Evaluation of semi-automated versus fully automated technologies for computed tomography scalable body composition analyses in patients with severe acute respiratory syndrome Coronavirus-2
When compared to a semi-automated software, a fully automated, AI-based software provides consistent findings for key CT body composition measures (SM, SAT, VAT, TAT). While our findings support good overall agreement as evidenced by small biases and limited outliers, additional studies are needed in other clinical populations to further support validity and advanced precision, especially in the context of body composition and malnutrition assessment.
Authors
- Mirza Faisal Beg (ORCID: https://orcid.org/0000-0001-6706-8630)
- Karteek Popuri (ORCID: https://orcid.org/0000-0002-1729-3255)
- Cara Joyce (ORCID: https://orcid.org/0000-0003-0468-8271)
- Vasilios Vasilopoulos (ORCID: https://orcid.org/0000-0003-3903-717X)
- Patricia Sheean (ORCID: https://orcid.org/0000-0003-0032-514X)
- Amy Wozniak (ORCID: https://orcid.org/0000-0002-0670-3677)
- Jared Seigal
- P. O'Connor (ORCID: https://orcid.org/0000-0003-3704-5475)
Institutions
- Loyola University Medical Center (US)
- Memorial University of Newfoundland (CA)
- Simon Fraser University (CA)
- Loyola University Chicago (US)
Publication Details
- Journal
- Clinical Nutrition ESPEN
- Published
- 2025-06-11
- DOI
- https://doi.org/10.1016/j.clnesp.2025.06.006
- Primary Topic
- COVID-19 Clinical Research Studies
- Type
- article
- Field-Weighted Citation Impact
- 0.00