Risk stratification for cardiovascular disease: a comparative analysis of cluster analysis and traditional prediction models
Authors' conclusion
Cluster analysis performed comparably to existing models and identified a larger high-risk group that included more individuals who developed CVD, though with more false positives.
Study context
- Population
- Individuals without prior cardiovascular disease (CVD) (mean age 66 years)161 CVD events
- Participants
- 3,416 individuals
- Exposure
- Cluster analysis risk stratification model vs Systematic Coronary Risk Evaluation (SCORE2), Pooled Cohort Equations (PCE) and PREVENT models
- Outcome
- Predictive accuracy for incident CVD (sensitivity, specificity, PPV, NPV, C-statistic)
- Follow-up
- Mean 5.2 years
Methodological detailsrisk prediction model development and comparison
- Risk prediction model development and comparison
Main finding
As reported in the abstract
Prediction of CVD
| Group | Sensitivity | PPV | Specificity | NPV |
|---|---|---|---|---|
| High-risk cluster | 59.0% | 7.5% | 64.2% | 96.9% |
High-risk cluster
Sensitivity59.0%
PPV7.5%
Specificity64.2%
NPV96.9%
Observational data: associations, not effects.
Original publication
Risk stratification for cardiovascular disease: a comparative analysis of cluster analysis and traditional prediction models. Eur J Prev Cardiol. Published 15 January 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →