Active learning and margin strategies for arrhythmia classification in implantable devices.

Journal: Computers in biology and medicine
PMID: 39951979

Abstract

BACKGROUND AND OBJECTIVES: The massive storage of cardiac arrhythmic episodes from Implantable Cardioverter Defibrillators (ICD) and the advent of new artificial intelligence algorithms are opening up new opportunities for electrophysiological knowledge extraction. However, in this context, accurate and reliable episode labeling by expert cardiologists still remains a manual, costly, and time-consuming process.

Authors

  • José-María Lillo-Castellano
    Universidad Rey Juan Carlos, Department of Signal Theory and Communications, Telematics and Computing Systems, Camino del Molino, 5. 28942, Fuenlabrada, Madrid, Spain.
  • Inmaculada Mora-Jiménez
    Department of Signal Theory and Communications, Telematics and Computing, Universidad Rey Juan Carlos, Fuenlabrada 28943, Spain.
  • María Martín-Méndez
    Medtronic Ibérica ®S.A, Dep. Cardiac Rhythm and Heart Failure, C/ María de Portugal 9, 28050 Madrid, Spain.
  • Laia Cerdá
    Medtronic Ibérica ®S.A, Dep. Cardiac Rhythm and Heart Failure, C/ María de Portugal 9, 28050 Madrid, Spain.
  • Arcadi García-Alberola
    Hospital CU Virgen de la Arrixaca. Arrhythmia Unit, Ctra. Madrid-Cartagena, s/n. 30120-El Palmar Murcia, Spain.
  • José Luis Rojo-Álvarez
    Department of Signal Theory and Communications, Telematics and Computing, Universidad Rey Juan Carlos, Fuenlabrada 28943, Spain; Universidad de las Fuerzas Armadas-ESPE, Sangolquí 171-5-231B, Ecuador.
  • Devis Tuia
    3 MultiModal Remote Sensing Group, Department of Geography, University of Zurich , Zurich, Switzerland .

Keywords

External Resources

Popular Topics
Recent Journals