EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Novel Method for ECG-Free Heart Sound Segmentation in Patients with Severe Aortic Valve Disease

Elza Abdessater iD, Paniz Balali iD, Jimmy Pawlowski, Jérémy Rabineau iD, Cyril Tordeur iD, Vitalie Faoro, Philippe van de Borne iD, Amin Hossein

Sensors · 2025

DOI: 10.3390/s25113360 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Elza Abdessater und 7 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Physics and Physiology, Department of Cardiology, Hôpital Erasme, Hôpital Universitaire de Bruxelles, 1070 Brussels, Belgium. Hauptthemen laut MEDLINE: Heart Sounds, Electrocardiography, Aortic Valve, Aortic Valve Disease. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fonds Erasme, Fonds de la Recherche Scientifique, PRODEX.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Severe aortic valve diseases (AVD) cause changes in heart sounds, making phonocardiogram (PCG) analyses challenging. This study presents a novel method for segmenting heart sounds without relying on an electrocardiogram (ECG), specifically targeting patients with severe AVD. Our algorithm enhances traditional Hidden Semi-Markov Models by incorporating signal envelope calculations and statistical tests to improve the detection of the first and second heart sounds (S1 and S2). We evaluated the method on the PhysioNet/CinC 2016 Challenge dataset and a newly acquired AVD-specific dataset. The method was tested on a total of 27,400 cardiac cycles. The proposed approach outperformed the existing methods, achieving a higher sensitivity and positive predictive value for S2, especially in the presence of severe heart murmurs. Notably, in patients with severe aortic stenosis, our proposed ECG-free method improved S2 sensitivity from 41% to 70%.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Heart SoundsElectrocardiographyAortic ValveAortic Valve DiseaseAortic Valve StenosisHumansAlgorithmsPhonocardiographySignal Processing, Computer-AssistedMaleFemale

Stichwörter der Autor:innen

aortic regurgitationaortic stenosisautomatic detectionphonocardiographytelemedicinevalvular heart disease

Autor:innen und Institutionen

  • Laboratory of Physics and Physiology, Department of Cardiology, Hôpital Erasme, Hôpital Universitaire de Bruxelles, 1070 Brussels, Belgium.
  • Laboratory of Image Synthesis and Analysis (LISA), Université libre de Bruxelles, 1050 Brussels, Belgium.
  • Research Unit in Cardio-Respiratory Physiology, Exercise & Nutrition, Faculty of Human Movement Sciences, Université libre de Bruxelles, 1070 Brussels, Belgium.
  • Department of Kinesiology and Health Sciences, University of Waterloo, Waterloo, ON N2L 3G1, Canada.

ORCID-Profile: Elza Abdessater, Paniz Balali, Jérémy Rabineau, Cyril Tordeur, Philippe van de Borne

Förderung

  • Fonds Erasme
  • Fonds de la Recherche Scientifique
  • PRODEX
  • Fonds pour la chirurgie cardiaque

Zitieren

APA

Abdessater, E., Balali, P., Pawlowski, J., Rabineau, J., Tordeur, C., Faoro, V., van de Borne, P., & Hossein, A. (2025). A Novel Method for ECG-Free Heart Sound Segmentation in Patients with Severe Aortic Valve Disease. Sensors. https://doi.org/10.3390/s25113360

Vancouver

Abdessater E, Balali P, Pawlowski J, Rabineau J, Tordeur C, Faoro V, et al. A Novel Method for ECG-Free Heart Sound Segmentation in Patients with Severe Aortic Valve Disease. Sensors. 2025. doi:10.3390/s25113360

BibTeX
@article{Abdessater2025,
  author = {Abdessater, Elza and Balali, Paniz and Pawlowski, Jimmy and Rabineau, Jérémy and Tordeur, Cyril and Faoro, Vitalie and van de Borne, Philippe and Hossein, Amin},
  title = {A Novel Method for ECG-Free Heart Sound Segmentation in Patients with Severe Aortic Valve Disease},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25113360}
}
Kostenlos starten →