Age and aging are important predictors of health status, disease progression, drug kinetics, and effects. The purpose was to develop ensemble learning-based physiological age (PA) models for evaluating drug metabolism. National Health and Nutrition Examination Survey (NHANES) data were modeled with ensemble learning to obtain two PA models, PA-M1 and PA-M2. PA-M1 included body composition, blood and urine biomarkers, and disease variables as predictors. PA-M2 had blood and urine-derived variables as predictors. Activity phenotypes for cytochrome-P450 (CYP) CYP2E1, CYP1A2, CYP2A6, xanthine oxidase (XO), and N-acetyltransferase-2 (NAT-2) and telomere attrition were assessed. Bayesian networks were used to obtain mechanistic systems pharmacology model structures for PA. The study included n = 22,307 NHANES participants (51.5% female, mean age 46.0 years, range: 18-79 years). The PA-M1 and PA-M2 distributions had greater dispersion across age strata with a right skew for younger age strata and a left skew for older age strata. There was no evidence of algorithmic bias based on sex or race/ethnicity. Klotho, lean body mass, glycohemoglobin, and systolic blood pressure were the top four predictors for PA-M1. Glycohemoglobin, serum creatinine, total cholesterol, and urine creatinine were the top four predictors for PA-M2. The models also performed satisfactorily in independent validation. Model-predicted PA was associated with CYP2E1, CYP1A2, CYP2A6, XO, and NAT-2 activity. Telomere attrition was associated with greater PA-M1 and PA-M2. Ensemble learning models provide robust assessments of PA from easily obtained blood and urine biomarkers. PA is associated with Phase I drug-metabolizing enzyme phenotypes.
Read full abstract