Sex-based differences in risk of revision for infection after hip, knee, shoulder, and ankle arthroplasty in osteoarthritis patients: a multinational registry study of 4,800,000 implants

Abstract

Background and purpose: We aimed to determine sex differences for periprosthetic joint infections after primary arthroplasty of the hip, knee, ankle, and shoulder in osteoarthritis patients in an international perspective.

Methods: This is a multinational combined arthroplasty registry study. Each arthroplasty registry performed Cox-regression analysis of their data and reported the crude and adjusted hazard ratios (HR) with an a priori designed data form. A random-effects model was used to pool these HRs to estimate an overall HR with 95% confidence interval (CI). Adjustment was undertaken for patient age, BMI, ASA grade, type of fixation, and type of implant. 9 arthroplasty registries participated. Patients who received primary total joint arthroplasty for primary osteoarthritis were considered: 2,134,313 hip arthroplasties, 2,658,237 knee arthroplasties, 57,889 shoulder arthroplasties, and 8,445 ankle arthroplasties. We calculated hazard ratios (HR) for the overall risk of complete revision due to infection for each implant type and follow-up.

Results: The pooled HR for revision due to infection for men compared with women at 1-year follow-up was 1.60 (95% confidence interval [CI] 1.42-1.80) for hip arthroplasties; 2.06 (CI 1.90-2.46) for knee arthroplasties; 4.51 (CI 2.99-6.80) for shoulder arthroplasties; and 0.87 (CI 0.46-1.62) for ankle arthroplasties. These results remained consistent over time and were identified in both unadjusted and adjusted models.

Conclusion: Men have a higher risk of revision due to infection than women after primary hip, knee, and shoulder arthroplasty. No evidence of difference was found for ankle arthroplasty. These elevated relative risks persist in the fully adjusted investigations and over the 10-year postoperative period studied.

Figure 1

Flowchart registry inclusions.

Figure 2

Forest plots: pooled unadjusted estimates and adjusted estimates for hip and knee arthroplasties at 1-year follow-up. HR > 1, equals a higher risk for men compared with women. Weights of registries in %. For abbreviations, see Table 1.