Dynamic Behaviour of Donor Specific Antibodies in the Early Period Following HLA Incompatible Kidney Transplantation

Abstract

In HLA-incompatible kidney transplantation, monitoring donor-specific antibodies (DSA) plays a crucial role in providing appropriate treatment and increases kidney survival times. This work aimed to determine if early post-transplant DSA dynamics inform graft outcome over and above other predictive factors. Eighty-eight cases were classified by unsupervised machine learning into five distinct DSA response groups: no response, fast modulation, slow modulation, rise to sustained and sustained. Fast modulation dynamics gave an 80% rate for early acute rejection, whereas the sustained group was associated with the lowest rejection rates (19%). In complete contrast, the five-year graft failure was lowest in the modulation groups (4-7%) and highest in the sustained groups (25-31%). Multivariable analysis showed that a higher pre-treatment DSA level, male gender and absence of early acute rejection were strongly associated with a sustained DSA response. The modulation group had excellent five-year outcomes despite higher rates of early rejection episodes. This work further develops an understanding of post-transplant DSA dynamics and their influence on graft survival following HLA-incompatible kidney transplantation.

Keywords: 5 years graft failure; antibody dynamics; clustering; donor specific antibody; dynamic patterns; kidney transplantation.

FIGURE 1

Histograms of the observed number of data points per measurement period. Total period includes pre-transplant and post-transplant period. Trx, transplant.

FIGURE 2

Post-transplant DSA dynamics clustering methodology. The cohort is passed through the system and sorted into groups based on the similarity of post-transplant DSA dynamics. Stage 1 separates DSA into a pre-designated “no response” group if their maximum post-transplant tDSA titre level is less than 1500 MFI. Stage 2 scales the remaining DSA based on maximum post-transplant tDSA titre level before an additional filter is applied, separating the DSA based on time series length. All data which have 50 days are passed to Stage 3 and subsequently clustered using DTW distance measure under an agglomerative hierarchical structure. The optimal numbers of groups within the structure are identified using the gap statistic. Stage 4 classifies the remaining DSA, which have 20–50 days of data, into the groups identified in Stage 3.

FIGURE 3

Results of the gap analysis for DSA time series. Left: within-cluster dispersion, the standard deviation is indicated for reference data via the shaded region. Right: one-standard-error measurements. The optimal number of clusters is indicated by the lowest k on the left in combination with positive one-standard-error measurement on the right; in this case, k = 4.

FIGURE 4

The four groups identified via the gap statistic from DTW agglomerative hierarchical clustering on the DSA dataset. Cluster linkages, i.e., means of the clusters, are shown in dark grey lines. The shaded region displays the standard deviation for each cluster, and individual profiles are displayed in grey dotted lines.

FIGURE 5

Maximum tDSA level distributions for each group. Group 1 has the highest median value (16,263 MFI) and is compared to groups 2–4 for a significant difference. In each case, no significant differences are identified between groups highlighting how different dynamics occur across all observed DSA ranges.

FIGURE 6

Dynamic cluster patterns at DSA-HLA specific allele levels. Class 1 and DR specific DSA has predominantly modulating response compared to HLA DP; HLA DQ has mixed dynamics.

FIGURE 7

Kaplan-Meier analysis comparing the survival rates in modulation (groups 1 and 2) and sustained (groups 3 and 4) groups.