Deepaware: A hybrid deep learning and context-aware heuristics-based model for atrial fibrillation detection.

Journal: Computer methods and programs in biomedicine
PMID: 35640394

Abstract

BACKGROUND: State-of-the-art automatic atrial fibrillation (AF) detection models trained on RR-interval (RRI) features generally produce high performance on standard benchmark electrocardiogram (ECG) AF datasets. These models, however, result in a significantly high false positive rates (FPRs) when applied on ECG data collected under free-living ambulatory conditions and in the presence of non-AF arrhythmias.

Authors

  • Devender Kumar
    Department of Health Technology, Technical University of Denmark, Kgs. Lyngby 2800, Denmark. Electronic address: deku@dtu.dk.
  • Abdolrahman Peimankar
    SDU Health Informatics and Technology, The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense 5230, Denmark. Electronic address: abpe@mmmi.sdu.dk.
  • Kamal Sharma
    U. N. Mehta Institute of Cardiology and Research Centre, Civil Hospital Campus, Ahmedabad, Gujarat, India. Electronic address: kamalcardiodoc@gmail.com.
  • Helena Domínguez
    Bispebjerg Hospital, Department of Cardiology, Copenhagen, and Department of Biomedical Sciences at the University of Copenhagen, Denmark.
  • Sadasivan Puthusserypady
    Department of Health Technology, Technical University of Denmark, 2800 Kgs. Lyngby, Denmark.
  • Jakob E Bardram
    Department of Health Technology, Technical University of Denmark, Kgs. Lyngby 2800, Denmark. Electronic address: jakba@dtu.dk.

Keywords

External Resources

Popular Topics
Recent Journals