Key result
Site-specific risk prediction models for major gastrointestinal bleeding (c-index 0.75) and intracranial hemorrhage (c-index 0.72) provided better risk discrimination than a general model for any major bleeding.
Why the study?
Reasons for the relatively poor performance of bleeding prediction models are not well understood but may relate to differences in predictors for various anatomical sites of bleeding.
Does the performance of bleeding risk prediction models vary by anatomic site, indication, and time since initiation in patients on antithrombotic therapy?
Observational (n=57,813)
Yes
Does the performance of bleeding risk prediction models vary by anatomic site, indication, and time since initiation in patients on antithrombotic therapy?
Bleeding risk prediction models perform better when tailored to specific anatomical sites (e.g., GI vs ICH) and their accuracy declines over time since antithrombotic initiation.
Site-specific models may improve bleeding prediction accuracy; leaves open whether they warrant adoption over general models in antithrombotic patients.
Background Reasons for the relatively poor performance of bleeding prediction models are not well understood but may relate to differences in predictors for various anatomical sites of bleeding. Methods We pooled individual participant data from four randomized controlled trials of antithrombotic therapy in patients with coronary and peripheral artery diseases, embolic stroke of undetermined source (ESUS), or atrial fibrillation. We examined discrimination and calibration of models for any major bleeding, major gastrointestinal (GI) bleeding, and intracranial hemorrhage (ICH), according to the time since initiation of antithrombotic therapy, and indication for antithrombotic therapy. Results Of 57,813 patients included, 1,948 (3.37%) experienced major bleeding, including 717 (1.24%) major GI bleeding and 274 (0.47%) ICH. The model derived to predict major bleeding at 1 year from any site (c-index, 0.69, 95% confidence interval [CI], 0.68–0.71) performed similarly when applied to predict major GI bleeding (0.71, 0.69–0.74), but less well to predict ICH (0.64, 0.61–0.69). Models derived to predict GI bleeding (0.75, 0.74–0.78) and ICH (0.72, 0.70–0.79) performed better than the general major bleeding model. Discrimination declined over time since the initiation of antithrombotic treatment, stabilizing at approximately 2 years for any major bleeding and major GI bleeding and 1 year for ICH. Discrimination was best for the model predicting ICH in the ESUS population (0.82, 0.78–0.92) and worst for the model predicting any major bleeding in the coronary and peripheral artery disease population (0.66, 0.65–0.69). Conclusion Performance of risk prediction models for major bleeding is affected by site of bleeding, time since initiation of antithrombotic therapy, and indication for antithrombotic therapy.
No takes yet. Share an insight, caveat, or question.
Bhagirath et al. (2024) conducted an observational in Cardiovascular disease requiring antithrombotic therapy (CAD, PAD, ESUS, atrial fibrillation) (n=57,813). Site-specific bleeding risk prediction models vs. General major bleeding risk prediction model was evaluated on Discrimination (c-index) for predicting major gastrointestinal bleeding at 1 year (95% CI 0.74-0.78). Site-specific risk prediction models for major gastrointestinal bleeding (c-index 0.75) and intracranial hemorrhage (c-index 0.72) provided better risk discrimination than a general model for any major bleeding.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: