Cross-population validation of the TyG-ABSI index as a novel predictor for chronic obstructive pulmonary disease: an integrated analysis using logistic regression and explainable machine learning - Pu
5 hours ago
- #COPD
- #Predictive Modeling
- #Metabolic Health
- The TyG-ABSI index is a composite marker of cardiometabolic risk used to predict COPD across Chinese and American populations.
- Analysis from CHARLS and NHANES cohorts shows a linear dose-response relationship, with higher TyG-ABSI levels significantly increasing COPD risk (OR up to 4.017 in NHANES).
- Explainable machine learning models, like XGBoost and LightGBM, achieved high predictive accuracy (AUC > 0.96) with SHAP identifying TyG-ABSI as a key feature.