Real-World Deployment of a ML Pipeline for Pressure Wounds Prediction.

Journal: Studies in health technology and informatics
Published Date: May 15, 2025

Abstract

Hospital-acquired pressure injuries (HAPIs) are common complications that impact patient outcomes and strain healthcare resources. The Braden Scale is the standard tool for assessing HAPI risk, but it has limitations, including a high false-positive rate, potential oversight of subtle symptoms, and added workload for nurses. To address these issues, a fully automated AI clinical decision support system (CDSS) achieving 0.90 AUROC on retrospective data has been deployed.

Authors

  • Jérémie Despraz
    Groupe Data Science, Direction des systèmes d'information, Département infrastructures, Centre hospitalier universitaire vaudois, 1011 Lausanne.
  • Snežana Nektarijević
    Biomedical Data Science Center, Lausanne University Hospital, Lausanne, CH.
  • Laure Vancauwenberghe
    Swiss Data Science Center, Swiss Institute of Technology, Zurich/Lausanne, CH.
  • Paloma Cito
    Biomedical Data Science Center, Lausanne University Hospital, Lausanne, CH.
  • Stefan Milosavljevic
    Swiss Data Science Center, Swiss Institute of Technology, Zurich/Lausanne, CH.
  • Sami Perrin
    Biomedical Data Science Center, Lausanne University Hospital, Lausanne, CH.
  • Sophie Pouzols
    IUFRS, University of Lausanne, Lausanne, CH.
  • Oksana Riba Grognuz
    Swiss Data Science Center, Swiss Institute of Technology, Zurich/Lausanne, CH.
  • Cédric Mabire
    IUFRS, University of Lausanne, Lausanne, CH.
  • Jean Louis Raisaro
    Biomedical Data Science Center, Lausanne University Hospital (CHUV) and Lausanne University, Lausanne, Switzerland.

Keywords

External Resources

Popular Topics
Recent Journals