Arrhythmias & electrophysiology
Validation of a machine learning algorithm to identify pulmonary vein isolation during ablation procedures for the treatment of atrial fibrillation: results of the PVISION study
Authors' conclusion
This study validated an automated algorithm using machine learning to assess the isolation status of pulmonary veins in patients undergoing PVI with different ablation modalities. The algorithm reached an AUC of 92%, with both sensitivity and specificity exceeding the primary study endpoints.
Study context
- Population
- Consecutive patients scheduled for pulmonary vein isolation (PVI) for AF at four centres498 electrograms (EGMs) analysed
- Participants
- 89 patients
- Comparison
- Automated machine learning algorithm vs expert (operator) opinion for PV isolation status
- Outcome
- Sensitivity and specificity exceeding 80%
Methodological detailsprospective, multicentre
- Prospective
- Multicentre
Performance
As reported in the abstract
Detection of PV isolation status
| Test or model | AUC | Sensitivity | Specificity |
|---|---|---|---|
| Algorithm | 92% | 86% | 87% |
Algorithm
AUC92%
Sensitivity86%
Specificity87%
Further findings
| Outcome | Algorithm |
|---|---|
| Accuracy in classifying time of isolation | |
| Accuracy | 87% |
Original publication
Validation of a machine learning algorithm to identify pulmonary vein isolation during ablation procedures for the treatment of atrial fibrillation: results of the PVISION study. Europace. Published 29 April 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →