Deep-learning algorithm helps to standardise ATS/ERS spirometric acceptability and usability criteria.

Journal: The European respiratory journal
PMID: 32527741

Abstract

RATIONALE: While American Thoracic Society (ATS)/European Respiratory Society (ERS) quality control criteria for spirometry include several quantitative limits, it also requires manual visual inspection. The current approach is time consuming and leads to high intertechnician variability. We propose a deep-learning approach called convolutional neural network (CNN), to standardise spirometric manoeuvre acceptability and usability.

Authors

  • Nilakash Das
    Laboratory of Respiratory Diseases, Department of Chronic Diseases, Metabolism and Ageing, KU Leuven, Belgium.
  • Kenneth Verstraete
    Laboratory of Respiratory Diseases and Thoracic Surgery, Dept of Chronic Diseases, Metabolism and Ageing, Katholieke Universiteit Leuven, Leuven, Belgium.
  • Sanja Stanojevic
    Translational Medicine, Division of Respiratory Medicine, Hospital for Sick Children, Toronto, ON, Canada.
  • Marko Topalovic
  • Jean-Marie Aerts
    KU Leuven, Department of Biosystems, Division of Animal and Human Health Engineering, Measure, Model and Manage Bioresponse (M3-BIORES), Kasteelpark Arenberg 30, 3001 Leuven, Belgium.
  • Wim Janssens

Keywords

External Resources

Popular Topics
Recent Journals