A novel dynamic risk score to predict clinically significant bleeding after 3 months of anticoagulation in patients with incident venous thromboembolism and without active cancer

BACKGROUND: After 3 months of treatment, clinicians and patients need to decide whether to continue anticoagulant therapy long-term, which is informed by bleeding risk; to date, we have not had a good way to estimate that risk. OBJECTIVES: To develop a dynamic, broad, treatment-adjusted risk score for clinically significant bleeding (CSB). METHODS: UK Clinical Practice Research Datalink (2001-2020) was used to generate a retrospective cohort of patients with first VTE who had received 3 months of anticoagulation. Covariates were collected at baseline and as time-varying data. Hazards with 95% confidence intervals (CIs) were estimated using a Fine-Gray model. A dynamic model with an additive (logarithmic) scoring scheme was developed from sub-distribution hazard ratios. Discrimination was expressed by the C-statistic. RESULTS: In 51,621 patients with VTE, 3301 CSB events were identified in 206,298 person-years of observation. The 10-year incidence rate for CSB was 1.60 per 100 person-years. The model incorporated 18 independent predictors of CSB, assigning risk scores from 0 to ≥14. Risk of CSB decreased over 10 years but within each year it increased by point category; ranging from 0.60% to 18.1% in the first year (0-≥14 points). Calibration slopes were 0.81 (0.76-0.87) base model, 0.95 (0.88-1.02) extended model; absolute intercepts <0.001 in both. Discrimination was stable, C-statistic 0.78 (0.77-0.79). CONCLUSIONS: Our dynamic score effectively identifies patients at risk of CSB, following 3 months of anticoagulant therapy, with good discrimination. It enables dynamic prediction of bleeding risk over time, accounting for anticoagulation status.