Subphenotyping prone position responders with machine learning
Distinct ARDS subphenotypes with varying mortality were identified in patients undergoing prone positioning; however, predicting which patients benefited from this intervention based on available data was not possible. These findings underscore the need for continued efforts in phenotyping ARDS through multimodal data to better understand the heterogeneity of this population.
Authors
- Boris Jung (ORCID: https://orcid.org/0000-0003-2522-1531)
- Julie Josse
- Maxime Fosset
- Elias Baedorf Kassis (ORCID: https://orcid.org/0000-0001-5491-6063)
- Maximilian S. Schaefer (ORCID: https://orcid.org/0000-0001-8186-4748)
- Simone Redaelli (ORCID: https://orcid.org/0000-0003-0128-7376)
- Dario von Wedel (ORCID: https://orcid.org/0000-0001-8102-0254)
- Daniel Talmor (ORCID: https://orcid.org/0000-0002-7239-8068)
- Nicolas Molinari (ORCID: https://orcid.org/0000-0002-1786-0088)
Institutions
- Lahey Hospital and Medical Center (US)
- Beth Israel Deaconess Medical Center (US)
- Institut national de recherche en sciences et technologies du numérique (FR)
- Harvard University (US)
- Université de Montpellier (FR)
- Düsseldorf University Hospital (DE)
- Centre Hospitalier Universitaire de Montpellier (FR)
- Lahey Medical Center (US)
- Hôpital Lapeyronie (FR)
- Heinrich Heine University Düsseldorf (DE)
- University of Milano-Bicocca (IT)
- Charité - Universitätsmedizin Berlin (DE)
Publication Details
- Journal
- Critical Care
- Published
- 2025-03-14
- DOI
- https://doi.org/10.1186/s13054-025-05340-8
- Citations
- 8
- Primary Topic
- Respiratory Support and Mechanisms
- Type
- article
- Field-Weighted Citation Impact
- 12.15
Funders
- Agence Nationale de la Recherche