Causal machine learning for assessing the effectiveness of off-label use of amiodarone in new-onset atrial fibrillation

Off-label drug use, i.e., uses of a drug that differ from what regulatory authorities have approved, is common, occurring overall in up to 36% of prescriptions. Yet, the effectiveness across different patient subgroups is often poorly understood. In this study, we demonstrate how one can use causal machine learning (ML) together with real-world data to identify which patient groups are most likely to benefit from off-label use. Specifically, we assessed the effectiveness of off-label use of amiodarone in patients with new-onset atrial fibrillation (NOAF). NOAF can often lead to hemodynamic instability and rapid ventricular response, so that hemodynamic stability should be restored. We developed a causal ML model to predict individualized treatment effects (ITEs) of off-label amiodarone use on the probability of returning to hemodynamic stability. We used real-world data from the U.S. to develop the causal ML model and externally evaluated that model on real-world data from the Netherlands. Our predicted ITEs show that 44.8% (95% confidence interval [CI]: 38.4% to 51.0%) of patients benefit from off-label use of amiodarone with large heterogeneity: amiodarone is predicted to increase the probability of restoring hemodynamic stability by a mean of 0.5 percentage points (pp), with an interquartile range (IQR) of -1.1 pp to 1.0 pp, in the external dataset from the Netherlands. Using these ITEs, we defined a personalized treatment rule, which could increase the number of patients achieving hemodynamic stability by 4.4% (95% CI: 1.0% to 7.8%) compared to current practice. Additionally, we studied which biomarkers are predictive of treatment effect heterogeneity and found that patients with higher blood pressure may benefit most from off-label use of amiodarone. Altogether, our study shows the potential of causal ML together with real-world data in identifying patients who benefit from off-label drug use.