Physical Address
304 North Cardinal St.
Dorchester Center, MA 02124
Epicardial Fat Radiomics: Early Detection of Heart Failure Risk
A radiomic signature of epicardial adipose tissue from routine cardiac CT identifies patients at high risk for heart failure, offering a scalable tool for early risk stratification.
Background
Epicardial adipose tissue (EAT) surrounds the heart. Rather than measuring volume, researchers developed FRP_HF—a radiomic profile capturing texture and morphology from standard cardiac CT. Applied to 72,751 patients across UK centers (2007-2022), it identifies myocardial stress signals before symptoms emerge.
Key Findings
- FRP_HF showed excellent discrimination: C-statistics 0.869 (internal validation) and 0.850 (external validation)
- Each 25-percentile increase in FRP_HF associated with nearly 4-fold higher heart failure risk; highest decile faced 20-fold increased risk
- Adding FRP_HF to conventional models improved 5-year discrimination and net reclassification with clinical benefit
- Predictive across demographic groups, coronary disease severity, and ejection fraction spectrum (HFrEF, HFmrEF, HFpEF)
- FRP_HF predicted heart failure specifically, not myocardial infarction, suggesting it reflects myocardial rather than vascular biology
Why It Matters
This establishes a scalable automated tool for identifying asymptomatic individuals at heart failure risk. By analyzing routine cardiac images, clinicians can risk-stratify without additional testing. This enables precision prevention and targeted deployment of adipose tissue-modulating therapies—shifting focus from treating to preventing heart failure.
Limitations
Findings come exclusively from UK CCTA populations, potentially limiting generalizability. The biological mechanism linking EAT patterns to myocardial remodeling remains unclear.
Original paper: Early Prediction of Heart Failure From Routine Cardiac CT Using Radiomic Phenotyping of Epicardial Fat. — Journal of the American College of Cardiology. 10.1016/j.jacc.2026.02.5116
