Independent External Validation of FRAX and Garvan Fracture Risk Calculators: A Sub-Study of the FRISBEE Cohort

Abstract

Probabilistic models including clinical risk factors with or without bone mineral density (BMD) have been developed to estimate the 5- or 10-year absolute fracture risk. We investigated the performance of the FRAX and Garvan tools in a well-characterized population-based cohort of 3560 postmenopausal, volunteer women, aged 60 to 85 years at baseline, included in the Fracture Risk Brussels Epidemiological Enquiry (FRISBEE) cohort, during 5 years of follow-up. Baseline data were used to calculate the estimated 10-year risk of hip and major osteoporotic fractures (MOFs) for each participant using FRAX (Belgium). We computed the 5-year risk according to the Garvan model with BMD. For calibration, the predicted risk of fracture was compared with fracture incidence across a large range of estimated fracture risks. The accuracy of the calculators to predict fractures was assessed using the area under the receiver operating characteristic curves (AUC). The FRAX tool was well calibrated for hip fractures (slope 1.09, p < 0.001; intercept -0.001, p = 0.46), but it consistently underestimated the incidence of major osteoporotic fractures (MOFs) (slope 2.12, p < 0.001; intercept -0.02, p = 0.06). The Garvan tool was well calibrated for "any Garvan" fractures (slope 1.05, p < 0.001; intercept 0.01, p = 0.37) but largely overestimated the observed hip fracture rate (slope 0.32, p < 0.001; intercept 0.006, p = 0.05). The predictive value for hip fractures was better for FRAX (AUC: 0.841, 95% confidence interval [CI] 0.795-0.887) than for Garvan (AUC: 0.769, 95% CI 0.702-0.836, p = 0.01). The Garvan AUC for "any Garvan" fractures was 0.721 (95% CI 0.693-0.749) and FRAX AUC for MOFs was 0.708 (95% CI 0.675-0.741). In conclusion, in our Belgian cohort, FRAX estimated quite well hip fractures but underestimated MOFs, while Garvan overestimated hip fracture risk but showed a good estimation of "any Garvan" fractures. Both models had a good discriminatory value for hip fractures but only a moderate discriminatory ability for MOFs or "any Garvan" fractures. © 2021 The Authors. JBMR Plus published by Wiley Periodicals LLC on behalf of American Society for Bone and Mineral Research.

Keywords: BMD; DISCRIMINATION; FRACTURE; OSTEOPOROSIS; RISK ASSESSMENT; RISK FACTORS; VALIDATION.

Fig 1

Calibration of the calculators. Each panel shows a plot of the observed probability of fracture versus the mean estimated fracture probability for the cohort divided by decile of estimated probability. The solid line represents a perfectly calibrated model, and the dotted lines the line of best fit with its 95% confidence interval.

Fig 2

Receiving operating characteristics (ROC) curves for hip and calculator‐defined osteoporotic fractures.