A Randomized 2x2 Factorial Clinical Trial of Renal Transplantation: Steroid-Free Maintenance Immunosuppression with Calcineurin Inhibitor Withdrawal after Six Months Associates with Improved Renal Function and Reduced Chronic Histopathology

Abstract

Introduction: The two most significant impediments to renal allograft survival are rejection and the direct nephrotoxicity of the immunosuppressant drugs required to prevent it. Calcineurin inhibitors (CNI), a mainstay of most immunosuppression regimens, are particularly nephrotoxic. Until less toxic antirejection agents become available, the only option is to optimize our use of those at hand.

Aim: To determine whether intensive rabbit anti-thymocyte globulin (rATG) induction followed by CNI withdrawal would individually or combined improve graft function and reduce graft chronic histopathology-surrogates for graft and, therefore, patient survival. As previously reported, a single large rATG dose over 24 hours was well-tolerated and associated with better renal function, fewer infections, and improved patient survival. Here we report testing whether complete CNI discontinuation would improve renal function and decrease graft pathology.

Methods: Between April 20, 2004 and 4-14-2009 we conducted a prospective, randomized, non-blinded renal transplantation trial of two rATG dosing protocols (single dose, 6 mg/kg vs. divided doses, 1.5 mg/kg every other day x 4; target enrollment = 180). Subsequent maintenance immunosuppression consisted of tacrolimus, a CNI, and sirolimus, a mammalian target of rapamycin inhibitor. We report here the outcome of converting patients after six months either to minimized tacrolimus/sirolimus or mycophenolate mofetil/sirolimus. Primary endpoints were graft function and chronic histopathology from protocol kidney biopsies at 12 and 24 months.

Results: CNI withdrawal (on-treatment analysis) associated with better graft function (p <0.001) and lower chronic histopathology composite scores in protocol biopsies at 12 (p = 0.003) and 24 (p = 0.013) months, without affecting patient (p = 0.81) or graft (p = 0.93) survival, or rejection rate (p = 0.17).

Conclusion: CNI (tacrolimus) withdrawal at six months may provide a strategy for decreased nephrotoxicity and improved long-term function in steroid-free low immunological risk renal transplant patients.

Trial registration: ClinicalTrials.gov NCT00556933.

Fig 1. CONSORT flow diagram of randomized 2x2 trial of rATG induction dosing and delayed CNI withdrawal [52].

The study statisticians provided computer-generated randomized assignments in sequentially-numbered, sealed opaque envelopes opened after obtaining consent for trial participation. Randomization included stratification by race (Caucasian/Asian vs. non-Caucasian/Asian), donor type (living vs. deceased), and whether listed for eventual pancreas transplantation. Study patients were identified and enrolled by attending transplant physicians and study coordinators. The integrity of the treatment arm assignments made by this system was monitored and confirmed by the study statisticians. Two patients not meeting enrollment criteria were consented and randomized in error, but were identified before transplantation and removed from participation in the trial.

Fig 2. Immunosuppression induction regimens and maintenance target blood levels.

Fig 3. Effect of CNI withdrawal on renal function.

The impact of CNI withdrawal on GFR was detected both by intent-to-treat (for all donors, p <0.01) and on-treatment analyses of deviation from a pre-withdrawal baseline GFR for each patient. Post-transplantation months 3–6 GFR values were averaged for use as baselines for CNI-minimization patients; for CNI-withdrawn patients, the three months preceding actual withdrawal were used. To ensure a valid on-treatment comparison of the effects of CNI withdrawal, five patients in the CNI-minimization arm were censored from the analysis due to early rejection (<6 months) because such patients were disqualified from withdrawal in the CNI-withdrawn group. Each time point is the average percentage change of three months of GFR scores.

Fig 4. Chronic Banff injury score distributions by on-treatment CNI withdrawal status.

Protocol biopsies collected at approximately 12 and 24 months were scored by a transplant renal pathologist blinded to treatment group assignment (author K.F.) for evidence of rejection, BK virus nephropathy, antibody-mediated rejection, recurrent disease, inflammation, and Banff 2005 categories of chronic renal injury. Chronic injury categories were arteriolar hyaline thickening (ah), allograft glomerulopathy (cg), interstitial fibrosis (ci), tubular atrophy (ct), and vascular fibrous intimal thickening (cv). A chronic injury composite score for each group was also created from the five individual injury category scores. Severity scores within each category could be 0 (<5%; none or minimal), 1 (>5%—<25%; mild), 2 (>25%—<50%, moderate), or 3 (>50%, severe). The composite scores shown are the total numbers of ah, cg, ci, ct, and cv scores in each severity grade (0, 1, 2, or 3). The proportions of patients in each severity grade (0, 1, 2, and 3) for both the individual categories and the composite were compared using Fisher’s exact test. Intent-to-treat (ITT) p-values are included in the figure.

Fig 5. Post hoc on-treatment analysis of graft inflammation (i IFTA & i Total).

Inflammation was scored both within areas of interstitial fibrosis and tubular atrophy (i IFTA) and throughout the biopsy (i Total). Severity scores within each category could be 0 (<5%; none or minimal), 1 (>5%—<25%; mild), 2 (>25%—<50%, moderate), or 3 (>50%, severe). The proportions of patients in each score category (0, 1, 2, and 3) were compared using Fisher’s exact test.

Fig 6. On-treatment patient and death-censored graft survival after CNI withdrawal.

P-values for the intent-to-treat analyses are also shown.

Fig 7. Rejection after CNI withdrawal.

On-treatment Kaplan-Meier analyses and log-rank tests (CNI minimized, n = 77; withdrawn, n = 64); intent-to-treat (ITT) p-values are included in the figures. (A) All biopsy findings of rejection ≥Grade 1A. The majority of rejection episodes after six months were low-grade Banff 1A: CNI minimized, 73% (4/7); CNI withdrawn, 70% (7/10). The number of higher-grade rejection episodes was similar between the two groups: CNI minimized, 27% (3-IB); CNI withdrawn, 30% (2-IB, 1-IIA). (B) Rejection ≥Grade 1A accompanied by clinically elevated serum creatinine (>30% above baseline). Only 18% of all rejection events in the CNI-minimized group were associated with an increase in serum creatinine. In contrast, 60% of rejection events in the CNI-withdrawn group associated with elevated serum creatinine (p = 0.10).

Fig 8. Combined impact of single-dose rATG induction with CNI withdrawal.

On-treatment comparison of best and worst treatment combinations (single-dose rATG with delayed CNI withdrawal vs. divided-dose rATG with delayed CNI minimization). (A) Renal function analyzed as in Fig 3. (B) Chronic Banff renal graft histopathology as in Fig 4.