Real-World Deployment of a ML Pipeline for Pressure Wounds Prediction
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
- Sami Perrin
- Jérémie Despraz (ORCID: https://orcid.org/0000-0002-2435-4079)
- Stefan Milosavljevic (ORCID: https://orcid.org/0000-0002-9135-1353)
- Jean Louis Raisaro (ORCID: https://orcid.org/0000-0003-2052-6133)
- Sophie Pouzols (ORCID: https://orcid.org/0000-0002-2750-3519)
- Cédric Mabire (ORCID: https://orcid.org/0000-0003-2666-8300)
- Oksana Riba‐Grognuz (ORCID: https://orcid.org/0000-0002-2961-2655)
- S. Nektarijevic (ORCID: https://orcid.org/0000-0003-4769-0187)
- Laure Vancauwenberghe (ORCID: https://orcid.org/0009-0000-0850-0016)
- Paloma Cito (ORCID: https://orcid.org/0009-0001-0780-711X)
Institutions
- Swiss Data Science Center (CH)
- University of Lausanne (CH)
Publication Details
- Journal
- Studies in health technology and informatics
- Published
- 2025-05-15
- DOI
- https://doi.org/10.3233/shti250280
- Primary Topic
- Pressure Ulcer Prevention and Management
- Type
- article
- Field-Weighted Citation Impact
- 0.00