Early prediction of renal graft function: Analysis of a multi-center, multi-level data set

Purpose of the study: Long-term graft survival rates after renal transplantation are still poor. We aimed to build an early predictor of an established long-term outcomes marker, the estimated glomerular filtration rate (eGFR) one year post-transplant (eGFR-1y). Materials and Methods: A large cohort of 376 patients was characterized for a multi-level bio-marker panel including gene expression, cytokines, metabolomics and antibody reactivity profiles. Almost one thousand samples from the pre-transplant and early post-transplant period were analysed and employed for machine learning-assisted prediction. Results: Pre-transplant data led to a prediction achieving a Pearson's correlation coefficient of r=0.38 between measured and predicted eGFR-1y. Two weeks post-transplant, the correlation was improved to r=0.63, and at the third month, to r=0.76. eGFR values were stable throughout the first post-transplant year. Several characteristics were predictive for eGFR, including age of donor and recipient, body mass index, HLA mismatch, cytomegalovirus mismatch and valganciclovir prophylaxis. Additionally, a subset of 19 nuclear magnetic resonance bins of the urine metabolome data was shown to have potential applications in non-invasive eGFR monitoring. Importantly, we identified the expression of the genes TMEM176B and HMMR as potential prognostic markers for changes in the eGFR after the second post-transplantation week. Conclusions: Our multi-center, multi-level data set represents a milestone in the efforts to predict transplant outcome. While an acceptable predictive capacity was achieved, we are still far from predicting changes in the eGFR precisely. Additional studies employing further marker panels are needed to establish predictors of eGFR-1y for clinical application; herein, gene expression markers seem to hold the most promise. (c) 2022 Elsevier Masson SAS. All rights reserved.

Automated summary

The purpose of this study was to establish an early predictor for long-term outcomes after renal transplantation. By analyzing a large cohort with multi-level bio-marker panels, machine learning-assisted prediction achieved significant correlation coefficients with measured eGFR-1y. These findings contribute to the prediction of transplant outcomes and improvement of post-transplant renal function.