Coronary Plaque Radiomic Phenotypes Predict Fatal or Nonfatal Myocardial Infarction: Analysis of the SCOT-HEART Trial
Authors' conclusion
Radiomics-based precision phenotyping of coronary plaque morphology provided improvements to long-term prediction of myocardial infarction by CT angiography over and above clinical factors and plaque burden.
Study context
- Population
- Patients undergoing coronary computed tomography (CT) angiography in the SCOT-HEART trial (aged 58 ± 9 years; 56% male)scans analysed
- Participants
- 1,750 patients
- Comparison
- Clinical model vs + plaque burden vs + eigen radiomic features for MI prediction
- Primary endpoint
- Fatal or nonfatal MI
- Follow-up
- Median 8.6 years
Methodological detailspost hoc analysis
- Post hoc analysis
Primary result
As reported in the abstract
Prediction of fatal or nonfatal MI (C-statistic) · median 8.6 years
Clinical model
0.70
C-statistic
Clinical + plaque burden
0.70
C-statistic
Clinical + plaque burden + radiomics
0.74
C-statistic
- Fatal or nonfatal MI events
- 82
- Eigen radiomic features associated with MI in univariable analysis
- 15
- Features retaining association after adjustment for CV risk score and plaque burden
- 8
Further findings
Cumulative/dynamic AUC over time · after fifth year of follow-up
- Model including eigen radiomic features had higher cumulative/dynamic AUC values following the fifth year
Original publication
Coronary Plaque Radiomic Phenotypes Predict Fatal or Nonfatal Myocardial Infarction: Analysis of the SCOT-HEART Trial. JACC Cardiovasc Imaging. Published 30 October 2024. doi:10.
Summarised from the published abstract; every number is checked against it