Lence A., Granese F., Fall Ahmad, Hanczar B., Salem J.E., Zucker Jean-Daniel, Prifti Edi. (2025). ECGrecover : a deep learning approach for electrocardiogram signal completion. In :
Sun Y. (ed.), Chierichetti F. (ed.), Lauw H.W. (ed.), Perlich C. (ed.), Tok W. (ed.), Tomkins A. (ed.). Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1. New York : Association for Computing Machinery, 2359-2370. ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 31., Toronto (CAN), 2025/08/03-07. ISBN 979-8-4007-1245-6.
Titre du document
ECGrecover : a deep learning approach for electrocardiogram signal completion
Année de publication
2025
Type de document
Partie d'ouvrage
Auteurs
Lence A., Granese F., Fall Ahmad, Hanczar B., Salem J.E., Zucker Jean-Daniel, Prifti Edi
In
Sun Y. (ed.), Chierichetti F. (ed.), Lauw H.W. (ed.), Perlich C. (ed.), Tok W. (ed.), Tomkins A. (ed.), Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1
Source
New York : Association for Computing Machinery, 2025,
2359-2370 ISBN 979-8-4007-1245-6
Colloque
ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 31., Toronto (CAN), 2025/08/03-07
In this work, we address the challenge of reconstructing the complete 12-lead ECG signal from its incomplete parts. We focus on two main scenarios: (i) reconstructing missing signal segments within an ECG lead and (ii) recovering entire leads from signal in another unique lead. Two emerging clinical applications emphasize the relevance of our work. The first is the increasing need to digitize paper-stored ECGs for utilization in AI-based applications, often limited to digital 12 lead 10s ECGs. The second is the widespread use of wearable devices that record ECGs but typically capture only one or a few leads. In both cases, a non-negligible amount of information is lost or not recorded. Our approach aims to recover this missing signal. We propose ECGrecover, a U-Net neural network model trained on a novel composite objective function to address the reconstruction problem. This function incorporates both spatial and temporal features of the ECG by combining the distance in amplitude and sycnhronization through time between the reconstructed and the real digital signals. We used real-life ECG datasets and through comprehensive assessments compared ECGrecover with three state-of-the-art methods based on generative adversarial networks (EKGAN, Pix2Pix) as well as the CopyPaste strategy. The results demonstrated that ECGrecover consistently outperformed state-of-the-art methods in standard distortion metrics as well as in preserving critical ECG characteristics, particularly the P, QRS, and T wave coordinates.
Plan de classement
Intelligence artificielle [122INTAR]
Localisation
Fonds IRD [F B010095087]
Identifiant IRD
fdi:010095087
