Short- and long-term effects of anti-CD20 treatment on B cell ontogeny in bone marrow of patients with rheumatoid arthritis

Abstract

Introduction: In the present study we evaluated changes in the B cell phenotype in peripheral blood and bone marrow (BM) of patients with rheumatoid arthritis (RA) following anti-CD20 treatment using rituximab.

Methods: Blood and BM samples were obtained from 37 patients with RA prior to rituximab treatment. Ten of these patients were resampled 1 month following rituximab, 14 patients after 3 months and the remaining 13 patients were included in the long-term follow up. B cell populations were characterized by CD27/IgD/CD38/CD24 expression.

Results: One and three months following rituximab BM retained up to 30% of B cells while circulation was totally depleted of B cells. Analysis of the remaining BM B cells showed prevalence of immature and/or transitional B cells (CD38++CD24++) and CD27+IgD- memory cells, while IgD+ cells were completely depleted. A significant reduction of CD27+ cells in BM and in circulation was observed long after rituximab treatment (mean 22 months), while levels of naive B cells in BM and in circulation were increased. The levels of rheumatoid factor decline after rituximab treatment but returned to baseline levels at the time of retreatment.

Conclusions: Anti-CD20 treatment achieves a depletion of IgD+ B cells shortly after the treatment. At the long term follow up, a reduction of CD27+ B cells was observed in blood and BM. The prolonged inability to up-regulate CD27 may inhibit the renewal of memory B cells. This reduction of CD27+ B cells does not prevent autoantibody production suggesting that mechanisms regulating the formation of auto reactive clones are not disrupted by rituximab.

Figure 1

Short-term changes of the Ig-secreting cells in BM and PB after rituximab treatment. (a) Number of immunoglobulin (Ig)-secreting cells in bone marrow (BM) isolated from patients with rheumatoid arthritis at day 0, 1 and 3 months after rituximab treatment. Paired with respect to the sampling occasion. Error bars respresenting mean ± standard error of the mean. (b) Ig-secreting cells in peripheral blood (PB) at day 0, 3 and 6 months after rituximab treatment. Box represents 25^th to 75^th percentile, line indicates median, whereas error bars represent range. Statistical evaluation was performed using paired t-test.

Figure 2

Short- and long-term changes of RF levels in PB after rituximab treatment. (a) Rheumatoid factor (RF)-levels in peripheral blood (PB) at day 0, 3 and 6 months after rituximab treatment. (b) RF-levels in PB comparing rituximab-naïve and treated patients. Box represents 25^th to 75^th percentile, line indicates median, whereas error bars represent range. Statistical evaluation was performed using paired t-test (short-term changes) and Mann-Whitney t-test (long-term changes).

Figure 3

Short-term changes in the immunoglobulin expression of B cells following rituximab treatment. Isolated bone marrow mononuclear cells were stained for immunoglobulin (Ig) expression at day 0, 1 and 3 months after rituximab treatment. In (a) CD19⁺IgD⁺, (b) CD19⁺IgM⁺, (c) CD19⁺IgG⁺ and (d) CD19⁺IgA⁺ is shown. Box represents 25^th to 75^th percentile, line indicates median, whereas error bars represent range. Statistical evaluation was performed using paired t-test.

Figure 4

A representative plot of short-term and long-term changes of the B cell expression of CD27 and IgD on B cells in bone marrow from patients with rheumatoid arthritis receiving rituximab treatment. Lower left quadrant = immature B cells (IgD^-CD27^-); lower right quadrant = naïve B cells (IgD⁺CD27^-); upper right quadrant = unswitched memory B cells (IgD⁺CD27⁺); and upper left quadrant = switched memory B cells (IgD^-CD27⁺). (a) Rituximab-naïve patient is shown at day 0, 1 month and 3 months following treatment. (b) Rituximab-treated patient is shown at day 0, 1 month and 3 months following treatment. Arrow indicates depleted populations.

Figure 5

A representative plot of short-term and long-term changes of the B cell expression of CD38 in combination with CD10/CD24/IgD or CD27 in BM from RA patients receiving rituximab treatment. B cells expressing CD38 were analysed with respect to CD10/CD24, IgD or CD27 expression. Using CD38/IgD, plasmablast (CD38⁺⁺⁺IgD^-), immature and transitional B cells (CD38⁺⁺IgD^+/-), Bm5 (CD38⁺IgD^-), Bm2 (CD38⁺IgD⁺) populations were defined. B cells from a rituximab-naïve patient at (a) day 0, (b) after 3 months, and (c) in a rituximab-treated patient at day 0, is shown for the combination of CD38/CD10/CD24/IgD/CD27.

Figure 6

Long-term changes in the immunoglobulin expression of B cells following rituximab treatment. Isolated bone marrow mononuclear cells were stained for immunoglobulin (Ig) expression comparing rituximab-naïve and treated patients. In (a) CD19⁺IgD⁺, (b) CD19⁺IgM⁺, (c) CD19⁺IgG⁺ and (d) CD19⁺IgA⁺ is shown. Box represents 25^th to 75^th percentile, line indicates median, whereas error bars represent range. Statistical evaluation was performed using the Mann-Whitney t-test.