TAILORED-AF
Trial question
What is the role of artificial intelligence-guided ablation of spatio-temporal dispersion areas in addition to pulmonary vein isolation in patients with drug-refractory persistent AF?
Study design
Multi-center
Double blinded
RCT
Population
Characteristics of study participants
21.0% female
79.0% male
N = 370
370 patients (77 female, 293 male).
Inclusion criteria: patients with drug-refractory persistent AF.
Key exclusion criteria: paroxysmal and short-standing AF < 3 months; long-standing persistent AF > 5 years; ≥ 2 previous ineffective cardioversion sessions in case of undetermined AF duration; severe obesity; AF secondary to an obvious reversible cause; inadequate anticoagulation; contraindications to anticoagulation.
Interventions
N=187 tailored ablation strategy (artificial intelligence-guided ablation of spatio-temporal dispersion electrograms in combination with pulmonary vein antrum isolation).
N=183 anatomical ablation strategy (pulmonary vein antrum isolation).
Primary outcome
Freedom from atrial fibrillation at 1 year
88%
70%
88.0 %
66.0 %
44.0 %
22.0 %
0.0 %
Tailored ablation
strategy
Anatomical ablation
strategy
Significant
increase ▲
NNT = 5
Significant increase in freedom from AF at 1 year (88% vs. 70%; HR 2.94, 95% CI 1.75 to 4.77).
Secondary outcomes
No significant difference in freedom from any atrial arrhythmia at 12 months after one or two ablation procedures (76% vs. 71%; HR 0.77, 95% CI 0.51 to 1.16).
No significant difference in freedom from any atrial arrhythmia at 12 months after one ablation procedure (60% vs. 60%; HR 0.94, 95% CI 0.68 to 1.31).
No significant difference in repeat catheter ablation procedure (27.8% vs. 21.5%; AD 6.3%, 95% CI -2.89 to 15.49).
Safety outcomes
No significant differences in death, cerebrovascular events, or major treatment-related serious adverse events.
Conclusion
In patients with drug-refractory persistent AF, tailored ablation strategy was superior to anatomical ablation strategy with respect to freedom from AF at 1 year.
Reference
Isabel Deisenhofer, Jean-Paul Albenque, Sonia Busch et al. Artificial intelligence for individualized treatment of persistent atrial fibrillation: a randomized controlled trial. Nat Med. 2025 Feb 14. Online ahead of print.
Open reference URL