ECG Synthesis via Diffusion-Based State Space Augmented Transformer
Sensors · 09.10.2023 · 23 (19) · 8328
DOI: 10.3390/s23198328 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 09.10.2023. Verfasst von Md Haider Zama und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Engineering, Jamia Millia Islamia, New Delhi 110025, India. Hauptthemen laut MEDLINE: Algorithms, Cardiovascular Diseases. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Cardiovascular diseases (CVDs) are a major global health concern, causing significant morbidity and mortality. AI’s integration with healthcare offers promising solutions, with data-driven techniques, including ECG analysis, emerging as powerful tools. However, privacy concerns pose a major barrier to distributing healthcare data for addressing data-driven CVD classification. To address confidentiality issues related to sensitive health data distribution, we propose leveraging artificially synthesized data generation. Our contribution introduces a novel diffusion-based model coupled with a State Space Augmented Transformer. This synthesizes conditional 12-lead electrocardiograms based on the 12 multilabeled heart rhythm classes of the PTB-XL dataset, with each lead depicting the heart’s electrical activity from different viewpoints. Recent advances establish diffusion models as groundbreaking generative tools, while the State Space Augmented Transformer captures long-term dependencies in time series data. The quality of generated samples was assessed using metrics like Dynamic Time Warping (DTW) and Maximum Mean Discrepancy (MMD). To evaluate authenticity, we assessed the similarity of performance of a pre-trained classifier on both generated and real ECG samples.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Engineering, Jamia Millia Islamia, New Delhi 110025, India.
- Institute of Neural Information Processing, Ulm University, 89081 Ulm, Germany.
ORCID-Profile: Md Haider Zama, Friedhelm Schwenker
Zitieren
APA
Zama, M. H., & Schwenker, F. (2023). ECG Synthesis via Diffusion-Based State Space Augmented Transformer. Sensors, 23(19), 8328. https://doi.org/10.3390/s23198328
Vancouver
Zama MH, Schwenker F. ECG Synthesis via Diffusion-Based State Space Augmented Transformer. Sensors. 2023;23(19):8328. doi:10.3390/s23198328
BibTeX
@article{Zama2023,
author = {Zama, Md Haider and Schwenker, Friedhelm},
title = {ECG Synthesis via Diffusion-Based State Space Augmented Transformer},
journal = {Sensors},
year = {2023},
volume = {23},
number = {19},
pages = {8328},
doi = {10.3390/s23198328}
}
EUVIMED