Arrhythmias & electrophysiology
Radiomic Cardiac MRI Signatures for Predicting Ventricular Arrhythmias in Patients With Nonischemic Dilated Cardiomyopathy
Authors' conclusion
In this proof-of-concept study, radiomic analysis of LGE images provides additional prognostic value beyond LGE presence in predicting arrhythmia in patients with DCM.
Study context
- Population
- Patients with nonischemic dilated cardiomyopathy (DCM) who received primary prevention implantable cardioverter-defibrillators (ICDs) according to the clinical guidelines and had a cardiovascular magnetic resonance before ICD implantationPatients with DCM in the development data and in the external validation cohort · development data (Cleveland Clinic Foundation) 270 · external validation (Beth Israel Deaconess Medical Center) 113Events: 40 (15%) in development and 16 (15%) in external validation
- Predictors
- Model 1: clinical risk factors and scar presence; model 2: model 1 combined with late gadolinium enhancement (LGE) radiomics (left ventricular myocardial radiomic features extracted from LGE images)
- Predicted outcome
- Appropriate ICD intervention defined as shock or antitachycardia pacing for VT/VF
Methodological detailsmodel development and external validation
- Model development and external validation
Model performance
As reported in the abstract
C-statistic
Model 2, development
0.71(95% CI: 0.62-0.80)
Model 1, development
0.61(95% CI: 0.53-0.71)
Model 2, external validation
0.70(95% CI: 0.59-0.85)
Model 1, external validation
0.61(95% CI: 0.46-0.77)
- Model 2 vs model 1: P = 0.028 in development
- Model 2 vs model 1: P = 0.025 in external validation
Further findings
Continuous net reclassification index
Development
0.60(95% CI 0.29–0.91)
External validation
0.29(95% CI 0.26–0.56)
- P < 0.001 in development
- P = 0.03 in external validation
Radiomic signature
- Consensus clustering and pairwise correlation revealed 3 distinct radiomic features
- 3
Gray level co-occurrence matrix autocorrelation as independent predictor of VT/VF
- HR, development
- 1.45 [95% CI: 1.10-1.91]; P = 0.01
- HR, external validation
- 2.38 [95% CI: 1.28-4.42]; P = 0.01
Follow-up
Years
- Median follow-up, development
- 4.0 (IQR: 2.5-6.1)
- Median follow-up, external validation
- 2.6 (IQR: 1.2-4.1)
Original publication
Radiomic Cardiac MRI Signatures for Predicting Ventricular Arrhythmias in Patients With Nonischemic Dilated Cardiomyopathy. JACC Adv. Published 23 March 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →