What question did this study set out to answer?

To assess whether pericardial adipose tissue volume enhances prediction of cardiovascular events beyond traditional metrics like coronary artery calcium score.

March 26, 2026Open Access

Deep Learning-Derived Pericardial Adipose Tissue by Electrocardiogram-Gated Cardiac Computed Tomography Predicts Cardiovascular Events Beyond Coronary Calcium Score

Key Result

Higher pericardial adipose tissue volume conferred an incremental risk of cardiovascular events even in patients with low coronary artery calcium scores (HR 1.24, 95% CI: 1.05-1.48).

Key Points

To assess whether pericardial adipose tissue volume enhances prediction of cardiovascular events beyond traditional metrics like coronary artery calcium score.
Analyzed ECG-gated cardiac CT scans from 11,897 residents without heart disease history.
Measured pericardial adipose tissue volume and density using a deep learning segmentation model.
Stratified patients based on PAT volume and coronary artery calcium score.
Applied Cox proportional hazard models to assess associations with cardiovascular events.
9.6% experienced total cardiovascular events over a median follow-up of 16.4 years.
Found progressively lower CVD-free survival linked to higher PAT and CAC scores (p < 0.001).
Higher PAT volume increased risk even in low CAC individuals (HR = 1.24).
PAT improved risk assessment within borderline and intermediate PREVENT TM categories.

Structured PICO

Does deep learning-derived pericardial adipose tissue volume predict cardiovascular events beyond coronary calcium score and the PREVENT equation in patients without known ASCVD or heart failure?

Population

11,897 residents of Olmsted County, MN, without known history of heart failure and atherosclerotic cardiovascular disease (ASCVD) events who underwent non-contrast, ECG-gated CAC scans.

Intervention

Measurement of pericardial adipose tissue (PAT) volume and density using an automated deep learning segmentation model on ECG-gated cardiac CT (stratified by top quartile >319 cm3).

Comparator

Standard risk prediction using Coronary Artery Calcium (CAC) score and the AHA PREVENT equation (or lower PAT volume).

Outcome

Composite outcome of total CVD (myocardial infarction, ischemic stroke, heart failure, and cardiovascular death).composite

Deep learning-derived pericardial adipose tissue volume provides independent prognostic value for cardiovascular events beyond traditional CAC scoring and the PREVENT risk equation.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

Pericardial adipose tissue (PAT) is an emerging imaging biomarker of cardiovascular disease (CVD) risk. We evaluated whether PAT volume improves prediction of cardiovascular events beyond Coronary Artery Calcium (CAC) score and the AHA Predicting Risk of Cardiovascular Disease Events (PREVENT TM ) equation. We analyzed data of 11,897 Olmsted County, MN, residents without known history of heart failure and atherosclerotic cardiovascular disease (ASCVD) events who underwent non-contrast, ECG-gated CAC scans. PAT volume (cm 3 ) and density (Hounsfield units) were measured using a validated automated deep learning (DL) segmentation model (Dice score 0.94). We stratified patients into groups based on PAT volume (cut-off: top quartile 319 cm 3 ) and CAC score (cut-off: 100 Agatston units). Cox proportional hazard models evaluated associations with the composite outcome of total CVD (myocardial infarction, ischemic stroke, heart failure, and cardiovascular death), while adjusting for cardiovascular risk factors, and CAC score across PREVENT TM risk categories. Over a median of 16.4 years, 9.6 % experienced total CVD events. Kaplan-Meier curves demonstrated progressively lower CVD-free survival across PAT and CAC groups (p < 0.001). PAT volume stratified risk across CAC categories, with higher volume conferring incremental risk even at low CAC (HR = 1.24, 95% CI:1.05–1.48), and enhanced risk stratification within borderline and intermediate PREVENT TM categories. PAT volume provides prognostic value for total CVD events beyond PREVENT TM and CAC scoring.