Single-lead electrocardiogram Artificial Intelligence model with risk factors detects atrial fibrillation during sinus rhythm
Europace · 01.02.2024 · 26 (2)
DOI: 10.1093/europace/euad354 ↗Kurz gefasst
Fachartikel in der Zeitschrift Europace, online erschienen am 11.12.2023. Verfasst von Stijn Dupulthys und 9 weiteren Autor:innen. Beteiligte Einrichtung: RADar Learning and Innovation Centre, AZ Delta, Deltalaan 1, 8800 Roeselare, Belgium. Hauptthemen laut MEDLINE: Atrial Fibrillation. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Flanders Innovation & Entrepreneurship, European Health Data Evidence Network.
Abstract (Originalsprache)
Aims
Guidelines recommend opportunistic screening for atrial fibrillation (AF), using a 30 s single-lead electrocardiogram (ECG) recorded by a wearable device. Since many patients have paroxysmal AF, identification of patients at high risk presenting with sinus rhythm (SR) may increase the yield of subsequent long-term cardiac monitoring. The aim is to evaluate an AI-algorithm trained on 10 s single-lead ECG with or without risk factors to predict AF. Methods and results This retrospective study used 13 479 ECGs from AF patients in SR around the time of diagnosis and 53 916 age- and sex-matched control ECGs, augmented with 17 risk factors extracted from electronic health records. AI models were trained and compared using 1- or 12-lead ECGs, with or without risk factors. Model bias was evaluated by age- and sex-stratification of results. Random forest models identified the most relevant risk factors. The single-lead model achieved an area under the curve of 0.74, which increased to 0.76 by adding six risk factors (95% confidence interval: 0.74–0.79). This model matched the performance of a 12-lead model. Results are stable for both sexes, over ages ranging from 40 to 90 years. Out of 17 clinical variables, 6 were sufficient for optimal accuracy of the model: hypertension, heart failure, valvular disease, history of myocardial infarction, age, and sex.
Conclusion
An AI model using a single-lead SR ECG and six risk factors can identify patients with concurrent AF with similar accuracy as a 12-lead ECG-AI model. An age- and sex-matched data set leads to an unbiased model with consistent predictions across age groups.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- RADar Learning and Innovation Centre, AZ Delta, Deltalaan 1, 8800 Roeselare, Belgium.
- Department of Cardiology, AZ Delta, Roeselare, Belgium.
- Resero Limited, Dublin, Ireland.
- RADar Learning and Innovation Centre, AZ Delta, Roeselare, Belgium.
- Department of Medicine and Life Sciences, Hasselt University, Martelarenlaan 42, 3500 Hasselt, Belgium.
ORCID-Profile: Stijn Dupulthys, Maarten Vanhaverbeke, Pieter-Jan Lammertyn, Louise Berteloot, Nathalie Mertens, Peter De Jaeger
Förderung
- Flanders Innovation & Entrepreneurship
- European Health Data Evidence Network
Zitieren
APA
Dupulthys, S., Dujardin, K., Anné, W., Pollet, P., Vanhaverbeke, M., McAuliffe, D., Lammertyn, P. J., Berteloot, L., Mertens, N., & De Jaeger, P. (2024). Single-lead electrocardiogram Artificial Intelligence model with risk factors detects atrial fibrillation during sinus rhythm. Europace, 26(2). https://doi.org/10.1093/europace/euad354
Vancouver
Dupulthys S, Dujardin K, Anné W, Pollet P, Vanhaverbeke M, McAuliffe D, et al. Single-lead electrocardiogram Artificial Intelligence model with risk factors detects atrial fibrillation during sinus rhythm. Europace. 2024;26(2). doi:10.1093/europace/euad354
BibTeX
@article{Dupulthys2024,
author = {Dupulthys, Stijn and Dujardin, Karl and Anné, Wim and Pollet, Peter and Vanhaverbeke, Maarten and McAuliffe, David and Lammertyn, Pieter-Jan and Berteloot, Louise and Mertens, Nathalie and De Jaeger, Peter},
title = {Single-lead electrocardiogram Artificial Intelligence model with risk factors detects atrial fibrillation during sinus rhythm},
journal = {Europace},
year = {2024},
volume = {26},
number = {2},
doi = {10.1093/europace/euad354}
}
EUVIMED