EUVIMEDEUVIMED entdecken
Crossref

Transfer Learning for Multi-Lead ECG Analysis in Cardiac Arrest Risk Classification

Zahra Safari, Emad Mohammed, Behrouz Far

Proceedings of the Canadian Conference on Artificial Intelligence · 19.05.2025

DOI: 10.21428/594757db.c9ff5d78 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the Canadian Conference on Artificial Intelligence, online erschienen am 19.05.2025. Verfasst von Zahra Safari und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sudden cardiac arrest (SCA) is the sudden loss of all heart activity due to an irregular heart rhythm, accounting for about 20% of fatalities in developed countries. Detecting SCA early is challenging because it occurs suddenly and unpredictably. Electrocardiograms (ECGs) provide valuable heart activity data utilized by Machine Learning (ML) models to predict known conditions like arrhythmias rather than predicting cardiac arrest risk. Additionally, these ML models typically rely on the full 12-lead ECGs, which is impractical for wearable devices. The proposed method in this study utilizes a pre-trained deep-learning model to predict cardiac arrest risk using single-lead ECG data.

Zitieren

APA

Safari, Z., Mohammed, E., & Far, B. (2025). Transfer Learning for Multi-Lead ECG Analysis in Cardiac Arrest Risk Classification. Proceedings of the Canadian Conference on Artificial Intelligence. https://doi.org/10.21428/594757db.c9ff5d78

Vancouver

Safari Z, Mohammed E, Far B. Transfer Learning for Multi-Lead ECG Analysis in Cardiac Arrest Risk Classification. Proceedings of the Canadian Conference on Artificial Intelligence. 2025. doi:10.21428/594757db.c9ff5d78

BibTeX
@article{Safari2025,
  author = {Safari, Zahra and Mohammed, Emad and Far, Behrouz},
  title = {Transfer Learning for Multi-Lead ECG Analysis in Cardiac Arrest Risk Classification},
  journal = {Proceedings of the Canadian Conference on Artificial Intelligence},
  year = {2025},
  doi = {10.21428/594757db.c9ff5d78}
}
Kostenlos starten →