EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Morphological Autoencoders for Beat-by-Beat Atrial Fibrillation Detection Using Single-Lead ECG

Rafael Silva iD, Ana Fred iD, Hugo Plácido da Silva iD

Sensors · 06.03.2023 · 23 (5) · 2854

DOI: 10.3390/s23052854 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 06.03.2023. Verfasst von Rafael Silva und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Bioengineering (DBE), Instituto Superior Técnico (IST), Av. Rovisco Pais 1, 1049-001 Lisboa, Portugal. Hauptthemen laut MEDLINE: Atrial Fibrillation. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundação para a Ciência e Tecnologia, Ministry of Science Technology and Higher Education, FCT/Ministério da Ciência, Tecnologia e Ensino Superior (MCTES).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Engineered feature extraction can compromise the ability of Atrial Fibrillation (AFib) detection algorithms to deliver near real-time results. Autoencoders (AEs) can be used as an automatic feature extraction tool, tailoring the resulting features to a specific classification task. By coupling an encoder to a classifier, it is possible to reduce the dimension of the Electrocardiogram (ECG) heartbeat waveforms and classify them. In this work we show that morphological features extracted using a Sparse AE are sufficient to distinguish AFib from Normal Sinus Rhythm (NSR) beats. In addition to the morphological features, rhythm information was included in the model using a proposed short-term feature called Local Change of Successive Differences (LCSD). Using single-lead ECG recordings from two referenced public databases, and with features from the AE, the model was able to achieve an F1-score of 88.8%. These results show that morphological features appear to be a distinct and sufficient factor for detecting AFib in ECG recordings, especially when designed for patient-specific applications. This is an advantage over state-of-the-art algorithms that need longer acquisition times to extract engineered rhythm features, which also requires careful preprocessing steps. To the best of our knowledge, this is the first work that presents a near real-time morphological approach for AFib detection under naturalistic ECG acquisition with a mobile device.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Atrial FibrillationHumansSignal Processing, Computer-AssistedElectrocardiographyHeart RateAlgorithms

Stichwörter der Autor:innen

ECG morphological featuresatrial fibrillation detectionautomatic feature extractionsupervised autoencoder

Autor:innen und Institutionen

  • Department of Bioengineering (DBE), Instituto Superior Técnico (IST), Av. Rovisco Pais 1, 1049-001 Lisboa, Portugal.
  • Instituto de Telecomunicações (IT), Av. Rovisco Pais 1, Torre Norte-Piso 10, 1049-001 Lisboa, Portugal.

ORCID-Profile: Rafael Silva, Ana Fred, Hugo Plácido da Silva

Förderung

  • Fundação para a Ciência e Tecnologia
  • Ministry of Science Technology and Higher Education
  • FCT/Ministério da Ciência, Tecnologia e Ensino Superior (MCTES)
  • Instituto de Telecomunicações (IT)
  • National Funds (OE)

Zitieren

APA

Silva, R., Fred, A., & Plácido da Silva, H. (2023). Morphological Autoencoders for Beat-by-Beat Atrial Fibrillation Detection Using Single-Lead ECG. Sensors, 23(5), 2854. https://doi.org/10.3390/s23052854

Vancouver

Silva R, Fred A, Plácido da Silva H. Morphological Autoencoders for Beat-by-Beat Atrial Fibrillation Detection Using Single-Lead ECG. Sensors. 2023;23(5):2854. doi:10.3390/s23052854

BibTeX
@article{Silva2023,
  author = {Silva, Rafael and Fred, Ana and Plácido da Silva, Hugo},
  title = {Morphological Autoencoders for Beat-by-Beat Atrial Fibrillation Detection Using Single-Lead ECG},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {5},
  pages = {2854},
  doi = {10.3390/s23052854}
}
Kostenlos starten →