Comprehensive evaluation of triglyceride glucose index-a body shape index (TyG-ABSI) for incident peripheral artery disease: data-driven phenotyping and machine learning-based risk prediction in the U
3 days ago
- #Insulin Resistance
- #Machine Learning
- #Peripheral Artery Disease
- The study evaluates the triglyceride glucose index-a body shape index (TyG-ABSI) for predicting peripheral artery disease (PAD) in the UK Biobank cohort.
- TyG-ABSI combines Triglyceride-Glucose (TyG) with A Body Shape Index (ABSI) to reflect insulin resistance and visceral adiposity.
- Higher TyG-ABSI levels were strongly associated with increased PAD incidence, with a 15-year cumulative incidence of 4.16% in the top quartile vs. 0.98% in the bottom quartile.
- Machine learning models, including logistic regression, were used for PAD prediction, with logistic regression showing the best performance (AUC = 0.788).
- Data-driven clustering identified four metabolic subgroups, with the highest PAD risk in the insulin resistance/glucose dysfunction cluster.
- SHAP analysis highlighted TyG-ABSI, age, and neutrophil count as key predictors for PAD.
- The study suggests TyG-ABSI as a robust predictor for PAD risk and emphasizes the utility of interpretable machine learning models for clinical risk stratification.