Risk of serious infections with immunosuppressive drugs and glucocorticoids for lupus nephritis: a systematic review and network meta-analysis

Abstract

Background: To perform a systematic review and network meta-analysis (NMA) to compare the risk of serious infections with immunosuppressive medications and glucocorticoids in lupus nephritis.

Methods: A trained librarian performed two searches: (1) PubMed for all lupus nephritis trials from the end dates for the systematic review for the 2012 American College of Rheumatology (ACR) lupus nephritis treatment guidelines and the 2012 Cochrane Systematic Review on treatments for lupus nephritis, to September 2013; and (2) PubMed and SCOPUS for all lupus trials (excluding lupus nephritis) from inception to February 2014, to obtain additional trials for harms data in any lupus patient. The search was updated to May 2016. Duplicate title/abstract review and duplicate data abstractions by two abstractors independently was performed for all eligible studies, including those studies abstracted for the 2012 ACR lupus nephritis treatment guidelines and the 2012 Cochrane Systematic Review on lupus nephritis treatments. We performed a systematic review and a Bayesian NMA, including randomized controlled trials (RCTs) of immunosuppressive drugs or glucocorticoids in patients with lupus nephritis assessing serious infection risk. Markov chain Monte Carlo methods were used to model 95 % credible intervals (CrI). Sensitivity analyses examined the robustness of estimates.

Results: A total of 32 RCTs with 2611 patients provided data. There were 26 two-arm, five three-arm, and one four-arm trials. We found that tacrolimus was associated with significantly lower risk of serious infections compared to glucocorticoids, cyclophosphamide (CYC), mycophenolate mofetil (MMF), and azathioprine (AZA) with odds ratios (95 % CrI) of 0.33 (0.12-0.88), 0.37 (0.15-0.87), 0.340 (0.18-0.81), and 0.32 (0.12-0.81), respectively. Conversely, CYC low dose (LD), CYC high dose (HD), and HD glucocorticoids were associated with higher odds of serious infections compared to tacrolimus, ranging from 4.84 to 12.83. We also found that MMF followed by AZA (MMF-AZA) was associated with significantly lower risk of serious infections as compared to CYC LD, CYC HD, CYC-AZA, or HD glucocorticoids with odds ratios (95 % CrI) of 0.09 (0.01-0.76), 0.07 (0.01-0.54), 0.14 (0.02-0.71), and 0.03 (0.00-0.56), respectively. Estimates were similar to pair-wise meta-analyses. Sensitivity analyses that varied estimate (odds ratio vs. Peto's odds ratio), method (random vs. fixed effects model), data (sepsis vs. serious infection data; exclusion of observational studies), treatment grouping (CYC and CYC HD as a combined treatment group vs. separate), made little/no difference to these estimates.

Conclusions: Tacrolimus and MMF-AZA combination were associated with lower risk of serious infections compared to other immunosuppressive drugs or glucocorticoids for lupus nephritis. In conjunction with comparative efficacy data, these data can help patients make informed decisions about treatment options for lupus nephritis.

Prospero registration: CRD42016032965.

Keywords: Cyclophosphamide; Glucocorticoids; Immunosuppressive drugs; Lupus; Lupus nephritis; Mycophenolate mofetil; Network meta-analysis; Serious infections; Tacrolimus.

Fig. 1

PRISMA flow chart for study selection. A total of 32 studies provided data on serious infections

Fig. 2

Each node indicates a treatment included in the analysis. The lines represent the direct (head-to-head) comparisons identified in the literature. The surface area of the nodes (represented as circles) represents the number of patients who received the treatment – the larger the size of the circle, the greater the number of patients who received that treatment. For example, there were more patients treated with mycophenolate mofetil or cyclophosphamide (left side of the figure) than tacrolimus or cyclosporine (right side of the figure). Some treatments are noted outside the nodes simply due to longer names that would not fit within the circle size, proportional to the number of patients that received that treatment

Fig. 3

League tables highlight the main findings from the analysis. For each comparison, the random effects model odds ratios (OR) and 95 % credible intervals are provided. The results of the plots are read from top to bottom and left to right. An OR < 1 means that the treatment in the top left is better than the comparator treatment. For example, tacrolimus is better/safer than glucocorticoids (a) and mycophenolate mofetil-azathioprine is better/safer than low-dose cyclophosphamide (b), since the odds of serious infections are lower in each case than the comparator. Significant results are in bold

Fig. 4

The figure shows the deviances from consistency and the inconsistency models. Consistency model assumes that the evidence derived from direct and indirect estimates should be in agreement. The inconsistency model does not make this assumption. Ideally, all deviances should be 2 or below. There were 71 unconstrained data points. Three data points show deviances of > 2 (extreme right side in the figure). Residual deviances from consistency versus inconsistency models were 72.49 versus 67.73 for 69 data points each. Deviance information criteria was 325.65 versus 325.96, respectively, indicating that the inconsistency model is a slightly better fit for the data than the consistency model. Thus, the model showed some evidence of inconsistency

Fig. 5

Sensitivity analyses comparing method of estimation, odds ratio versus Peto’s odds ratio for meta-analyses of tacrolimus versus mycophenolate mofetil and tacrolimus versus cyclophosphamide. Same analyses using the Peto Method for rare events