Unsupervised Learning-Derived Complex Metabolic Signatures Refine Cardiometabolic Risk
Authors' conclusion
These metabolic signatures extract comprehensive information from the metabolomic profile while maintaining clarity and interpretability, facilitating clinical translation. The findings emphasize the crucial roles of lipid subpopulations in cardiometabolic risks, encouraging clinicians to take a more nuanced approach to managing blood lipids and balancing different disease risks.
Study context
- Population
- UK Biobank participants with plasma metabolomic profiles
- Participants
- 118,001 UK Biobank participants
- Exposure
- Unsupervised learning-derived metabolic signatures vs traditional lipids in cardiometabolic risk prediction
- Outcome
- Metabolic clusters identified
Methodological detailsunsupervised learning, nuclear magnetic resonance metabolomics
- Unsupervised learning
- Nuclear magnetic resonance metabolomics
Main finding
As reported in the abstract
- Metabolic clusters
- Eleven
- Linked loci
- 101
- Linked phenotypes, mostly cardiometabolic diseases
- 445
Observational data: associations, not effects.
Further findings
Cardiometabolic risk prediction
- Novel signatures partially outperformed traditional lipids
- Triglyceride-rich lipoproteins superior predictive power for ischemic heart disease, type 2 diabetes, and hypertension compared with apolipoprotein B and lipoprotein(a)
Non-high-density lipoprotein cholesterol and cardiometabolic diseases
- Increased risk of hyperlipidemia and ischemic heart disease; protective effect against type 2 diabetes
High-density lipoprotein clusters and cardiometabolic diseases
- Subpopulations enriched in free cholesterol or triglyceride increasing risk
- Subpopulations enriched in cholesterol esters providing protection
- Heterogeneous associations
Original publication
Unsupervised Learning-Derived Complex Metabolic Signatures Refine Cardiometabolic Risk. JACC Adv. Published 20 February 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →