Prediction of incident osteoporotic fractures in elderly women using the free estradiol index

A decline in postmenopausal estrogen concentration accelerates postmenopausal bone loss. We have examined the predictive power of endogenous estrogen production, DXA hip bone density (BMD), and heel quantitative ultrasound (QUS) on incident clinical fracture in a prospective 3-year population based, randomised controlled trial of calcium supplementation. Baseline blood testing on 1499 women mean (SD) age 75 ( 3) years for estradiol and sex hormone binding globulin measurements and ankle QUS measurements ( Lunar Achilles) was undertaken. Bone density was measured using DXA (Hologic 4500A) at 1 year. Incident clinical fractures were confirmed by X-ray. At 3 years, 10% had sustained more than one incident fracture. The fracture group had significantly lower levels of free estradiol index (FEI) ( 0.40 +/- 0.44 versus 0.49 +/- 0.54 pmol/nmol), hip BMD (0.776 +/- 0.129 versus 0.815 +/- 0.124 g/cm(2)) and measures of QUS (BUA 98 +/- 8 versus 101 +/- 8 db/Hz, SOS 1504 +/- 22 versus 1514 +/- 26 m/s; stiffness 67 +/- 11 versus 71 +/- 11 % mean young adult), respectively, than the non-fracture group. After adjustment for age, weight, use of topical estrogen, calcium supplementation and prevalent fracture, incident fracture was predicted by free estradiol index (HR per SD: 1.43: 95% CI: 1.08 - 1.91, P= 0.013). After adjustment for BMD, SOS or stiffness, the free estradiol index no longer predicted fracture. When examined separately, the presence of a vertebral or an appendicular fracture was associated with an 18% lower free estradiol index compared with no fracture. The risk of vertebral fracture increased with decreased free estradiol index ( HR per SD reduction: 1.63: 95% CI: 0.91 - 2.92); the risk of appendicular fracture also increased with decreased free estradiol index ( HR per SD reduction: 1.45: 95% CI: 1.05 - 2.01) after adjustment for age, weight, use of topical estrogen, calcium supplementation and prevalent fracture. After further adjustment for hip BMD or QUS measures, the effect of free estradiol index was no longer significant for vertebral or appendicular fractures. Therefore, a low free estradiol index increases the probability of having an incident fracture as a result of decreased BMD. These data confirm the importance of postmenopausal estrogen concentration in the pathogenesis of osteoporosis in elderly women.