Machine Learning Analysis of Left Ventricular Function to Characterize Heart Failure With Preserved Ejection Fraction.

Journal: Circulation. Cardiovascular imaging
PMID:

Abstract

BACKGROUND: Current diagnosis of heart failure with preserved ejection fraction (HFpEF) is suboptimal. We tested the hypothesis that comprehensive machine learning (ML) of left ventricular function at rest and exercise objectively captures differences between HFpEF and healthy subjects.

Authors

  • Sergio Sanchez-Martinez
    Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain. Electronic address: sergio.sanchezm@upf.edu.
  • Nicolas Duchateau
    Inria Asclepios research project, Sophia Antipolis, France.
  • Tamas Erdei
    Wales Heart Research Institute, Cardiff University, United Kingdom.
  • Gabor Kunszt
    Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain (S.S.-M., G.P., B.H.B.); Asclepios Research Group, Université Côte d'Azur, Inria, Sophia Antipolis, France (N.D.); Wales Heart Research Institute, Cardiff University, United Kingdom (T.E., A.G.F.); Department of Cardiology, Oslo University Hospital, Norway (G.K., S.A.); Department of Circulation and Imaging, Faculty of Medicine, NTNU, Norwegian University of Science and Technology, Trondheim, Norway (S.A.); Clinic of Cardiology, St. Olav Hospital, Trondheim, Norway (S.A.); Department of Cardiology, University of Eastern Piedmont, Novara, Italy (A.D., P.M.); Division of Cardiology, University Hospital "S.Maria della Misericordia", Perugia, Italy (E.C.); and Catalan Institution for Research and Advanced Studies, Barcelona, Spain (B.H.B.).
  • Svend Aakhus
    Department of Circulation and Medical Imaging, Faculty of Medicine and Health Science, Norwegian University of Science and Technology, Prinsesse Kristinas gate 3, Trondheim 7030, Norway.
  • Anna Degiovanni
    Department of Thoracic, Heart and Vascular Diseases, Maggiore Della Carità Hospital, Corso Mazzini 18, 28100 Novara, Italy.
  • Paolo Marino
    Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain (S.S.-M., G.P., B.H.B.); Asclepios Research Group, Université Côte d'Azur, Inria, Sophia Antipolis, France (N.D.); Wales Heart Research Institute, Cardiff University, United Kingdom (T.E., A.G.F.); Department of Cardiology, Oslo University Hospital, Norway (G.K., S.A.); Department of Circulation and Imaging, Faculty of Medicine, NTNU, Norwegian University of Science and Technology, Trondheim, Norway (S.A.); Clinic of Cardiology, St. Olav Hospital, Trondheim, Norway (S.A.); Department of Cardiology, University of Eastern Piedmont, Novara, Italy (A.D., P.M.); Division of Cardiology, University Hospital "S.Maria della Misericordia", Perugia, Italy (E.C.); and Catalan Institution for Research and Advanced Studies, Barcelona, Spain (B.H.B.).
  • Erberto Carluccio
    Cardiology and Cardiovascular Pathophysiology-Heart Failure Unit, 'Santa Maria della Misericordia' Hospital, University of Perugia, Piazzale Giorgio Menghini, 1, 06129 Perugia, Italy.
  • Gemma Piella
    Information and Communication Technologies Department, Universitat Pompeu Fabra, Barcelona, Spain.
  • Alan G Fraser
    Wales Heart Research Institute, Cardiff University Cardiff UK.
  • Bart H Bijnens
    Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain; ICREA, Barcelona, Spain.