Machine learning models compared with current clinical indices to predict the outcome of high flow nasal cannula therapy in acute hypoxemic respiratory failure
Decision support tools based on SVM models could provide clinicians with more accurate early predictions of HFNC outcome than currently available clinical indices. If available, ABG measurements could improve the capability to accurately identify patients at risk of failing HFNC therapy.
Authors
- Letícia Kawano-Dourado (ORCID: https://orcid.org/0000-0003-0784-1331)
- Alexandre Biasi Cavalcanti (ORCID: https://orcid.org/0000-0003-2798-6263)
- Enrico Clini (ORCID: https://orcid.org/0000-0002-1515-5094)
- Israel Silva Maia (ORCID: https://orcid.org/0000-0003-3467-5287)
- Sina Saffaran (ORCID: https://orcid.org/0000-0001-9296-180X)
- António M. Esquinas (ORCID: https://orcid.org/0000-0003-0571-2050)
- Roberto Tonelli (ORCID: https://orcid.org/0000-0002-6202-0758)
- Declan G. Bates (ORCID: https://orcid.org/0000-0003-1395-9846)
- John G. Laffey (ORCID: https://orcid.org/0000-0002-1246-9573)
- Hang Yu
- Lucas Martins de Lima (ORCID: https://orcid.org/0009-0004-2282-8850)
Institutions
- University of Modena and Reggio Emilia (IT)
- Ollscoil na Gaillimhe – University of Galway (IE)
- University Hospital Galway (IE)
- University of Warwick (GB)
- Hospital General Universitario Morales Meseguer (ES)
- Azienda Ospedaliero-Universitaria di Modena (IT)
Publication Details
- Journal
- Critical Care
- Published
- 2025-03-07
- DOI
- https://doi.org/10.1186/s13054-025-05336-4
- Citations
- 7
- Primary Topic
- Respiratory Support and Mechanisms
- Type
- article
- Field-Weighted Citation Impact
- 10.63
Funders
- Royal Academy of Engineering
- Engineering and Physical Sciences Research Council