How long does a knee replacement last? A systematic review and meta-analysis of case series and national registry reports with more than 15 years of follow-up

Abstract

Background: Knee replacements are the mainstay of treatment for end-stage osteoarthritis and are effective. Given time, all knee replacements will fail and knowing when this failure might happen is important. We aimed to establish how long a knee replacement lasts.

Methods: In this systematic review and meta-analysis, we searched MEDLINE and Embase for case series and cohort studies published from database inception until July 21, 2018. Articles reporting 15 year or greater survival of primary total knee replacement (TKR), unicondylar knee replacement (UKR), and patellofemoral replacements in patients with osteoarthritis were included. Articles that reviewed specifically complex primary surgeries or revisions were excluded. Survival and implant data were extracted, with all-cause survival of the knee replacement construct being the primary outcome. We also reviewed national joint replacement registry reports and extracted the data to be analysed separately. In the meta-analysis, we weighted each series and calculated a pooled survival estimate for each data source at 15 years, 20 years, and 25 years, using a fixed-effects model. This study is registered with PROSPERO, number CRD42018105188.

Findings: From 4363 references found by our initial search, we identified 33 case series in 30 eligible articles, which reported all-cause survival for 6490 TKRs (26 case series) and 742 UKRs (seven case series). No case series reporting on patellofemoral replacements met our inclusion criteria, and no case series reported 25 year survival for TKR. The estimated 25 year survival for UKR (based on one case series) was 72·0% (95% CI 58·0-95·0). Registries contributed 299 291 TKRs (47 series) and 7714 UKRs (five series). The pooled registry 25 year survival of TKRs (14 registries) was 82·3% (95% CI 81·3-83·2) and of UKRs (four registries) was 69·8% (67·6-72·1).

Interpretation: Our pooled registry data, which we believe to be more accurate than the case series data, shows that approximately 82% of TKRs last 25 years and 70% of UKRs last 25 years. These findings will be of use to patients and health-care providers; further information is required to predict exactly how long specific knee replacements will last.

Funding: The National Joint Registry for England, Wales, Northern Ireland, and Isle of Man and the Royal College of Surgeons of England.

Figure 1

Flow chart of case series and cohort study selection TKR=total knee replacement. UKR=unicondylar knee replacement. PKR=patellofemoral replacement.

Figure 2

Forest plot of estimates for reported survival of knee replacements from case series, , , , , , , , , , , , , , , , , , , , , (A) Total knee replacements at 15 years and 20 years. (B) Unicondylar knee replacements at 15 years, 20 years, and 25 years. The CIs for individual point estimates are shown with horizontal lines. The surrounding box shows the contribution made by that individual estimate to the overall pooled estimate, weighted by the standard error of that individual series.

Figure 3

Forest plot of estimates for reported survival of total knee replacements from registry reports at 15 years, 20 years, and 25 years

Figure 4

Forest plot of estimates for reported survival of unicondylar knee replacements from registry reports at 15 years, 20 years, and 25 years

Figure 5

Comparison of pooled survival estimates for knee replacements from case series and registry reports at 15 years, 20 years, and 25 years (A) Total knee replacements. (B) Unicondylar knee replacements. The size of the circle representing each point estimate is proportional to the total number of hip replacements at the start of all the series contributing to that pooled estimate. Bars indicate 95% CIs. TKR=total knee replacement. UKR=unicondylar knee replacements.