Machine learning models compared with current clinical indices to predict the outcome of high flow nasal cannula therapy in acute hypoxemic respiratory failure.

Journal: Critical care (London, England)
PMID: 40055757

Abstract

BACKGROUND: Early identification of patients with acute hypoxemic respiratory failure (AHRF) who are at risk of failing high-flow nasal cannula (HFNC) therapy could facilitate closer monitoring, and timely adjustment/escalation of treatment. We aimed to establish whether machine learning (ML) models could predict HFNC outcome, early in the course of treatment, with greater accuracy than currently used clinical indices.

Authors

  • Hang Yu
  • Sina Saffaran
    Faculty of Engineering Science, University College London, London, WC1E 6BT, UK.
  • Roberto Tonelli
    Department of Mathematics and Computer Science, University of Cagliari, Cagliari, Italy.
  • John G Laffey
    Anaesthesia and Intensive Care Medicine, Galway University Hospitals, Galway, Ireland.
  • Antonio M Esquinas
    Intensive Care Unit, Hospital Morales Meseguer, Murcia, Spain.
  • Lucas Martins de Lima
    Hcor Research Institute, Hcor Hospital, Rua Desembargador Eliseu Guilherme, 200 Paraíso, São Paulo, 04004-030, Brazil.
  • Letícia Kawano-Dourado
    Hcor Research Institute, Hcor Hospital, Rua Desembargador Eliseu Guilherme, 200 Paraíso, São Paulo, 04004-030, Brazil.
  • Israel S Maia
    Hcor Research Institute, Hcor Hospital, Rua Desembargador Eliseu Guilherme, 200 Paraíso, São Paulo, 04004-030, Brazil.
  • Alexandre Biasi Cavalcanti
    Research Institute, Heart Hospital (Hospital do Coração - Hcor), São Paulo, São Paulo, Brazil; Cancer Institute of the State of São Paulo (Instituto do Câncer do Estado de São Paulo - ICESP), São Paulo, São Paulo, Brazil.
  • Enrico Clini
    Respiratory Diseases Unit, Azienda Ospedaliero-Universitaria Policlinico of Modena, Modena, Italy.
  • Declan G Bates
    School of Engineering, University of Warwick, Coventry, CV4 7AL, UK.

Keywords

External Resources

Popular Topics
Recent Journals