Machine learning and geometric morphometrics to predict obstructive sleep apnea from 3D craniofacial scans.

Journal: Sleep medicine
PMID: 35567881

Abstract

BACKGROUND: Obstructive sleep apnea (OSA) remains massively underdiagnosed, due to limited access to polysomnography (PSG), the highly complex gold standard for diagnosis. Performance scores in predicting OSA are evaluated for machine learning (ML) analysis applied to 3D maxillofacial shapes.

Authors

  • Fabrice Monna
    ARTEHIS, UMR CNRS 6298, Université de Bourgogne Franche-Comté, 6 boulevard Gabriel, Bât. Gabriel, F-21000, Dijon, France.
  • Raoua Ben Messaoud
    HP2 Laboratory, Inserm U1300, Grenoble Alpes University, Grenoble, France.
  • Nicolas Navarro
    Biogéosciences UMR CNRS 6282, Université de Bourgogne Franche-Comté, 6, boulevard Gabriel, Bat. Gabriel, F-21000, Dijon, France; EPHE, PSL University, 4-14 rue Ferrus, F-75014, Paris, France.
  • Sébastien Baillieul
    HP2 Laboratory, Inserm U1300, Grenoble Alpes University, Grenoble, France; EFCR Laboratory, Thorax and Vessels Division, Grenoble Alpes University Hospital, Grenoble, France.
  • Lionel Sanchez
    ARCTIC, 18 Chemin Cadet, F-97411, Saint-Paul, France.
  • Corinne Loiodice
    HP2 Laboratory, Inserm U1300, Grenoble Alpes University, Grenoble, France; EFCR Laboratory, Thorax and Vessels Division, Grenoble Alpes University Hospital, Grenoble, France.
  • Renaud Tamisier
    University Grenoble Alpes Grenoble, France.
  • Marie Joyeux-Faure
    HP2 Laboratory, Inserm U1300, Grenoble Alpes University, Grenoble, France; EFCR Laboratory, Thorax and Vessels Division, Grenoble Alpes University Hospital, Grenoble, France.
  • Jean-Louis Pépin
    University Grenoble Alpes Grenoble, France.

Keywords

External Resources

Popular Topics
Recent Journals