idw – Informationsdienst Wissenschaft
Nachrichten, Termine, Experten
Nachrichten, Termine, Experten
An analysis of the NOAH – AFNET 6 trial used large language models to extract AF burden from pacemaker data in patients with device-detected atrial fibrillation. This approach enables to evaluate the impact of AF burden on cardiovascular outcome and on the effectiveness and safety of anticoagulation in pacemaker patients. The AF burden in the population was 0.4%, with 20% of patients showing a baseline AF burden of more than 1%. In these patients, there was no effect of AF burden on stroke or other cardiovascular events. Today, the findings were presented by AFNET board member Prof. Ulrich Schotten, Maastricht, as a hotline at the Heart Rhythm congress 2026 in Chicago (1).
Patients with device-detected atrial fibrillation (DDAF) have a lower risk of stroke than patients with ECG-diagnosed atrial fibrillation (AF) and comparable stroke risk factors. AF burden – the amount of time a patient spends in AF – has emerged as an important factor linked to stroke risk and outcomes, yet it remains difficult to capture at scale in clinical research and practice.
The primary analysis of NOAH – AFNET 6 (Non vitamin K antagonist Oral anticoagulants in patients with Atrial High-rate episodes), an investigator-initiated trial conducted by the AFNET, revealed: In patients with DDAF, anticoagulation slightly reduces the relatively low risk of stroke but also increases the risk of major bleeding. The trial was terminated early due to the expected increase in bleeding events in patients with DDAF while the stroke preventing effect was smaller than expected. The weak effects of anticoagulation were also found in several subgroups. (2-10)
This substudy of NOAH – AFNET 6 shows that AI-driven models using natural language processing can reliably automatically extract AF burden information from routine pacemaker reports supporting more individualized risk assessment and helping clinicians make more informed decisions about therapies such as anticoagulation. This approach was applied to NOAH – AFNET 6 to better understand how AF burden relates to clinical outcomes and response to the anticoagulant edoxaban.
Researchers analysed 11,964 pacemaker reports from 2,534 patients with device-detected AF enrolled in NOAH – AFNET 6. AF burden or mode switch burden was successfully identified in more than 70% of reports, demonstrating broad applicability to real-world data. The large language model-extracted AF burden was identical to manual review in more than 98% in a validation subcohort. In addition, AF burden and mode switch burden showed high concordance, reinforcing the reliability of device-based measures. Across the study population, baseline AF burden remained low, highlighting the importance of more precise measurement to better understand patient risk and treatment response.
The baseline AF burden was then correlated to cardiovascular events during 19 months median follow-up in the NOAH-AFNET 6 trial. Baseline AF burden did not modify thrombo-embolic risk, with low rates of stroke even in the small number of patients with a high AF burden. AF burden did not interact with the effectiveness of anticoagulation therapy in this detailed analysis. As expected, anticoagulation increased the risk of bleeding and death independent of AF burden.
“With atrial fibrillation on the rise worldwide, we must find better ways to leverage the latest technology to better understand not just whether patients have atrial fibrillation, but how much it affects them over time,” says Prof. Schotten, lead author and presenter of the data in Chicago. “This AI-driven large language model approach allows us to unlock meaningful insights from data we already collect and use them to advance research and improve patient care.”
“These results highlight the need to determine the effects of low-burden AF on stroke risk. The signal from this robust analysis is clear: A low AF burden translates into a low stroke risk. We need similar analyses in larger data sets to define which AF burden justifies anticoagulation therapy, and which burden requires rhythm control therapy. Together with international partners, we started to combine relevant data sets earlier this year (www.afburden.org)” states Paulus Kirchhof, the senior author of the analysis.
References
(1) Schotten U et al. Distribution of atrial fibrillation burden, relation to outcomes, and effectiveness and safety of anticoagulation based on device reports: The NOAH-AFNET 6 trial. 2026. HRS congress abstract
(2) Kirchhof P, Toennis T, Goette A, et al. Anticoagulation with Edoxaban in Patients with Atrial High-Rate Episodes. N Engl J Med 2023; 389:1167-1179. DOI:10.1056/NEJMoa2303062.
(3) Toennis T, Bertaglia E, Brandes A, et al. The influence of Atrial High Rate Episodes on Stroke and Cardiovascular Death - An update. Europace. 2023 Jul 4;25(7). DOI:10.1093/europace/euad166.
(4) Becher N, Toennis T, Bertaglia E, et al. Anticoagulation with edoxaban in patients with long Atrial High-Rate Episodes ≥24 hours. Eur Heart J. 2024 Mar 7;45(10):837-849. DOI:10.1093/eurheartj/ehad771
(5) Lip YH, Nikorowitsch J, Sehner S et al. Oral anticoagulation in device-detected atrial fibrillation: effects of age, sex, cardiovascular comorbidities, and kidney function on outcomes in the NOAH-AFNET 6 trial. Eur Heart J. 2024 April 9. DOI:10.1093/eurheartj/ehae225
(6) Diener HC, Becher N, Sehner S, Toennis T et al. Anticoagulation in patients with device-detected atrial fibrillation with and without a prior stroke or transient ischemic attack. The NOAH-AFNET 6 trial. J Am Heart Assoc. 2024 Sep 3;13(17):e036429. DOI:10.1161/JAHA.124.036429
(7) McIntyre WF, Benz AP, Becher N, et al. Direct Oral Anticoagulants for Stroke Prevention in Patients with Device-Detected Atrial Fibrillation: A Study-Level Meta-Analysis of the NOAH-AFNET 6 and ARTESiA Trials. Circulation. 2024 Mar 26;149(13):981-988. DOI:10.1161/CIRCULATIONAHA.123.067512
(8) Schnabel RB, Benezet-Mazuecos J, Becher N, McIntyre WF et al. Anticoagulation in patients with device-detected atrial fibrillation with and without concomitant vascular disease – A combined secondary analysis of the NOAH-AFNET 6 and ARTESiA trials. Eur Heart J. 2024 Dec 7;45(46):4902-4916. DOI:10.1093/eurheartj/ehae596
(9) Becher N, Koellner G, Blomstrom-Lundqvist C, Camm AJ et al. Effects of anticoagulation in patients with device-detected atrial fibrillation and multiple stroke risk factors: A Win Ratio analysis of the NOAH-AFNET 6 trial. Eur Heart J Qual Care Clin Outcomes. 2025 Dec 19;11(8):1351-1358. DOI:10.1093/ehjqcco/qcaf087
(10) Goette A, Lemoine MD, Fierenz A et al. Kidney disease increases the risk of cardiovascular events in patients with device-detected atrial fibrillation: NOAH-AFNET 6. Europace. 2026. DOI:10.1093/europace/euag083
About the Atrial Fibrillation NETwork (AFNET)
The Atrial Fibrillation NETwork is an interdisciplinary research network comprising scientists and physicians from hospitals and practices dedicated to improving the management of atrial fibrillation through coordinated research in Germany, Europe, and worldwide. Its main objective is to conduct high quality investigator-initiated clinical trials and registries on a national and international level as well as translational research projects. The AFNET continues the long-term activities of the network which has been funded by the German Federal Ministry of Research and Education over a decade. Since January 2015, specific projects and infrastructures of the AFNET are funded by the German Centre for Cardiovascular Research (DZHK), and some projects by EU research grants. AFNET has long expertise in the management of atrial fibrillation, but also provides support for work in other fields informing cardiovascular care. The results of 20 years of clinical and translational research improved the lives of patients with cardiovascular diseases and influenced treatment guidelines.
Funding of the NOAH trial: AFNET, DZHK, Daiichi Sankyo. This analysis was partially funded by the European Union AF-B-STEP (grant agreement 101252780, www.afburden.org).
NOAH registration: NCT 02618577, ISRCTN 17309850
Press Contact
Angelika Leute, PhD
Phone: +49 202 2623395
a.leute@t-online.de
Schotten U et al. Distribution of atrial fibrillation burden, relation to outcomes, and effectiveness and safety of anticoagulation based on device reports: The NOAH-AFNET 6 trial. 2026. HRS congress abstract
Criteria of this press release:
Journalists, Scientists and scholars
Medicine, Nutrition / healthcare / nursing
transregional, national
Research results, Scientific conferences
English
You can combine search terms with and, or and/or not, e.g. Philo not logy.
You can use brackets to separate combinations from each other, e.g. (Philo not logy) or (Psycho and logy).
Coherent groups of words will be located as complete phrases if you put them into quotation marks, e.g. “Federal Republic of Germany”.
You can also use the advanced search without entering search terms. It will then follow the criteria you have selected (e.g. country or subject area).
If you have not selected any criteria in a given category, the entire category will be searched (e.g. all subject areas or all countries).
