Heart failure & cardiomyopathiesCohort study
Clustering in Dilated Cardiomyopathy at Initial Evaluation: An Effective Tool for Clinical Stratification
- Retrospective cohort study
- machine learning unsupervised clustering
- external validation
Authors' conclusion
Using ML, baseline ECG variables were found to effectively identify two DCM subgroups differing in disease progression and genetic background.
Study context
- Population
- Patients with dilated cardiomyopathy at first cardiological evaluationexternal validation n = 160
- Participants
- 409 patients
- Exposure
- CL2 vs CL1
Main finding
SCD/major ventricular arrhythmias
Hazard ratio
0.29
95% CI 0.13–0.67
CL2 vs CL1
HR 0.29 (95% CI 0.13–0.67)
As reported in the abstract
Observational data: associations, not effects.
Further findings
Pathogenic/likely pathogenic variants
P < 0.001
Original publication
Clustering in Dilated Cardiomyopathy at Initial Evaluation: An Effective Tool for Clinical Stratification. Eur J Heart Fail. Published 15 August 2025. doi:10.1002/ejhf.3780
Summarised from the published abstract; every number is checked against it