Unveiling risk factors and predicting osteoporosis through bone density based aging model

Background Osteoporosis is a progressive skeletal disorder influenced by multiple clinical and lifestyle factors. Early identification of individuals at high risk is essential for prevention and personalized management. This study aimed to identify key determinants of osteoporosis and to establish a bone density–based aging model to evaluate accelerated skeletal aging. Methods We analyzed data from a large cohort with dual-energy X-ray absorptiometry (DXA) measurements of the lumbar spine and proximal femur. Univariate and multivariate regression models were applied to assess the associations between clinical and lifestyle factors and osteoporosis risk. A bone density aging model was developed using support vector regression to estimate bone density age, and bone density age acceleration (BDAA) was calculated as the residual from chronological age. Results The bone density aging model showed good predictive performance (mean absolute error = 5.716 years, R² = 0.145). Higher BDAA was positively correlated with osteoporosis risk across bone health categories, including individuals without clinical diagnosis. In addition, BDAA differed significantly by exercise level, dietary pattern, body mass index, blood pressure, and metabolic comorbidities, providing insights into skeletal aging beyond chronological age. Conclusions Bone density based biological aging models can improve early identification and personalized risk stratification of osteoporosis. This approach may facilitate and support the development of precision medicine strategies in osteoporosis prevention and management. Trial registration Not applicable.