Renal outcomes of STOP-IgAN trial patients in relation to baseline histology (MEST-C scores)

Abstract

Background: The Oxford classification of IgA nephropathy (IgAN) defines histologic criteria (MEST-C) that provide prognostic information based on the kidney biopsy. There are few data on the predictive impact of this classification in randomized clinical trial settings.

Methods: We performed an exploratory analysis of MEST-C scores in 70 available renal biopsies from 162 randomized STOP-IgAN trial participants and correlated the results with clinical outcomes. Analyses were performed by researchers blinded to the clinical outcome of the patients. Biopsies had been obtained 6.5 to 95 (median 9.4) months prior to randomization.

Results: Mesangial hypercellularity (M1) associated with higher annual eGFR-loss during the 3-year trial (M1: - 5.06 ± 5.17 ml/min/1.73 m², M0: - 0.79 ± 4.50 ml/min/1.73 m², p = 0.002). An M0-score additionally showed a weak association with full clinical remission, whereas the percentage of patients losing ≥15 ml/min/1.73 m² over the 3-year trial phase was higher among those scored as M1. Among patients with additional immunosuppression, ESRD occurred more frequently in patients when tubulointerstitial fibrosis (T1/2) was present (T1/2 = 33%, T0 = 0%, p = 0.008). In patients receiving supportive care only, ESRD frequencies were similar (T1/2 = 18%, T0 = 7%, p = 0.603). At randomization, eGFR was significantly lower when tubulointerstitial fibrosis was present (T1/2: 45.2 ± 15.7 ml/min/1.73 m², T0: 74.6 ± 28.2 ml/min/1.73 m², p < 0.0001). Endocapillary hypercellularity (E), and glomerular segmental sclerosis (S) were not associated with any clinical outcome parameter. In the analyzed cohort, patients with glomerular crescents (C1/2 scores) in their biopsies were more likely to develop ESRD during the 3-year trial phase, but this trend was only significant in patients under supportive care.

Conclusions: This secondary analysis of STOP-IgAN biopsies indicates that M1, T1/2 and C1/2 scores associate with worse renal outcomes.

Keywords: IgA nephropathy; IgAN; MEST-C; Oxford classification; STOP-IgAN.

Fig. 1

Flowchart of analyzed patients. A total of 337 patients with biopsy-proven IgAN entered the run-in phase of the STOP-IgAN trial during which all patients received supportive care. After 6 months, 162 patients were randomized to either continue on supportive care (n = 80) or received additional immunosuppression (n = 82). Upon amendment of the initial trial protocol in 2009, we aimed to retrieve the original kidney biopsies from the randomized patients for the current secondary analysis. Eventually, 70 biopsies were collected and could be scored using the MEST-C criteria

Fig. 2

Quantitative morphometry of the T-score in kidney biopsies. In contrast to semiquantitative analyses of tubular atrophy and interstitial fibrosis (T-score) in previous validation studies of the Oxford MEST-C classification, we assessed the T-score of by quantitative morphometry of the tubulointerstitial area using a virtual microscope tool (MIRAX Viewer). The pathologic lesions in the cortical area were encircled and then put in relation to the entire cortical area

Fig. 3

Kaplan-Meier curves for the event “full clinical remission” based on the M-score (a), E-score (b), S- score(c), T-score (d) and C-score (e). Full clinical remission was defined as urinary protein-creatinine ratio < 0.2 g/g and an eGFR decrease of < 5 ml/min/1.73m². Univariate Cox regression yielded the following p-values: M-score: p = 0.41; E-score: p = 0.46; S-score: p = 0.38; T-score: p = 0.39. Multivariate Cox regression adjusting for GFR and proteinuria at baseline and the treatment arm yielded the following p-values (also given in the figure): M-score: p = 0.33; E-score: p = 0.71; S-score: p = 0.65; T-score: p = 0.39). For the C-score, the proportional hazard assumption was not met

Fig. 4

Kaplan-Meier curves for the event “eGFR-loss ≥15 ml/min/1.73 m²” based on the M-score (a), E-score (b), S-score (c), T-score (d) and C-score (e). Univariate Cox regression yielded the following p-values: M-score: p = 0.08; E-score: p = 0.41; S-score: p = 0.91; T-score: p = 0.15. Multivariate Cox regression adjusting for GFR and proteinuria at baseline and the treatment arm yielded the following p-values (also given in the figure): M-score: p = 0.07; E-score: p = 0.69; S-score: p = 0.54; T-score: p = 0.79). For the C-score, the proportional hazard assumption was not met

Fig. 5

Kaplan-Meier curves for the event “ESRD development” based on the M-score (a), E-score (b), S-Sscore (c), T-score (d) and C-score (e). Univariate Cox regression yielded the following p-values: M-score: p = 0.32; E-score: p = 0.96; S-score: p = 0.90; T-score: p = 0.02. Multivariate Cox regression adjusting for GFR and proteinuria at baseline and the treatment arm yielded the following p-values (also given in the figure): M-score: p = 0.15; E-score: p = 0.27; S-score: p = 0.49; T-score: p = 0.01). For the C-score, the proportional hazard assumption was not met