Why the study?
Improved risk stratification for post-stroke AF is needed, and whether brain MRI provides additional predictive value over clinical variables or age and heart rate variability remains controversial.
Does the addition of brain MRI-derived features improve the prediction of atrial fibrillation detected after ischemic stroke in patients with ischemic stroke?
Population
1,227 patients in the primary cohort and 462 in the external cohort
Comparison
ML models with MRI-derived features vs models with clinical variables or age and HRV alone
Design
Cohort study with external validation
Key result
Adding brain MRI-derived features to a clinical model improved prediction of atrial fibrillation detected after stroke (ROC-AUC 0.75 vs 0.67; p<0.01), but did not improve an age and HRV model.
Authors
Loading...
Supports adding MRI to post-stroke AF risk models; extends prior age- and HRV-based ML predictions.
Cohort (n=1,689)
Does the addition of brain MRI-derived features improve the prediction of atrial fibrillation detected after ischemic stroke in patients with ischemic stroke?
Absolute Event Rate: 0.75% vs 0.67%
p-value: p=<0.01
Brain MRI-derived features do not add significant predictive value for post-stroke atrial fibrillation beyond simple clinical variables like age and heart rate variability.
Schöls et al. (2026) conducted a cohort in Ischemic stroke (n=1,689). Brain MRI-derived features vs. Clinical variables or age and heart rate variability (HRV) alone was evaluated on Prediction of atrial fibrillation detected after stroke (AFDAS) (p=<0.01). Adding brain MRI-derived features to a clinical model improved prediction of atrial fibrillation detected after stroke (ROC-AUC 0.75 vs 0.67; p<0.01), but did not improve an age and HRV model.