To evaluate PCCT radiomic features of epicardial adipose tissue (EAT) in patients without coronary artery disease, stenosis, or calcifications in relation to arterial hypertension as a cardiac risk factor.
Approach:
Data Collection: Epicardial adipose tissue was manually segmented, and 1,015 radiomic features were extracted specifically from EAT using PyRadiomics.
Key Findings:
Logistic regression achieved moderate performance with a cross-validated AUC of 0.65 and a held-out test AUC of 0.59, indicating a need for further investigation.
The most robust finding was a lower mean EAT attenuation in the hypertension group.
Interpretation:
These exploratory findings should be regarded as hypothesis-generating and require validation in larger cohorts to confirm their significance.
Limitations:
Single-center study limits generalizability and may not reflect broader populations.
Small sample size may affect the robustness of findings and statistical power.
Exploratory nature of the study necessitates further validation to establish clinical relevance.
Conclusion:
The study highlights the potential of radiomics in assessing EAT and its correlation with hypertension, warranting further research to validate these findings.
