External validation of the GLORIA-AF Stroke Weighted Risk Score supports its transportability and potential adjunctive role in guideline-directed thromboembolic risk assessment and generally greater net benefit than CHA2DS2-VA.
Abstract
Background
AND
Aims
Accurate stroke-risk stratification is central to anticoagulation decision-making in patients with atrial fibrillation (AF), but conventional scores may not fully capture risk heterogeneity. We aimed to develop and externally validate an interpretable weighted score using a time-to-event framework.
Methods
GLORIA-AF Phase II/III data were used to evaluate 17 baseline predictors using LASSO-penalized Cox regression with stability selection; coefficients were converted into integer weights. Performance was assessed using discrimination, calibration, integrated discrimination improvement (IDI), continuous net reclassification improvement (NRI), and decision-curve analysis. External validation was performed in EORP-AF and APHRS-AF registries.
Results
Among 20,517 patients included in the derivation cohort (mean [SD] age, 69.9 [10.3] years; 9,196 women [44.8%]), 487 (2.4%) had stroke, and 17,397 (84.8%) were receiving anticoagulation at baseline. Ten selected predictors formed a 0-23-point score. The derived score achieved a C-index of 0.661 (95% CI, 0.636-0.685), higher than CHA2DS2-VA (0.626; P < 0.001), CHA2DS2-VASc (0.615; P < 0.001), and the unweighted score (P = 0.016), with no significant difference from the full Cox or machine learning models. In external validation (8,309 patients; 147 strokes), the C-index was 0.652 (95% CI, 0.614-0.690) versus 0.616 for CHA2DS2-VA (95%CI, 0.598-0.634; P < 0.001). IDI/NRI, calibration, and decision-curve analyses supported improved risk differentiation, close calibration, and generally greater net benefit than CHA2DS2-VA. The score retained higher discrimination than CHA2DS2-VA among patients without baseline anticoagulation (P < 0.001).
Conclusion
The GLORIA-AF Stroke Weighted Risk Score provides risk refinement beyond CHA2DS2-VA while retaining discrimination consistent with more complex models. External validation supports its transportability and potential adjunctive role in guideline-directed thromboembolic risk assessment.
AIMS
Major bleeding remains a major barrier to optimal anticoagulation in patients with atrial fibrillation (AF). We aimed to develop and externally validate a weighted score that balances simplicity and prediction for 1-year major bleeding prediction.
METHODS
Using prospective multinational GLORIA-AF Phase II/III data, we developed the GLORIA-AF Bleeding Weighted Risk Score using LASSO-penalized regression with stability selection, coefficient-rescaling and internal validation. The score was externally evaluated in EORP-AF and APHRS-AF registries. Discrimination, calibration and clinical benefit were assessed using C-index, observed-to-expected ratio, calibration plot and decision-curve analysis, and compared with HAS-BLED, unweighted GLORIA-AF score and full multivariable Cox model.
RESULTS
Among 20,250 eligible derivation cohort patients (69.9 [10.3] years; 9,092 female [44.9%]), 317 (1.6%) had major bleeding during 1-year follow-up. The derived score ranges from 0 to 22, with the highest weight (5) assigned to age >65 years, followed by abnormal kidney function (3). The derived score achieved C-index of 0.688 (95% CI: 0.660-0.717), outperforming HAS-BLED (C-index: 0.631, 95% CI: 0.604-0.658; P < 0.001), while preserving discrimination comparable to full multivariable regression (C-index: 0.690; 95%CI: 0.661-0.719; P = 0.084). Calibration was good (O:E ratio: 0.996) and DCA showed greater net benefit than HAS-BLED across 1% to 3% thresholds. Among 9,752 external validation patients, 148 (1.5%) had major bleeding. The derived score achieved C-index of 0.674 (95% CI: 0.643-0.705; P < 0.001), with better discrimination, calibration and clinical benefit than HAS-BLED.
CONCLUSIONS
The GLORIA-AF Bleeding Score showed modestly higher discrimination than HAS-BLED for 1-year major bleeding prediction while retaining clinical interpretability and usability. External validation in independent European and Asia-Pacific registries further supports its transportability beyond the derivation population.
Yi-Fan Xie, Wenhui Li, Yanda Meng et al.· European Journal of Preventi...· 0 citations
BACKGROUND
Accurate prediction of ischemic stroke or systemic embolism is central to atrial fibrillation (AF) management, yet the transportability of available risk scores to Chinese populations remains uncertain.
OBJECTIVE
Externally validate and compare published stroke risk scores in Chinese patients with non-valvular AF.
METHODS
We systematically retrieved and externally validated 17 published models in a retrospective cohort of 1,283 adults hospitalized with non-valvular AF at a Chinese tertiary-care center. Discrimination was evaluated using the 4-year Uno C-index and time-dependent areas under the curve (AUC). Models providing absolute risks also underwent calibration, Brier score, and reclassification analyses. Sensitivity analyses accounted for death as a competing event and separately evaluated patients not receiving OAC at baseline.
RESULTS
During 4 years of follow-up, 103 primary outcomes occurred, corresponding to 2.85 events per 100 person-years. Across models, 4-year Uno C-indices ranged from 0.572 to 0.767, compared with 0.690 for CHA2DS2-VASc. GARFIELD-AF 2017, GARFIELD-AF 2021, and ATRIA had higher Uno C-indices than CHA2DS2-VASc. However, no model had significantly higher time-dependent AUC at any time point. For 1-year calibration, CHA2DS2-VASc had predicted and observed risks of 3.39% and 3.54%, respectively, with an observed-to-expected ratio of 1.04, whereas several other models underestimated risk. Brier scores and reclassification measures showed no consistent advantage Competing-risk analyses lowered cumulative incidence without changing comparative patterns. Among patients not receiving OAC at baseline, no model outperformed CHA2DS2-VASc.
CONCLUSION
Candidate models did not consistently outperform CHA2DS2-VASc in this external validation; CHA2DS2-VASc remains practical, while other models may require population-specific validation and recalibration.
The EHR-based machine learning model, FIND-AF 2.0, identifies a high-risk subpopulation for AF diagnosis among patients at elevated risk of stroke and could enable scalable, EHR-driven, risk-guided AF screening.
R. Nadarajah, Jianhua Wu, A. Wahab et al.· Circulation· 0 citations
With advancements in cancer therapy and prolonged survival, the prevalence of concomitant cancer and atrial fibrillation (AF) is increasing. The interaction between antineoplastic agents and anticoagulants complicates clinical management, rendering bleeding risks unpredictable. Current bleeding risk scores (e.g., HAS-BLED) often lack cancer-specific variables, limiting their accuracy in this population. We aimed to develop and validate a novel nomogram to predict bleeding risk specifically for patients with cancer and AF.
We conducted a retrospective study of 972 patients with cancer and AF. Patients were randomly assigned to a training set and a validation set in a 7:3 ratio. Univariate and multivariate logistic regression analyses were performed to identify independent risk factors for bleeding. A nomogram was constructed using R software. The model's performance was compared with the HAS-BLED, HEMORR2HAGES, NBLDSCOR, and ORBIT scores using the Area Under the Receiver Operating Characteristic Curve (AUC). Decision Curve Analysis (DCA) was used to assess clinical utility.
Bleeding events occurred in 173 patients (17.8%), with the gastrointestinal tract being the most common site. Multivariate analysis identified eight independent risk factors: age ≥75 years, anemia, history of bleeding, anticoagulant usage, vitamin K antagonist (VKA) therapy, concomitant antiplatelet therapy, advanced cancer stage, and anti-angiogenic therapy. The novel nomogram demonstrated robust discrimination with an AUC of 0.784 in the training set and 0.770 in the validation set. Compared to the HAS-BLED, HEMORR2HAGES, NBLDSCOR, and ORBIT scores, the new model showed a higher AUC and superior net benefit in the validation cohort.
We developed a novel bleeding risk prediction model for patients with cancer and AF that incorporates crucial cancer-specific factors, such as tumor stage and anti-angiogenic therapy. This nomogram outperforms traditional risk scores in predictive accuracy and offers a valuable tool for personalized anticoagulation decision-making in this high-risk population.
J. Liu· European Heart Journal, Supp...· 0 citations
The CHA2DS2-VALa score significantly improves stroke risk stratification in AF by integrating LA diameter into conventional scoring, as echocardiographic measurement is widely available and reproducible.
Sefa Erdi Ömür, Emin Koyun, Gülşen Genç Tapar et al.· Cardiovascular Electrophysio...· 0 citations
In patients with cryptogenic stroke receiving an ICM, the ECG-AI score showed modest discrimination for AF detection, outperforming CHA2DS2-VA and HAVOC, but not Brown ESUS-AF, which indicates a possible role for AI-driven ECG analysis in risk stratification.
F. Wouters, M. Barthels, J. Vranken et al.· Digital Health· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
