EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

A Neural Network for Atrial Fibrillation Detection via PPG

Rishad Howlader, Monika Jurgec, Andrea Schimanko, Christopher Dohnal, Anne Busch, Martin Baumgartner, Fabian Wiesmüller, Aaron Lauschensky, Dieter Hayn, Günter Schreier

Studies in Health Technology and Informatics · 2025

DOI: 10.3233/shti250201 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Rishad Howlader und 9 weiteren Autor:innen. Beteiligte Einrichtung: University of Applied Sciences Wiener Neustadt, Wiener Neustadt, Austria. Hauptthemen laut MEDLINE: Atrial Fibrillation, Photoplethysmography, Neural Networks, Computer, Mobile Applications. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Atrial fibrillation (AF) is a prevalent cardiac arrhythmia associated with severe complications such as ischemic stroke and heart failure. Early detection is essential for timely intervention; however, traditional diagnostic methods often lack scalability and accessibility. This project explores the use of photoplethysmography (PPG) signals recorded via smartphone applications to develop a predictive neural network model for AF detection. Data collection involved student participants using a smartphone app, supplemented with curated open-source datasets to enhance generalizability. A multilayer perceptron (MLP) was designed and trained using TensorFlow, with model performance evaluated based on accuracy, sensitivity, specificity, and F1-score. The initial model achieved an accuracy of approximately 75%, indicating the potential of PPG-based AF detection. Optimization efforts continue, focusing on improving predictive accuracy and minimizing false positives. Future research will refine the model architecture, validate it on larger datasets, and integrate findings into scalable digital health initiatives, such as the Austrian Digital Heart Program, supported by the Austrian Institute of Technology (AIT).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Atrial FibrillationPhotoplethysmographyNeural Networks, ComputerMobile ApplicationsHumansSmartphoneSensitivity and SpecificityMale

Stichwörter der Autor:innen

Artificial IntelligenceAtrial FibrillationMobile HealthNeural NetworksPhotoplethysmography

Autor:innen und Institutionen

  • University of Applied Sciences Wiener Neustadt, Wiener Neustadt, Austria.
  • Austrian Institute of Technology, Vienna, Austria.

Zitieren

APA

Howlader, R., Jurgec, M., Schimanko, A., Dohnal, C., Busch, A., Baumgartner, M., Wiesmüller, F., Lauschensky, A., Hayn, D., & Schreier, G. (2025). A Neural Network for Atrial Fibrillation Detection via PPG. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250201

Vancouver

Howlader R, Jurgec M, Schimanko A, Dohnal C, Busch A, Baumgartner M, et al. A Neural Network for Atrial Fibrillation Detection via PPG. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250201

BibTeX
@article{Howlader2025,
  author = {Howlader, Rishad and Jurgec, Monika and Schimanko, Andrea and Dohnal, Christopher and Busch, Anne and Baumgartner, Martin and Wiesmüller, Fabian and Lauschensky, Aaron and Hayn, Dieter and Schreier, Günter},
  title = {A Neural Network for Atrial Fibrillation Detection via PPG},
  journal = {Studies in Health Technology and Informatics},
  year = {2025},
  doi = {10.3233/shti250201}
}
Kostenlos starten →