Machine learning‐based clustering identifies obesity subgroups with differential multi‐omics profiles and metabolic patterns
Authors' conclusion
Although the two identified clusters may represent progressive obesity-related pathologic processes measured at different stages, other mechanisms in combination could also underpin the identified clusters given no significant age difference between the comparative groups. For instance, clusters may reflect differences in dietary/behavioral patterns or differential rates of metabolic damage.
Study context
- Population
- Individuals living with obesity (BMI ≥ 30 kg/m²) in the Multi-Ethnic Study of Atherosclerosis (MESA) cohortMESA cohort
- Participants
- 243 individuals
- Exposure
- iCluster1 vs iCluster2
- Outcome
- Multi-omics-defined clusters and cardiometabolic traits
Methodological detailsmachine learning-based integrative unsupervised clustering, proteomics and metabolomics
- Machine learning-based integrative unsupervised clustering
- Proteomics and metabolomics
Main finding
As reported in the abstract
- Two distinct clusters identified (iCluster1 and 2)
- iCluster2 had significantly higher average BMI, fasting blood glucose and inflammation
- iCluster1 associated with higher total cholesterol and HDL-C
- Cell growth, lipogenesis and energy expenditure pathways positively associated with iCluster1
- Inflammatory response and insulin resistance pathways positively associated with iCluster2
Observational data: associations, not effects.
Original publication
Machine learning‐based clustering identifies obesity subgroups with differential multi‐omics profiles and metabolic patterns. Obesity (Silver Spring). Published 5 November 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →