractal-based and 12 shape-based radiomic features extracted from primary and secondary PV branches
- Multi-site
- 3 sites
- AI-based CT segmentation
- Independent validation set
- 48 fractal-based and 12 shape-based radiomic features extracted from primary and secondary PV branches
Performance
As reported in the abstract
AF recurrence prediction
| Test or model | AUC D1 | AUC D2 | AUC D3 |
|---|---|---|---|
| Mp | 0.73 | 0.71 | 0.70 |
Mp
AUC D10.73
AUC D20.71
AUC D30.70
Original publication
Artificial Intelligence–Based Feature Analysis of Pulmonary Vein Morphology on Computed Tomography Scans and Risk of Atrial Fibrillation Recurrence After Catheter Ablation: A Multi-Site Study. Circ Arrhythm Electrophysiol. Published 3 December 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →