Vascular Remodeling Radiomic Risk Model (FRP) Calculator

Vascular Remodeling Radiomic Risk Model: Explanation and Clinical Context This calculator operationalizes a published perivascular fat radiomic profile (FRP) derived from coronary CT angiography to reflect adverse perivascular adipose tissue remodeling (fibrosis and microvascular changes) that accompanies chronic coronary inflammation. The original model was trained via machine learning (random forest) using hundreds of PVAT radiomic features and validated against both biology (radiotranscriptomics) and outcomes. In cohort analyses, FRP significantly improved prediction of major adverse cardiac events beyond traditional risk factors, stenosis, calcium score and high-risk plaque characteristics.

A cut-off of 0.63 defined FRP-positive status; individuals with FRP≥0.63 had ~10.8× adjusted hazard of MACE versus FRP<0.63, and those with both FRP≥0.63 and high-risk plaque features exhibited ~43× adjusted hazard versus FRP−/HRP−. For a continuous read-out, each 0.01 increase in FRP corresponded to ~12% higher adjusted hazard in the SCOT-HEART cohort. This page does not recreate the proprietary training pipeline; instead it accepts an FRP already computed by your validated workflow and translates it to risk categories/multipliers as reported.

Use as a research/decision-support adjunct; clinical actions should integrate the full patient context, guideline-directed therapy, and local validation.