Vertebral fracture prevalence among women screened for the fracture intervention trial and a simple clinical tool to screen for undiagnosed vertebral fractures

Objective: To evaluate the ability of self-reported risk factors to identify postmenopausal women likely to have extant vertebral fractures because approximately two thirds of women with radiographic evidence of vertebral fracture are unaware of the fracture. Patients and Methods: Questionnaire and spinal radiographic data were collected from postmenopausal women with a femoral neck bone mineral density T score of -1.6 or lower during screening for the Fracture Intervention Trial. Logistic regression was used to identify risk factors for extant vertebral fractures and to derive a final multivariable model, Results: Almost two thirds of 25,816 women 55 years and older met the bone density criterion, and 21% of those had an extant vertebral fracture. The final model consisted of 5 self-reported items: history of vertebral fracture, history of nonvertebral fracture, age, height loss, and diagnosis of osteoporosis. These were combined to yield a Prevalent Vertebral Fracture Index (PVFI), The prevalence of women with vertebral fracture varied from 3.8% to 62.3% over the range PVFI of 0 to greater than 5, Among the 13,051 women screened with spinal radiographs, a PVFI of 4 or greater identified 65.5% of women with vertebral fractures (sensitivity), with a specificity of 68.6%. Excluding 881 women who reported prior vertebral fractures reduced the sensitivity to 53.6% and increased the specificity to 70.7% but did not alter the fracture prevalence at PVFI values less than 6, Conclusion: In this population, 5 simple questions identified women who were likely to have undiagnosed vertebral fractures. Further research is needed to determine the validity of this index in other populations, including women without low bone mineral density.