Artificial intelligence for prediction of atrial fibrillation in the stroke unit: a retrospective derivation validation cohort studyResearch in context

Summary: Background: Paroxysmal atrial fibrillation (AF) is a major cause of stroke but is often undetected in routine clinical practice. Effective stratification is needed to identify patients with stroke who might benefit the most from intensified AF screening. Several artificial intelligence mod...

Full description

Saved in:
Bibliographic Details
Main Authors: Maximilian Schoels, Laura Krumm, Alexander Nelde, Manuel C. Olma, Christian H. Nolte, Jan F. Scheitz, Markus G. Klammer, Christoph Leithner, Andreas Meisel, Franziska Scheibe, Michael Krämer, Karl Georg Haeusler, Matthias Endres, Christian Meisel
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:EBioMedicine
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352396425003135
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849405468051505152
author Maximilian Schoels
Laura Krumm
Alexander Nelde
Manuel C. Olma
Christian H. Nolte
Jan F. Scheitz
Markus G. Klammer
Christoph Leithner
Andreas Meisel
Franziska Scheibe
Michael Krämer
Karl Georg Haeusler
Matthias Endres
Christian Meisel
author_facet Maximilian Schoels
Laura Krumm
Alexander Nelde
Manuel C. Olma
Christian H. Nolte
Jan F. Scheitz
Markus G. Klammer
Christoph Leithner
Andreas Meisel
Franziska Scheibe
Michael Krämer
Karl Georg Haeusler
Matthias Endres
Christian Meisel
author_sort Maximilian Schoels
collection DOAJ
description Summary: Background: Paroxysmal atrial fibrillation (AF) is a major cause of stroke but is often undetected in routine clinical practice. Effective stratification is needed to identify patients with stroke who might benefit the most from intensified AF screening. Several artificial intelligence models have been proposed to predict AF based on ECG in sinus rhythm, but broad implementation has been limited. The most valuable input features and most effective model design for AF prediction are also unclear. Methods: We developed and tested AF prediction models utilising continuous electrocardiogram monitoring (CEM) recordings from the first 72 h after admission and multiple clinical input features from patients with stroke hospitalised at Charité, Berlin, Germany, between September 2020 and August 2023. We compared different models and input data to identify the best-performing model for prediction of AF. The relative contributions of different input data sources were assessed for explainability. A final model was externally validated using the first hour of monitoring data from the intervention group of the prospective multicentre MonDAFIS study. Findings: The derivation dataset included 2068 patients with acute ischaemic stroke, of whom 469 (22.7%) had AF, first detected before or during the index hospital stay (366 vs. 103). In predicting newly detected AF, a Bayesian fusion model emerged as best, achieving a ROC-AUC of 0.89 (95% CI: 0.80, 0.96). Model introspection indicated that HRV was the main driver of the model's predictions. A final, simplified tree-based ensemble model using age and HRV parameters of the first hour of CEM data achieved similar performance (ROC-AUC 0.88, 95% CI: 0.79, 0.95). The final model consistently outperformed the AS5F score in a real-world scenario external validation on the MonDAFIS dataset (1519 patients, thereof 36 (2.37%) with AF; ROC-AUC 0.79 vs. ROC-AUC 0.69, p = 4.69e-03). Interpretation: HRV appears to be the most informative variable for predicting AF. A computationally inexpensive model requiring only 1 h of single-lead CEM data and patients' age supports prediction of AF after acute ischaemic stroke for up to seven days. Such a model may enable risk-based stratification for cardiac monitoring, prioritising efforts where most needed to enhance AF screening efficiency and, ultimately, secondary stroke prevention. Funding: This study was supported by the German Federal Ministry of Education and Research and the German Research Foundation.
format Article
id doaj-art-486bb53d256a4d41a39b09b6937c3bcb
institution Kabale University
issn 2352-3964
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series EBioMedicine
spelling doaj-art-486bb53d256a4d41a39b09b6937c3bcb2025-08-20T03:36:39ZengElsevierEBioMedicine2352-39642025-08-0111810586910.1016/j.ebiom.2025.105869Artificial intelligence for prediction of atrial fibrillation in the stroke unit: a retrospective derivation validation cohort studyResearch in contextMaximilian Schoels0Laura Krumm1Alexander Nelde2Manuel C. Olma3Christian H. Nolte4Jan F. Scheitz5Markus G. Klammer6Christoph Leithner7Andreas Meisel8Franziska Scheibe9Michael Krämer10Karl Georg Haeusler11Matthias Endres12Christian Meisel13Computational Neurology, Department of Neurology, Charité – Universitätsmedizin Berlin, Germany; Berlin Institute of Health, Berlin, Germany; Center for Stroke Research Berlin, Berlin, GermanyComputational Neurology, Department of Neurology, Charité – Universitätsmedizin Berlin, Germany; Berlin Institute of Health, Berlin, Germany; Bernstein Center for Computational Neuroscience, Berlin, Germany; Einstein Center for Neurosciences, Berlin, Germany; Institute for Theoretical Biology, Department of Biology, Humboldt-Universität zu Berlin, Berlin, GermanyComputational Neurology, Department of Neurology, Charité – Universitätsmedizin Berlin, Germany; Berlin Institute of Health, Berlin, GermanyDepartment of Neurology with Experimental Neurology, Charité – Universitätsmedizin Berlin, GermanyCenter for Stroke Research Berlin, Berlin, Germany; Department of Neurology with Experimental Neurology, Charité – Universitätsmedizin Berlin, Germany; German Center for Neurodegenerative Diseases (DZNE), Partner Site Berlin, GermanyCenter for Stroke Research Berlin, Berlin, Germany; Department of Neurology with Experimental Neurology, Charité – Universitätsmedizin Berlin, Germany; German Center for Cardiovascular Research (DZHK), Partner Site Berlin, GermanyCenter for Stroke Research Berlin, Berlin, Germany; Department of Neurology with Experimental Neurology, Charité – Universitätsmedizin Berlin, GermanyDepartment of Neurology with Experimental Neurology, Charité – Universitätsmedizin Berlin, GermanyCenter for Stroke Research Berlin, Berlin, Germany; Department of Neurology with Experimental Neurology, Charité – Universitätsmedizin Berlin, Germany; Neuroscience Clinical Research Center, Berlin, GermanyDepartment of Neurology with Experimental Neurology, Charité – Universitätsmedizin Berlin, Germany; NeuroCure Cluster of Excellence, Charité – Universitätsmedizin Berlin, Berlin, GermanyBerlin Institute of Health, Berlin, GermanyDepartment of Neurology, Universitätsklinikum Ulm, Ulm, GermanyCenter for Stroke Research Berlin, Berlin, Germany; Department of Neurology with Experimental Neurology, Charité – Universitätsmedizin Berlin, Germany; German Center for Neurodegenerative Diseases (DZNE), Partner Site Berlin, Germany; NeuroCure Cluster of Excellence, Charité – Universitätsmedizin Berlin, Berlin, GermanyComputational Neurology, Department of Neurology, Charité – Universitätsmedizin Berlin, Germany; Berlin Institute of Health, Berlin, Germany; Center for Stroke Research Berlin, Berlin, Germany; Bernstein Center for Computational Neuroscience, Berlin, Germany; Einstein Center for Neurosciences, Berlin, Germany; Corresponding author. Computational Neurology, Department of Neurology & Berlin Institute of Health, Luisenstrasse 65, Berlin, 10117, Germany.Summary: Background: Paroxysmal atrial fibrillation (AF) is a major cause of stroke but is often undetected in routine clinical practice. Effective stratification is needed to identify patients with stroke who might benefit the most from intensified AF screening. Several artificial intelligence models have been proposed to predict AF based on ECG in sinus rhythm, but broad implementation has been limited. The most valuable input features and most effective model design for AF prediction are also unclear. Methods: We developed and tested AF prediction models utilising continuous electrocardiogram monitoring (CEM) recordings from the first 72 h after admission and multiple clinical input features from patients with stroke hospitalised at Charité, Berlin, Germany, between September 2020 and August 2023. We compared different models and input data to identify the best-performing model for prediction of AF. The relative contributions of different input data sources were assessed for explainability. A final model was externally validated using the first hour of monitoring data from the intervention group of the prospective multicentre MonDAFIS study. Findings: The derivation dataset included 2068 patients with acute ischaemic stroke, of whom 469 (22.7%) had AF, first detected before or during the index hospital stay (366 vs. 103). In predicting newly detected AF, a Bayesian fusion model emerged as best, achieving a ROC-AUC of 0.89 (95% CI: 0.80, 0.96). Model introspection indicated that HRV was the main driver of the model's predictions. A final, simplified tree-based ensemble model using age and HRV parameters of the first hour of CEM data achieved similar performance (ROC-AUC 0.88, 95% CI: 0.79, 0.95). The final model consistently outperformed the AS5F score in a real-world scenario external validation on the MonDAFIS dataset (1519 patients, thereof 36 (2.37%) with AF; ROC-AUC 0.79 vs. ROC-AUC 0.69, p = 4.69e-03). Interpretation: HRV appears to be the most informative variable for predicting AF. A computationally inexpensive model requiring only 1 h of single-lead CEM data and patients' age supports prediction of AF after acute ischaemic stroke for up to seven days. Such a model may enable risk-based stratification for cardiac monitoring, prioritising efforts where most needed to enhance AF screening efficiency and, ultimately, secondary stroke prevention. Funding: This study was supported by the German Federal Ministry of Education and Research and the German Research Foundation.http://www.sciencedirect.com/science/article/pii/S2352396425003135StrokeAtrial fibrillationPredictionMachine learningArtificial intelligenceHeart rate variability
spellingShingle Maximilian Schoels
Laura Krumm
Alexander Nelde
Manuel C. Olma
Christian H. Nolte
Jan F. Scheitz
Markus G. Klammer
Christoph Leithner
Andreas Meisel
Franziska Scheibe
Michael Krämer
Karl Georg Haeusler
Matthias Endres
Christian Meisel
Artificial intelligence for prediction of atrial fibrillation in the stroke unit: a retrospective derivation validation cohort studyResearch in context
EBioMedicine
Stroke
Atrial fibrillation
Prediction
Machine learning
Artificial intelligence
Heart rate variability
title Artificial intelligence for prediction of atrial fibrillation in the stroke unit: a retrospective derivation validation cohort studyResearch in context
title_full Artificial intelligence for prediction of atrial fibrillation in the stroke unit: a retrospective derivation validation cohort studyResearch in context
title_fullStr Artificial intelligence for prediction of atrial fibrillation in the stroke unit: a retrospective derivation validation cohort studyResearch in context
title_full_unstemmed Artificial intelligence for prediction of atrial fibrillation in the stroke unit: a retrospective derivation validation cohort studyResearch in context
title_short Artificial intelligence for prediction of atrial fibrillation in the stroke unit: a retrospective derivation validation cohort studyResearch in context
title_sort artificial intelligence for prediction of atrial fibrillation in the stroke unit a retrospective derivation validation cohort studyresearch in context
topic Stroke
Atrial fibrillation
Prediction
Machine learning
Artificial intelligence
Heart rate variability
url http://www.sciencedirect.com/science/article/pii/S2352396425003135
work_keys_str_mv AT maximilianschoels artificialintelligenceforpredictionofatrialfibrillationinthestrokeunitaretrospectivederivationvalidationcohortstudyresearchincontext
AT laurakrumm artificialintelligenceforpredictionofatrialfibrillationinthestrokeunitaretrospectivederivationvalidationcohortstudyresearchincontext
AT alexandernelde artificialintelligenceforpredictionofatrialfibrillationinthestrokeunitaretrospectivederivationvalidationcohortstudyresearchincontext
AT manuelcolma artificialintelligenceforpredictionofatrialfibrillationinthestrokeunitaretrospectivederivationvalidationcohortstudyresearchincontext
AT christianhnolte artificialintelligenceforpredictionofatrialfibrillationinthestrokeunitaretrospectivederivationvalidationcohortstudyresearchincontext
AT janfscheitz artificialintelligenceforpredictionofatrialfibrillationinthestrokeunitaretrospectivederivationvalidationcohortstudyresearchincontext
AT markusgklammer artificialintelligenceforpredictionofatrialfibrillationinthestrokeunitaretrospectivederivationvalidationcohortstudyresearchincontext
AT christophleithner artificialintelligenceforpredictionofatrialfibrillationinthestrokeunitaretrospectivederivationvalidationcohortstudyresearchincontext
AT andreasmeisel artificialintelligenceforpredictionofatrialfibrillationinthestrokeunitaretrospectivederivationvalidationcohortstudyresearchincontext
AT franziskascheibe artificialintelligenceforpredictionofatrialfibrillationinthestrokeunitaretrospectivederivationvalidationcohortstudyresearchincontext
AT michaelkramer artificialintelligenceforpredictionofatrialfibrillationinthestrokeunitaretrospectivederivationvalidationcohortstudyresearchincontext
AT karlgeorghaeusler artificialintelligenceforpredictionofatrialfibrillationinthestrokeunitaretrospectivederivationvalidationcohortstudyresearchincontext
AT matthiasendres artificialintelligenceforpredictionofatrialfibrillationinthestrokeunitaretrospectivederivationvalidationcohortstudyresearchincontext
AT christianmeisel artificialintelligenceforpredictionofatrialfibrillationinthestrokeunitaretrospectivederivationvalidationcohortstudyresearchincontext