Clinical Research Directory

AI-Based CT Analysis of Coronary Plaque Evolution

Sponsor: Zhejiang Hospital

Summary

This retrospective, multicenter, observational study will evaluate an artificial intelligence-based system for quantitative assessment and risk stratification of coronary atherosclerotic plaque. Adults with coronary plaque on baseline coronary CT angiography (CCTA) and at least one follow-up CCTA obtained between January 1, 2020 and December 31, 2025 will be identified from participating centers. The system will integrate clinical factors, CCTA plaque morphology and burden, functional measures, hemodynamic parameters, and biomechanical features using baseline data. Two independent readers will assess conventional CCTA findings, including CAD-RADS and adverse plaque characteristics, while remaining blinded to system outputs. The primary outcome is patient-level definite progression of non-calcified plaque, defined by annualized change in non-calcified plaque percent atheroma volume exceeding the reproducibility-based minimum detectable change (MDC95). Model discrimination will be assessed by area under the receiver operating characteristic curve and compared with conventional CCTA models. Approximately 326 participants are planned.

Official title: Artificial Intelligence-Based CT Analysis of Coronary Plaque Characteristics and Longitudinal Evolution

Key Details

Conditions

Locations (5)