Individualised prediction of major bleeding in patients with atrial fibrillation treated with anticoagulation

Background Anticoagulation in atrial fibrillation (AF) increases the risk of major bleeding. No predictive model has hitherto provided estimates of the absolute risk for individual patients. Aim To predict the individual 1-year risk of major bleeding in patients with AF taking anticoagulants and evaluate the importance of individual risk factors. Design A nationwide register-based cohort study. Participants Danish patients with first-time non-valvular AF who redeemed anticoagulants within 7 days after diagnosis. Method The individual absolute risk of major bleeding was estimated from a logistic regression model (the Calculator of Absolute Bleeding Risk/CABS model) utilising the same risk factors as HAS-BLED, except allowing non-linear age effects, and allowing effect modification of all factors according to history of bleeding. The logistic regression was assessed in term of discrimination using the Area Under the ROC curve (AUC) and calibration. Results Among 76,102 patients with AF redeeming anticoagulants, 2,406 suffered a major bleeding within 1 year. History of bleeding was the strongest predictor, and age significantly modified the risk. The CABS model superseded HAS-BLED score with regards to discrimination (AUC 0.646 vs 0.615, p<0.001) and calibrated well. A typical male patient was 70-years old without any risk factors and he had a 1-year bleeding risk of 1.4% (1.2; 1.6) while a typical female patient was 73-years old, had hypertension and a 1-year bleeding risk of 2.2% (1.9;2.6). Conclusion We propose CABS as a tool for prediction of individual absolute risks of major bleeding in patients with AF taking anticoagulant. The predicted absolute risk can be used for patient counselling.