Peri-aortic fat to assess cardiovascular aging using an AI-driven radiomic biomarker
Authors' conclusion
Radiomic profiling of PAAT on routine chest CT yields a scalable imaging biomarker of cardiovascular aging.
Study context
- Population
- Adults with routine chest CT in four cohorts with different protocolstraining 4451
- Exposure
- Accelerated or resilient peri-aortic adipose tissue (PAAT) radiomic CV age vs normative agers
- Outcome
- Incident 5-point major adverse cardiovascular events (MACE):
- MI
- Stroke
- Revascularization
- HF
- Death
Methodological detailsmulticohort, external validation
- Multicohort
- External validation
Main finding
As reported in the abstract
5-point MACE
Each group vs normativeHazard ratio (95% CI)
Accelerated
1.51(1.37–1.66)
Resilient
0.70(0.63–0.77)
- ΔAge-stratified event-free survival differed across groups
- log-rank P < .001
Observational data: associations, not effects.
Further findings
Age prediction accuracy (31-feature radiomic signature)
Years
- Training MAE
- 2.2
- Primary external validation MAE
- 2.7
ΔAge in separate higher-risk cohort
- Median ΔAge
- +5.4 years
Risk reclassification, cardiovascular age (CV-Age) substituted into PREVENT
- Categorical NRI +0.03
- P < 0.01
- Continuous NRI +0.04
- P < 0.05
Original publication
Peri-aortic fat to assess cardiovascular aging using an AI-driven radiomic biomarker. Eur Heart J. Published 9 July 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →