Key result
Random forest models outperform HAS-BLED in predicting 1-year bleeding hospitalization for AF patients on DOACs.
Why the study?
Predicting major bleeding in nonvalvular AF patients on DOACs is crucial for personalized care, especially given alternative stroke prevention strategies with lower bleeding risk.
Do machine learning models improve the prediction of hospitalization for bleeding compared to conventional risk scores in nonvalvular AF patients on DOACs?
Cohort (n=24,468)
No
Do machine learning models improve the prediction of hospitalization for bleeding compared to conventional risk scores in nonvalvular AF patients on DOACs?
Effect estimate: AUC 0.76 (95% CI 0.70-0.81)
p-value: p=<0.001
Machine learning models, specifically random forest, significantly outperform conventional risk scores like HAS-BLED in predicting bleeding hospitalizations in AF patients on DOACs.
Machine learning may enhance bleeding prediction over HAS-BLED in AF on DOACs; hypothesis-generating and requires prospective validation before practice change.
Predicting major bleeding in nonvalvular atrial fibrillation (AF) patients on direct oral anticoagulants (DOACs) is crucial for personalized care. Alternatives like left atrial appendage closure devices lower stroke risk with fewer nonprocedural bleeds. This study compares machine learning (ML) models with conventional bleeding risk scores (HAS-BLED, ORBIT, and ATRIA) for predicting bleeding events requiring hospitalization in AF patients on DOACs at their index cardiologist visit. This retrospective cohort study used electronic health records from 2010 to 2022 at the University of Pittsburgh Medical Center. It included 24,468 nonvalvular AF patients (age ≥18) on DOACs, excluding those with prior significant bleeding or warfarin use. The primary outcome was hospitalization for bleeding within one year, with follow-up at one, two, and five years. ML algorithms (logistic regression, classification trees, random forest, XGBoost, k-nearest neighbor, naïve Bayes) were compared for performance. Of 24,468 patients, 553 (2.3%) had bleeding within one year, 829 (3.5%) within two years, and 1,292 (5.8%) within five years. ML models outperformed HAS-BLED, ATRIA, and ORBIT in 1-year predictions. The random forest model achieved an AUC of 0.76 (0.70 to 0.81), G-Mean of 0.67, and net reclassification index of 0.14 compared to HAS-BLED's AUC of 0.57 (p < 0.001). ML models showed superior results across all timepoints and for hemorrhagic stroke. SHAP analysis identified new risk factors, including BMI, cholesterol profile, and insurance type. In conclusion, ML models demonstrated improved performance to conventional bleeding risk scores and uncovered novel risk factors, offering potential for more personalized bleeding risk assessment in AF patients on DOACs.
No takes yet. Share an insight, caveat, or question.
Chaudhary et al. (2025) conducted a cohort in Nonvalvular atrial fibrillation (n=24,468). Machine learning models vs. Conventional bleeding risk scores (HAS-BLED, ORBIT, and ATRIA) was evaluated on Hospitalization for bleeding within one year (AUC 0.76, 95% CI 0.70-0.81, p=<0.001). Machine learning models, particularly random forest, outperformed the HAS-BLED score in predicting 1-year hospitalization for bleeding in AF patients on DOACs (AUC 0.76 vs 0.57; p<0.001).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: