Heart failure & cardiomyopathiesCohort study
Early Prediction of Heart Failure From Routine Cardiac CT Using Radiomic Phenotyping of Epicardial Fat
- Multicentre cohort study
- 9 UK centres
- external validation
Authors' conclusion
Automated radiomic phenotyping of EAT from routine CCTA enables scalable, biologically informed stratification of future HF risk before clinical onset
Study context
- Population
- Adults without known heart failure (HF) or MI undergoing coronary computed tomographic angiography (CCTA), 9 UK centres, 2007–2022
- Participants
- 72,751 adults
- Exposure
- Internal vs External
- Internaln = 59,327
- Externaln = 13,424
- Outcome
- Incident HF (radiomic signature of EAT, FRPHF)
Main finding
As reported in the abstract
Incident HF, discrimination and risk per 25-percentile increase in FRPHF · median follow-up 5.1 (internal) and 4.0 (external) years
| Group | Value | C-statistic | Adjusted HR per 25-percentile increase |
|---|---|---|---|
| Internal | 2.9% | 0.869 (95% CI: 0.850-0.889) | 3.90 (95% CI: 3.13-4.84) |
| External | 2.7% | 0.850 (95% CI: 0.831-0.870) | 3.79 (95% CI: 3.01-4.76) |
- Adjusted HRs, both cohorts
- P < 0.001
Observational data: associations, not effects.
Further findings
| Outcome | Estimate |
|---|---|
| Incremental value of FRPHF over conventional risk models (incl. EAT volume, CAD severity), external cohort · 5 years — Conventional model + FRPHF vs Conventional model | ΔAUC 0.047 (95% CI 0.029–0.065) |
| Incremental value of FRPHF over conventional risk models (incl. EAT volume, CAD severity), external cohort · 5 years — Conventional model + FRPHF vs Conventional model | NRI 0.39 (95% CI 0.29–0.48) |
Incremental value of fat radiomic profile for HF (FRPHF) over conventional risk models (incl. Epicardial adipose tissue (EAT) volume, coronary artery disease (CAD) severity), external cohort · 5 years
- Suggested net clinical benefit on decision curve analysis
Subgroups (demographic, EF spectrum)
- Associations consistent across demographic subgroups and across the EF spectrum
Original publication
Early Prediction of Heart Failure From Routine Cardiac CT Using Radiomic Phenotyping of Epicardial Fat. J Am Coll Cardiol. Published 8 April 2026. doi:10.1016/j.jacc.2026.02.5116
Summarised from the published abstract; every number is checked against it