Arrhythmias & electrophysiology
Comparison of the characteristics between machine learning and deep learning algorithms for ablation site classification in a novel cloud-based system
Authors' conclusion
The R14 model significantly improved sensitivity and PPV compared with the R12.1 model. The tendency for predicting potential reconnection sites was similar to that of the previous version, the R12 model.
Study context
- Population
- Atrial fibrillation ablation cases analysed with the cloud-based CARTONET systematrial fibrillation ablation cases, overall tags of 39,169 points and gap prediction of 625 segments
- Participants
- 396 cases
- Index test or model
- CARTONET R12.1 vs CARTONET R14 models
- Target condition
- automated anatomic location (ablation site classification)
Performance
As reported in the abstract
| Test or model | Sensitivity | PPV |
|---|---|---|
| R12.1 | 71.2% | 85.6% |
| R14 | 77.5% | 86.2% |
Sensitivity
R12.171.2%
R1477.5%
PPV
R12.185.6%
R1486.2%
Further findings
Incidence of reconnections
- Posterior area of the right pulmonary veins
- 98/238 [41.2%]
- Posterior area of the left pulmonary veins
- 190/387 [49.1%]
Possibility of reconnection (highest in the roof area)
- Roof area, right pulmonary veins
- 14% [5.5%-41%]
- Roof area, left pulmonary veins
- 16% [8%-22%]
Original publication
Comparison of the characteristics between machine learning and deep learning algorithms for ablation site classification in a novel cloud-based system. Heart Rhythm. Published 17 March 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →