Respiratory failure & ventilation
Phenotyping COVID-19 respiratory failure in spontaneously breathing patients with AI on lung computed tomography (CT)-scan
Authors' conclusion
Integrating lung-CT data in a LCA allowed us to identify two subphenotypes of COVID-19, with different clinical trajectories.
Study context
- Population
- Spontaneously breathing patients with COVID-19 respiratory failure with lung CT within 7 days of admission
- Participants
- 559 complete datasets
- Exposure
- Latent class analysis (LCA)-derived subphenotype 1 vs subphenotype 2
- Subphenotype 1n = 156
- Subphenotype 2n = 403reference
- Outcome
- Identification of COVID-19 subphenotypes by LCA of clinical, laboratory and deep-learning lung CT variables
Methodological detailsdeep learning CT analysis, latent class analysis
- Deep learning CT analysis
- Latent class analysis
Main finding
As reported in the abstract
Subphenotypes identified by LCA
LCA identified two subphenotypes
2
Observational data: associations, not effects.
Further findings
Comorbidities associated with endothelial dysfunction and 90-day mortality
- Subphenotype 1 had higher prevalence of endothelial-dysfunction comorbidities and higher 90-day mortality than subphenotype 2, even after adjustment
- Adjusted for clinically meaningful variables
Original publication
Phenotyping COVID-19 respiratory failure in spontaneously breathing patients with AI on lung CT-scan. Crit Care. Published 5 August 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →