The Impact of NOACS versus VKAS on Absolute and Relative Cognitive Function Decline Over Time: A Machine Learning Approach
Der Einfluss von NOACS versus VKAS auf den absoluten und relativen kognitiven Funktionsabfall über die Zeit: ein Machine-Learning-Ansatz
Thrombosis and Haemostasis · 01.10.2026 · 126 (10) · 1017-1027
DOI: 10.1055/a-2698-3739 ↗Auf einen Blick
Bei 983 älteren AF-Ambulanzpatient:innen war der kognitive Abfall unter VKA stärker als unter NOAC. NOAC war mit einem geringeren Risiko für kognitiven Abfall verbunden.
Fragestellung
Welchen Einfluss haben NOACs im Vergleich zu VKAs auf den kognitiven Abfall bei älteren Patient:innen mit Vorhofflimmern?
Methode
Multizentrische prospektive Kohortenstudie mit 983 AF-Ambulanzpatient:innen; Vergleich von NOACs und VKAs; MMSE, logistische Regression und Random Forest.
Ergebnisse
Nach 7,2 ± 3,4 Jahren sank der MMSE unter VKA stärker als unter NOAC (−1,7 vs. −0,3 Punkte; p < 0,001). NOAC war mit niedrigerem Risiko für kognitiven Abfall assoziiert (OR 0,322; 95 %-KI 0,221–0,469).
Schlussfolgerung der Autor:innen
NOAC war mit einer geringeren vorhergesagten Wahrscheinlichkeit für kognitiven Abfall verbunden und könnte gegenüber VKAs kognitive Vorteile haben.
Kernaussagen
- MMSE-Abfall unter VKA stärker als unter NOAC
- OR 0,322 für kognitiven Abfall bei NOAC
- Random Forest: AUC 0,8719; Test-AUC 0,880
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Multizentrische Studie in der Zeitschrift Thrombosis and Haemostasis, erschienen am 01.10.2026. Verfasst von Sergio Ferrantelli und 15 weiteren Autor:innen. Beteiligte Einrichtung: Internal Medicine and Stroke Care Ward, University of Palermo, Palermo, Italy. Hauptthemen laut MEDLINE: Anticoagulants, Atrial Fibrillation, Cognition, Cognitive Dysfunction. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Atrial fibrillation (AF) is the most common arrhythmia in older adults and is associated with an increased risk of cognitive impairment and dementia, even in patients without prior stroke. Nonvitamin K antagonist oral anticoagulants (NOACs) offer a better safety profile than vitamin K antagonists (VKAs), but their cognitive benefit remains uncertain. To assess the impact of NOACs versus VKAs on cognitive decline in elderly AF patients using a machine learning approach. This multicenter prospective cohort study included 983 AF outpatients enrolled between 2008 and 2022 at the Geriatrics Department, University of Catanzaro, and the ProMISE Department, University of Palermo. Stroke and bleeding risks were assessed using CHA2DS2-VASc and HAS-BLED scores. Cognitive function was evaluated using the Mini-Mental State Examination (MMSE). Cognitive decline was defined as a decrease in MMSE score between baseline and follow-up. Patients with prior anticoagulant therapy (OAT), severe dementia, or comorbidities affecting cognition were excluded. Multivariable logistic regression and a random forest classifier were used to assess whether anticoagulant type independently predicted cognitive decline. Class imbalance was addressed using both class-weighted learning and the synthetic minority over-sampling technique (SMOTE), with model performance evaluated through repeated stratified cross-validation and threshold optimization. At baseline, cognitive performance was comparable between groups (p = 0.11). After a mean follow-up of 7.2 ± 3.4 years, MMSE scores declined significantly more in VKA-treated patients (−1.7 vs. −0.3 points, p < 0.001). In logistic regression, NOAC use was independently associated with a lower risk of cognitive decline (odds ratio: 0.322; 95% confidence interval: 0.221–0.469; p < 0.0001). The random forest classifier achieved a mean cross-validated AUC of 0.8719 (standard deviation: 0.0273) and a test-set AUC of 0.880. Threshold adjustment and SMOTE improved sensitivity (recall increased: 0.47–0.84), with a precision–recall AUC of 0.763. Permutation importance analysis identified “OAT” as the top predictor. Predicted probabilities of cognitive decline were significantly higher in VKA users (median = 0.70) than in NOAC users (median = 0.09), confirmed by a Kolmogorov–Smirnov test (KS = 0.385, p < 0.001). NOAC use is associated with a lower predicted probability of cognitive decline, suggesting potential cognitive benefits over VKAs.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Internal Medicine and Stroke Care Ward, University of Palermo, Palermo, Italy.
- Department of Health Promotion, Mother and Child Care, Internal Medicine and Medical Specialities, University of Palermo, Palermo, Italy.
- Department of Medical and Surgical Sciences, University Magna Græcia of Catanzaro, Campus Universitario di Germaneto, Catanzaro, Italy.
- Department of Clinical Internal, Anesthesiological and Cardiovascular Sciences, Sapienza University of Rome, Rome, Italy.
- IRCCS Neuromed, Pozzilli, Italy.
ORCID-Profile: Mario Daidone, Giuseppe Armentaro
Zitieren
APA
Ferrantelli, S., Daidone, M., Armentaro, G., Pacinella, G., Scaglione, S., Ciaccio, A. M., Pirera, E., Maida, C. D., Miceli, G., Rizzo, G., Della Corte, V., Di Raimondo, D., Pastori, D., Sciacqua, A., Tuttolomondo, A., & MEDIREG (Mediterranean Research Group) (2026). The Impact of NOACS versus VKAS on Absolute and Relative Cognitive Function Decline Over Time: A Machine Learning Approach. Thrombosis and Haemostasis, 126(10), 1017-1027. https://doi.org/10.1055/a-2698-3739
Vancouver
Ferrantelli S, Daidone M, Armentaro G, Pacinella G, Scaglione S, Ciaccio AM, et al. The Impact of NOACS versus VKAS on Absolute and Relative Cognitive Function Decline Over Time: A Machine Learning Approach. Thrombosis and Haemostasis. 2026;126(10):1017-1027. doi:10.1055/a-2698-3739
BibTeX
@article{Ferrantelli2026,
author = {Ferrantelli, Sergio and Daidone, Mario and Armentaro, Giuseppe and Pacinella, Gaetano and Scaglione, Stefania and Ciaccio, Anna M and Pirera, Edoardo and Maida, Carlo D and Miceli, Giuseppe and Rizzo, Giuliana and Della Corte, Vittoriano and Di Raimondo, Domenico and Pastori, Daniele and Sciacqua, Angela and Tuttolomondo, Antonino and MEDIREG (Mediterranean Research Group), MEDIREG (Mediterranean Research Group)},
title = {The Impact of NOACS versus VKAS on Absolute and Relative Cognitive Function Decline Over Time: A Machine Learning Approach},
journal = {Thrombosis and Haemostasis},
year = {2026},
volume = {126},
number = {10},
pages = {1017--1027},
doi = {10.1055/a-2698-3739}
}
EUVIMED