Coronary disease & ACSDiagnostic or prognostic study
Development and validation of a computed tomography myocardial perfusion imaging radiomic model for major adverse cardiovascular events prediction: a multicenter study
- Development and validation of a computed tomography myocardial perfusion imaging radiomic model for major adverse cardiovascular events prediction: a multicenter study
- retrospectively enrolled
- eight hospitals
Authors' conclusion
The radiomic features from multiparametric CT-MPI maps simultaneously captured perfusion features associated with MACE at both macrovascular and microvascular levels. The combined model exhibited improved MACE prognostic performance compared with conventional models while maintaining high interpretability.
Study context
- Population
- Patients with suspected coronary artery disease who underwent coronary CT angiography (CCTA) and CT myocardial perfusion imaging (CT-MPI)patients from eight hospitals
- Participants
- 784 patients
- Comparison
- Model 3 vs Model 1 and Model 2 for Major Adverse Cardiovascular Events (MACE) prediction
Performance
As reported in the abstract
MACE prediction, C-index of Model 3
| Test or model | Training set | Internal validation set | External validation set |
|---|---|---|---|
| Model 3 | 0.898 (95% confidence interval [CI]: 0.856-0.947) | 0.844 (95% CI: 0.780-0.908) | 0.840 (95% CI: 0.791-0.889) |
- Significant improvements over Model 1 and Model 2
- all P < 0.05
Further findings
- Time-dependent AUC for MACE prediction, Model 3, external validation set · 1-, 3-, and 5-year
- 0.890 [95% CI: 0.831-0.948] · 1-year · 3-year 0.880 [95% CI: 0.823-0.938] · 5-year 0.837 [95% CI: 0.726-0.949]
Time-dependent AUC for MACE prediction, Model 3, external validation set · 1-, 3-, and 5-year
- Model 3 had the largest time-dependent AUC values compared with Model 1 and Model 2
Original publication
Development and validation of a computed tomography myocardial perfusion imaging radiomic model for major adverse cardiovascular events prediction: a multicenter study. Eur Heart J Cardiovasc Imaging. Published 6 February 2026. doi:10.1093/ehjci/jeag044
Summarised from the published abstract; every number is checked against it