THE IMPACT OF NOACS VS. VKAS ON ABSOLUTE AND RELATIVE COGNITIVE FUNCTION DECLINE OVER TIME: A MACHINE LEARNING APPROACH.

Background: Atrial fibrillation (AF) is the most common arrhythmia in adults, with incidence increasing with age. Cognitive impairment (CoI) and dementia share risk factors with AF. Meta-analyses indicate that AF increases the risk of CoI by 2.4-fold and 1.4-fold in patients with and without prior stroke, respectively. Thromboembolic events contribute to CoI, highlighting the importance of anticoagulant therapy (OAT). Non-vitamin K antagonist oral anticoagulants (NOACs) have a better safety profile than vitamin K antagonists (VKAs), but evidence of a cognitive benefit remains inconclusive. Aims: This multicenter prospective cohort study evaluates the impact of NOACs versus VKAs on cognitive decline in elderly AF patients, using a Machine Learning approach. Methods: Between 2008 and 2022, AF outpatients were enrolled at the Geriatrics Department, “Magna Graecia” University of Catanzaro, and the ProMISE Department, University of Palermo, Italy. Stroke and bleeding risks were assessed, and cognitive function was evaluated via the Mini-Mental State Examination (MMSE). A Random Forest Classifier predicted cognitive decline based on clinical and demographic features. Results: At baseline, 58% of patients had normal MMSE scores, 18% were borderline, and 24% had mild impairment. NOAC users were younger (74±5 vs. 77±6 years, p<0.001) and had a lower BMI (29±5 vs. 30±3, p=0.002). The predicted probability of cognitive decline was significantly higher for VKA users (0.5027) versus NOAC users (0.2473, p<0.001). Conclusion: NOAC use is associated with a lower predicted probability of cognitive decline, suggesting potential cognitive benefits over VKAs.

Publikationsverlauf

Eingereicht: 14. März 2025

Angenommen nach Revision: 11. August 2025

Accepted Manuscript online:
10. September 2025