A review of the methods used to define glucocorticoid exposure and risk attribution when investigating the risk of fracture in a rheumatoid arthritis population

Background: Glucocorticoid therapy is used widely in patients with rheumatoid arthritis (RA) with good efficacy but concerns about safety including fractures. Estimates of fracture risk for any given patient are complicated by the dynamic pattern of glucocorticoid use, where patients vary in their dose, duration and timing of glucocorticoid use. Objective: To investigate which methods are currently used to attribute fractures to glucocorticoid exposure and investigate whether such methods can consider individual treatment patterns. Results: Thirty-eight studies used five common definitions of risk attribution to glucocorticoid exposure: "current use", "ever use", "daily dose", "cumulative dose" and "time variant". One study attempted to combine multiple definitions where "cumulative dose" was nested within "daily dose", covering the effects of dose and duration but not timing. The majority of results demonstrated an equivocal or increased risk of fracture with increased exposure, although there was wide variation, with odds ratios, hazard ratios and relative risks ranging from 0.16 to 8.16. Within definitions there was also variability in the results with the smallest range for "time variant", 1.07 to 2.8, and the largest for "cumulative dose", ranging from risk estimates of 0.88 to 8.12. Conclusion: Many studies have looked into the effect of glucocorticoids on fracture risk in patients with RA. Despite this, there is no clear consensus about the magnitude of risk. This is a consequence of the varied analysis models and their different assumptions. Moreover, no current analysis method allows consideration of dose, duration and timing of glucocorticoid therapy, preventing a clear understanding of fracture risk for patients and their individual treatment patterns. (C) 2016 The Authors. Published by Elsevier Inc.