Machine learning for outcome prediction in patients with non-valvular atrial fibrillation from the GLORIA-AF registry

Aug 5, 2026

Upload by Noah

Clinical risk scores for atrial fibrillation outcomes provide only modest predictive performance. Multiple machine-learning models were evaluated and compared with established scores for adverse outcomes in 26,183 patients with non-valvular atrial fibrillation from the GLORIA-AF registry. Models used 23 demographic variables plus comorbidities and current treatments. For one-year stroke prediction, ML reached an AUC of 0.653 versus CHADS2 and CHA2DS2-VASc. ML also improved one-year major bleeding and predicted one- and three-year all-cause mortality with higher AUCs than HAS-BLED and clinical comparators, showing broad performance gains.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Background and rationale

Risk scores vs machine learning approaches

Study population and prediction tasks

Aalborg Universitet Machine learning for outcome prediction in patients with non-valvular atrial fibrillation from the GLORIA-AF registry Joddrell, Martha; El-Bouri, Wahbi; Harrison, Stephanie L. ; Huisman, Menno V. ; Lip, Gregory Y. H. ; Zheng, Yalin; GLORIA-AFinvestigators Published in: Scientific Reports DOI (link to publication from Publisher): 10.1038/s41598-024-78120-z Creative Commons License CC BY 4.0 Publication date: 2024 Document Version Publisher's PDF, also known as Version of record Link to publication from Aalborg University Citation for published version (APA): Joddrell, M. , El-Bouri, W. , Harrison, S. L. , Huisman, M. V. , Lip, G. Y. H. , Zheng, Y. , & GLORIA-AFinvestigators (2024) . Machine learning for outcome prediction in patients with non-valvular atrial fibrillation from the GLORIAAF registry. Scientific Reports, 14(1), Article 27088. [https://doi.org/10.1038/s41598-024-78120-z](https://doi.org/10.1038/s41598-024-78120-z) General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. -Users may download and print one copy of any publication from the public portal for the purpose of private study or research. -You may not further distribute the material or use it for any profit-making activity or commercial gain -You may freely distribute the URL identifying the publication in the public portal Take down policy If you believe that this document breaches copyright please contact [us at vbn@aub.aau.dk](us at vbn@aub.aau.dk) providing details, and we will remove access to the work immediately and investigate your claim. [www. nature.com/scientificreports](www. nature.com/scientificreports) OPEN Machine learning for outcome prediction in patients with nonvalvular atrial fibrillation from the GLORIA-AF registry Martha Joddrell1,2􀀍, Wahbi El-Bouri1,2, Stephanie L. Harrison1,2, MennoV. Huisman3, Gregory Y. H. Lip1,2,5, Yalin Zheng1,4 & GLORIA-AFinvestigators Clinical risk scores that predict outcomes in patients with atrial fibrillation (AF) have modest predictive value. Machine learning (ML) may achieve greater results when predicting adverse outcomes inpatients with recently diagnosed AF. Several ML models were tested and compared with current clinical risk scores on a cohort of 26,183 patients (mean age 70.13 (standard deviation 10.13); 44.8% female) with non-valvularAF. Inputted into the ML models were 23 demographic variables alongside comorbidities and current treatments. For one-year stroke prediction, ML achieved an area under the curve (AUC) of 0.653 (95% confidence interval 0.576–0.730), compared tothe CHADS2 and CHA2DS2-VASc scores performance of 0.587 (95% CI 0.559–0.615) and 0.535 (95% CI 0.521–0.550), respectively. Using ML for one-year major bleed prediction increased theAUC from 0.537 (95% CI 0.518–0.557) generated by the HAS-BLED score to 0.677 (95% CI 0.619–0.724) . ML was able to predict one-year and three-year all-cause mortality with anAUC of 0.734 (95% CI 0.696–0.771) and 0.742 (95% CI 0.718–0.766). In this study a significant improvement in performance was observed when transitioning from clinical risk scores to machine learning-based approaches across all applications tested. Obtaining precise prediction tools is desirable for increased interventions to reduce event rates. Trial Registry[https://www.clinicaltrials.gov](https://www.clinicaltrials.gov); Unique identifier: NCT01468701, NCT01671007, NCT01937377 . Risk stratification scores are used to determine the likelihood of an outcome occurring, guiding appropriate treatment and therapy interventions. Existing methods for stroke and major bleeding prediction in patients with atrial fibrillation (AF) are typically developed using traditional statistical a

FAQs

Which patient population and data sources were used in the study?

The study evaluated 26,183 patients with non-valvular atrial fibrillation from the GLORIA-AF registry, using 23 demographic variables plus comorbidities and current treatments.

How did machine learning perform for one-year stroke prediction compared with clinical scores?

Machine learning achieved an AUC of 0.653 for one-year stroke prediction, outperforming CHADS2 (AUC 0.587) and CHA2DS2-VASc (AUC 0.535).

Did machine learning improve predictions beyond bleeding and stroke outcomes?

Yes. Machine learning predicted one-year and three-year all-cause mortality with AUCs of 0.734 and 0.742, respectively, and showed significant performance improvements across tested applications when compared with clinical risk scores.

Aug 5, 2026

Upload by Noah