Prevention & lipidsDiagnostic or prognostic study
Lipidomic Risk Score to Enhance Cardiovascular Risk Stratification for Primary Prevention
- Risk prediction model development and validation study
- machine learning (ridge regression)
- external validation
Authors' conclusion
LRS, augmenting the FRS, presents potential to improve intermediate-risk stratification and to predict atherosclerotic markers using a simple blood test, suitable for clinical application.
Study context
- Population
- Primary prevention of cardiovascular disease (CVD), intermediate-risk group; AusDiab (development), Busselton Health Study (external validation), BioHEART (coronary artery calcium scoring (CACS)-based outcomes)AusDiab n = 10,339
- Comparison
- LRS vs Framingham Risk Score (FRS)
- Outcome
- Risk prediction and reclassification of CVD events within the intermediate-risk group, benchmarked against the FRS
Performance
As reported in the abstract
CVD events, intermediate-risk group
- AusDiab
- AUC increase 0.114 (95% CI 0.1123–0.1157); P < 0.001
- Busselton Health Study
- AUC increase 0.077 (95% CI 0.0755–0.0785); P < 0.001
- AusDiab
- net reclassification improvement 0.36 (95% CI 0.21–0.51); P < 0.001
- Busselton Health Study
- net reclassification improvement 0.33 (95% CI 0.15–0.49); P < 0.001
Further findings
| Outcome | LRS | FRS | AUC improvement | P value |
|---|---|---|---|---|
| CACS-based outcomes (BioHEART) | 0.02 | P < 1.0 × 10-5 | ||
| AUC | 0.76 | 0.74 |
Simplified LRS
- Simplified, clinically applicable LRS had comparable performance to the original LRS
Original publication
Lipidomic Risk Score to Enhance Cardiovascular Risk Stratification for Primary Prevention. J Am Coll Cardiol. Published 30 July 2024. doi:10.1016/j.jacc.2024.04.060
Summarised from the published abstract; every number is checked against it