Metabolomics and Machine Learning Identify Metabolic Differences and Potential Biomarkers for Frequent Versus Infrequent Gout Flares
Authors' conclusion
Systematic metabolic alterations underlie InGF and FrGF, and distinct profiles are associated with differences in gout flare frequencies. Predictive modeling based on selected metabolites from metabolomics can differentiate InGF and FrGF.
Study context
- Population
- Patients with gout with infrequent or frequent flares; discovery cohort (163 infrequent gout flares (InGF), 239 frequent gout flares (FrGF)) and independent validation cohort (97 InGF, 139 FrGF)discovery and validation cohorts
- Comparison
- Infrequent gout flares vs frequent gout flares
- Outcome
- Differential serum metabolites and pathways between InGF and FrGF, and ML predictive model performance (AUC)
Methodological detailsuntargeted metabolomics (discovery), quantitative targeted metabolomics (optimisation), independent validation cohort, machine learning (ML)-based multivariable selection
- Untargeted metabolomics (discovery)
- Quantitative targeted metabolomics (optimisation)
- Independent validation cohort
- ML-based multivariable selection
Performance
As reported in the abstract
Differential metabolites between InGF and FrGF
439
AUC for differentiating InGF and FrGF, discovery cohort
0.88
AUC for differentiating InGF and FrGF, validation cohort
0.67
Original publication
Metabolomics and Machine Learning Identify Metabolic Differences and Potential Biomarkers for Frequent Versus Infrequent Gout Flares. Arthritis Rheumatol. Published 9 November 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →