Ratio of visceral-to-subcutaneous fat area improves long-term mortality prediction over either measure alone: automated CT-based AI measures with longitudinal follow-up in a large adult cohort
AI-based CT measures of SAT, VAT, and VSR are predictive of mortality, with VSR being the highest performing fat area biomarker overall. These metrics tended to perform better for women and younger patients. Incorporating AI tools can augment patient assessment and management, improving outcome.
Authors
- John W. Garrett (ORCID: https://orcid.org/0000-0002-8152-736X)
- Daniel Liu (ORCID: https://orcid.org/0000-0002-4153-504X)
- Adam J. Kuchnia (ORCID: https://orcid.org/0000-0002-3418-0965)
- Glen M. Blake (ORCID: https://orcid.org/0000-0002-1530-5267)
- Perry Joseph Pickhardt (ORCID: https://orcid.org/0000-0002-5534-8202)
- Matthew Lee (ORCID: https://orcid.org/0000-0001-7103-4660)
Institutions
- University of Wisconsin–Madison (US)
- King's College London (GB)
- University of Wisconsin Health (US)
Publication Details
- Journal
- Abdominal Radiology
- Published
- 2025-08-11
- DOI
- https://doi.org/10.1007/s00261-025-05149-7
- Primary Topic
- Cardiovascular Disease and Adiposity
- Type
- article
- Field-Weighted Citation Impact
- 0.00