Joint models quantify associations between immune cell kinetics and allo-immunological events after allogeneic stem cell transplantation and subsequent donor lymphocyte infusion

Abstract

Alloreactive donor-derived T-cells play a pivotal role in alloimmune responses after allogeneic hematopoietic stem cell transplantation (alloSCT); both in the relapse-preventing Graft-versus-Leukemia (GvL) effect and the potentially lethal complication Graft-versus-Host-Disease (GvHD). The balance between GvL and GvHD can be shifted by removing T-cells via T-cell depletion (TCD) to reduce the risk of GvHD, and by introducing additional donor T-cells (donor lymphocyte infusions [DLI]) to boost the GvL effect. However, the association between T-cell kinetics and the occurrence of allo-immunological events has not been clearly demonstrated yet. Therefore, we investigated the complex associations between the T-cell kinetics and alloimmune responses in a cohort of 166 acute leukemia patients receiving alemtuzumab-based TCD alloSCT. Of these patients, 62 with an anticipated high risk of relapse were scheduled to receive a prophylactic DLI at 3 months after transplant. In this setting, we applied joint modelling which allowed us to better capture the complex interplay between DLI, T-cell kinetics, GvHD and relapse than traditional statistical methods. We demonstrate that DLI can induce detectable T-cell expansion, leading to an increase in total, CD4+ and CD8+ T-cell counts starting at 3 months after alloSCT. CD4+ T-cells showed the strongest association with the development of alloimmune responses: higher CD4 counts increased the risk of GvHD (hazard ratio 2.44, 95% confidence interval 1.45-4.12) and decreased the risk of relapse (hazard ratio 0.65, 95% confidence interval 0.45-0.92). Similar models showed that natural killer cells recovered rapidly after alloSCT and were associated with a lower risk of relapse (HR 0.62, 95%-CI 0.41-0.93). The results of this study advocate the use of joint models to further study immune cell kinetics in different settings.

Keywords: T-cell depletion; T-cell kinetics; acute lymphoblastic leukemia; acute myeloid leukemia; allogeneic stem cell transplantation; donor lymphocyte infusion; graft-versus-host-disease; joint modelling.

Figure 1

Structure of the joint models. Graphical description of the two joint models. Joint model I (A) starts at time of alloSCT, joint model II (B) at time of the early low-dose DLI. Each model consists of a longitudinal and a time-to-event submodel and was run in turn for each T-cell subset, considering either the CD3+, CD4+ or CD8+ T-cell counts, and the NK cell counts. These are the outcome of the longitudinal submodel and a time-dependent covariate in the time-to-event submodel. All other variables in each submodel are baseline covariates. Per endpoint of the time-to-event submodels, the clinical events that occurred during the relevant time period (first 6 months after alloSCT or first 3 months after the early low-dose DLI) are described. The NK cells were only analyzed in model I. See the Statistical Supplement for a detailed description of the model structures.

Figure 2

Observed versus estimated CD3 counts from alloSCT. Observed (dots) and estimated subject-specific trajectories (solid line) of a random subset of 16 patients in the dataset. The estimated trajectories are based on the longitudinal submodel of model I. Dotted lines show the time of terminating event or administrative censoring because of administration of a modified T-cell product or standard DLI. The secondary axis shows the cell counts on the log scale, which is the scale used for modelling. For example, a cell count of 1 on the primary axis corresponds to log(1) = 0 on the secondary axis.

Figure 3

Model-based T-cell count trajectories after alloSCT. Predicted average trajectories of the total, CD4+ and CD8+ T-cell counts during the first 6 months after alloSCT, based on the longitudinal submodel of model I. For all predicted trajectories, the patient/donor CMV status was set to -/-. 95% confidence intervals are shown in grey. The right column zooms in on a specific part of the total trajectory.

Figure 4

Model-based T-cell count trajectories after early low-dose DLI. Predicted average trajectories of the total, CD4+ and CD8+ T-cell counts during the first 3 months after early low-dose DLI. These are based on the longitudinal submodel of model II. 95% confidence intervals are shown in grey. The distance between the two lines in each panel (and further visualized by the adjacent arrows) corresponds to the CMV patient/donor effect on the trajectories. Namely, higher cell counts are predicted for patient/donor pairs where at least one is CMV seropositive, relative to a pair where both are CMV seronegative.

Figure 5

Forest plot for ITT analysis. Hazard ratios with associated 95% confidence intervals for donor type, disease risk and current value of the log of total, CD4+ or CD8+ T-cell counts on the events of interest. These are based on the time-to-event submodel of model I (see Figure 1A ).

Figure 6

Forest plot for postDLI models. Hazard ratios with associated 95% confidence intervals for donor type and current value of the log of total, CD4+ or CD8+ T-cell counts on the events of interest. These are based on the time-to-event submodel of model II (see Figure 1B ).

Figure 7

Model-based NK cell count trajectories after alloSCT. Predicted average trajectories of the NK cell counts during the first 6 months after alloSCT, based on the longitudinal submodel of model I. The left panel shows the predicted trajectories for CMV seronegative patients with a CMV seronegative donor, the right panel the predicted trajectories for patients with any other patient/donor CMV serostatus combination. 95% confidence intervals are shown in grey.