Abstract
Identifying robust, non-invasive biomarkers of biological age is key to preventive medicine. While gut aging clocks exist, the oral microbiome remains underexplored as a quantitative biomarker. Using oral microbiome data from two NHANES cohorts (N = 4,675), we identified 64 age-dependent bacterial genera and developed a machine learning model predicting chronological age, with generalizability in an independent external cohort (N = 1,293). We derived an Oral Microbiome Aging Acceleration (OMAA) Score as the residual of predicted age against chronological age. The OMAA Score independently predicted all-cause mortality (HR = 1.05, P = 0.024) and frailty (OR = 1.05, P = 0.008), correlated with impaired kidney function (lower eGFR: β = -0.066, P = 5.22×10-4), and enhanced risk prediction for cancer (AUC 0.70 vs. 0.67, P = 0.009) and heart attack (AUC 0.79 vs. 0.76, P = 0.016) beyond conventional risk factors. Diet and medication had minimal association. The OMAA Score offers a scalable, non-invasive tool to identify high-risk individuals for age-related morbidity and mortality.