Arrhythmias & electrophysiology
Application of artificial intelligence to analyze data from randomized controlled trials: An example from DECAAF II
Authors' conclusion
Applying causal ML on random controlled trial datasets helped us identify groups of patients that profited from the treatment of interest in an efficient and unbiased manner.
Study context
- Population
- DECAAF II trial participants undergoing ablation
- Comparison
- Fibrosis-guided ablation plus pulmonary vein isolation (PVI) vs PVI alone, by subgroup
- Primary endpoint
- Recurrence of atrial tachyarrhythmia (aTA)
Methodological detailscausal machine learning (causal tree learning)
- Causal machine learning (causal tree learning)
Primary result
As reported in the abstract
aTA recurrence by age subgroup (cutoff 58 years)
Fibrosis-guided ablation vs PVI-onlyHazard ratio (95% CI)P value
Older patients
1.06(0.77–1.47)
P = 0.72Younger patients
0.50(0.28–0.90)
P = 0.02Original publication
Application of artificial intelligence to analyze data from randomized controlled trials: An example from DECAAF II. Heart Rhythm. Published 13 January 2025. doi:10.
Summarised from the published abstract; every number is checked against it