Prediction of atrial fibrillation from sinus-rhythm electrocardiograms based on deep neural networks: Analysis of time intervals and longitudinal study
Entity
UAM. Departamento de Tecnología Electrónica y de las ComunicacionesPublisher
ElsevierDate
2023-10-27Citation
10.1016/j.irbm.2023.100811
Innovation and Research in BioMedical engineering 44.6 (2023): 100811
ISSN
1959-0318 (print)DOI
10.1016/j.irbm.2023.100811Funded by
European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No860813 – TReSPAsS-ETNTRESPASS-ETNProject
info:eu-repo/grantAgreement/EC/H2020/860813/EU//TReSPAsS-ETNEditor's Version
https://doi.org/10.1016/j.irbm.2023.100811Subjects
ECG; Healthcare; Artificial Intelligence; Atrial Fibrillation; Deep Learning; ElectrónicaRights
© 2023 AGBMEsta obra está bajo una licencia de Creative Commons Reconocimiento-NoComercial-SinObraDerivada 4.0 Internacional.
Abstract
Objective: Artificial Intelligence (AI) in electrocardiogram (ECG) analysis helps to identify persons at risk of developing atrial fibrillation (AF) and reduces the risk for severe complications. Our aim is to investigate the performance of AI-based methods predicting future AF from sinus rhythm (SR) ECGs, according to different characteristics of patients, time intervals for prediction, and longitudinal measures. Methods: We designed a retrospective, prognostic study to predict AF occurrence in patients from 12-lead SR ECGs. We classified patients in two groups, according to their ECGs: 3,761 developed AF and 22,896 presented only SR ECGs. We assessed the impact of age on the overall performance of deep neural network (DNN)-based systems, which consist in a variation of Residual Networks for time series. Then, we analysed how much in advance our system can predict AF from SR ECGs and the performance for different categories of patients with AUC and other metrics. Results: After balancing the age distribution between the two groups of patients, our model achieves AUC of 0.79 (0.72-0.86) without additional constraints, 0.83 (0.76-0.89) for ECGs recorded in the last six months before AF, and 0.87 (0.81-0.93) for patients with stable AF risk measures over time, with sensitivity of 90.62% (80.70-96.48) and diagnostic odd ratio of 20.49 (8.56-49.09). Conclusion: This study shows the ability of DNNs to predict new onsets of AF from SR ECGs, with the best performance achieved for patients with stable AF risk score over time. The introduction of this time-based score opens new possibilities for AF prediction, thanks to the analysis of long-span time intervals and score stability
Files in this item
Google Scholar:Melzi, Pietro
-
Vera Rodríguez, Rubén
-
Tolosana Moranchel, Rubén
-
Sanz-García, Ancor
-
Cecconi, Alberto
-
Ortega, Guillermo J.
-
Jiménez-Borreguero, Luis Jesús
This item appears in the following Collection(s)
Related items
Showing items related by title, author, creator and subject.