Prediction scores for risk of allograft loss in patients receiving kidney transplants: nil satis nisi optimum

Molecular Markers of Kidney Transplantation Outcome: Current Omics Tools and Future Developments

Purpose of review: The emerging field of molecular predictive medicine is aiming to change the traditional medical approach in renal transplantation. Many studies have explored potential biomarker molecules with predictive properties in renal transplantation, issued from omics research. Herein, we review the biomarker molecules of four technologies (i.e., Genomics, Transcriptomics, Proteomics, and Metabolomics) associated with favorable kidney transplant outcomes. Recent findings: Several panels of molecules have been associated with the outcome that the majority of markers are related to inflammation and immune response; although. other molecular ontologies are also represented, such as proteasome, growth, regeneration, and drug metabolism. Throughout this review, we highlight the lack of properly validated statistical demonstration. Indeed, the most preeminent molecular panels either remain at the limited size study stage or are not confirmed during large-scale studies. At the core of this problem, we identify the methodological shortcomings and propose a comprehensive workflow for discovery and validation of molecular biomarkers that aims to improve the relevance of these tools in the future. Summary: Overall, adopting a patient management through omics approach could bring remarkable improvement to transplantation success. An increased effort and investment between scientists, medical biologists, and clinicians seem to be the path toward a proper solution.

Deep Learning Algorithms for the Prediction of Posttransplant Renal Function in Deceased-Donor Kidney Recipients: A Preliminary Study Based on Pretransplant Biopsy

Background

Posttransplant renal function is critically important for kidney transplant recipients. Accurate prediction of graft function would greatly help in deciding acceptance or discard of allocated kidneys.

Methods

: Whole-slide images (WSIs) of H&E-stained donor kidney biopsies at × 200 magnification between January 2015 and December 2019 were collected. The clinical characteristics of each donor and corresponding recipient were retrieved. Graft function was indexed with a stable estimated glomerular filtration rate (eGFR) and reduced graft function (RGF). We used convolutional neural network (CNN)-based models, such as EfficientNet-B5, Inception-V3, and VGG19 for the prediction of these two outcomes.

Results

In total, 219 recipients with H&E-stained slides of the donor kidneys were included for analysis [biopsies from standard criteria donor (SCD)/expanded criteria donor (ECD) was 191/28]. The results showed distinct improvements in the prediction performance of the deep learning algorithm plus the clinical characteristics model. The EfficientNet-B5 plus clinical data model showed the lowest mean absolute error (MAE) and root mean square error (RMSE). Compared with the clinical data model, the area under the receiver operating characteristic (ROC) curve (AUC) of the clinical data plus image model for eGFR classification increased from 0.69 to 0.83. In addition, the predictive performance for RGF increased from 0.66 to 0.80. Gradient-weighted class activation mappings (Grad-CAMs) showed that the models localized the areas of the tubules and interstitium near the glomeruli, which were discriminative features for RGF.

Conclusion

Our results preliminarily show that deep learning for formalin-fixed paraffin-embedded H&E-stained WSIs improves graft function prediction accuracy for deceased-donor kidney transplant recipients.