A longitudinal analysis of serum adiponectin levels and bone mineral density in postmenopausal women in Taiwan

Abstract

Since bone and fat mass are derived from mesenchyme in early development, adipokines secreted by adipose tissue may have an effect on bone metabolism. The relationship between adiponectin and bone mineral density (BMD) has been inconsistent in previous reports, with results being dependent on age, gender, menopausal status and bone sites. We investigated the relationship between serum adiponectin levels and the BMD of proximal femur and vertebrae bones in a 96-week longitudinal study of post-menopausal women with repeated measures of both. Linear regression models were used to determine the relation between adiponectin and BMD at each time point cross-sectionally, and a generalized estimating equation (GEE) model was used to investigate the longitudinal trends. Among 431 subjects, 376 (87%) provided baseline adiponectin measurements and 373 provided more than two measurements for longitudinal analysis. The means of serum adiponectin and BMD decreased with time. In linear regression models, adiponectin at baseline, the 48th week and the 96th week appeared to be inversely associated with BMD of proximal femur bone, but not lumbar spine after adjusting for age and various confounders. However, they all turn insignificant with further adjustment of body mass index. The inverse association between adiponectin and BMD of proximal femur is substantiated by all generalized equation models. Before adding the BMI in the model, the increase of 1 mg/dL of adiponectin can accelerate the decrease of proximal femur BMD by 0.001 (SE = 0.0004, p = 0.008). With BMI in the model, the drop rate was 0.0008 (SE = 0.0004, p = 0.026) and remained similar with further adjustment of two bone turnover markers. In this longitudinal analysis with both adiponectin and BMD measured at three time points, we demonstrate that with the increase of adiponectin level, the decline of proximal femur BMD in postmenopausal women accelerated during a period of 96 weeks.

Figure 1

Whiskers plots of BMD and T-score at baseline, week 24 and week 96 in the quartiles of serum adiponectin levels: BMD (g/cm²) (A), T score (B) at lumbar spine and BMD (g/cm²) (C), T-score (D) at total proximal femur.