Recognition of intraglomerular histological features with deep learning in protocol transplant biopsies and their association with kidney function and prognosis.

Background: The Banff Classification may not adequately address protocol transplant biopsies categorized as normal in patients experiencing unexplained graft function deterioration. This study seeks to employ convolutional neural networks to automate the segmentation of glomerular cells and capillaries and assess their correlation with transplant function. Methods: A total of 215 patients were categorized into three groups. In the Training cohort, glomerular cells and capillaries from 37 patients were manually annotated to train the networks. The Test cohort (24 patients) compared manual annotations vs automated predictions, while the Application cohort (154 protocol transplant biopsies) examined predicted factors in relation to kidney function and prognosis. Results: In the Test cohort, the networks recognized histological structures with Precision, Recall, F-score and Intersection Over Union exceeding 0.92, 0.85, 0.89 and 0.74, respectively. Univariate analysis revealed associations between the estimated glomerular filtration rate (eGFR) at biopsy and relative endothelial area (r = 0.19, P = .027), endothelial cell density (r = 0.20, P = .017), mean parietal epithelial cell area (r = -0.38, P < .001), parietal epithelial cell density (r = 0.29, P < .001) and mesangial cell density (r = 0.22, P = .010). Multivariate analysis retained only endothelial cell density as associated with eGFR (Beta = 0.13, P = .040). Endothelial cell density (r = -0.22, P = .010) and mean podocyte area (r = 0.21, P = .016) were linked to proteinuria at biopsy. Over 44 ± 29 months, 25 patients (16%) reached the primary composite endpoint (dialysis initiation, or 30% eGFR sustained decline), with relative endothelial area, mean endothelial cell area and parietal epithelial cell density below medians linked to this endpoint [hazard ratios, respectively, of 2.63 (P = .048), 2.60 (P = .039) and 3.23 (P = .019)]. Conclusion: This study automated the measurement of intraglomerular cells and capillaries. Our results suggest that the precise segmentation of endothelial and epithelial cells may serve as a potential future marker for the risk of graft loss.

CMV Infection and Lymphopenia: Warning Markers of Pneumocystis Pneumonia in Kidney Transplant Recipients.

Pneumocystis pneumonia (PcP) remains life-threatening in kidney transplant recipients (KTR). Our study investigated risk factors one-year before PcP. We conducted a monocentric, case-control study including all KTR at the Dijon University Hospital (France) with a diagnosis of PcP between 2005 and 2022 (cases), and matched control KTR with no history of PcP (3 controls/case). Among all 1,135 KTR, 57 cases (5%) and 169 matched-controls were included. PcP was associated with 18% mortality. Compared to controls, cases were older, with a higher immunological risk, and CMV infection was more frequent in the year preceding the occurrence of PcP (23% vs. 4%; p < 0.001). As early as 1 year before PcP, lymphocyte counts were lower and serum creatinine levels were higher in cases, but immunosuppressive regimens were not significantly different. Multivariable analysis identified lymphocyte count, serum creatinine level, being treated by immunosuppressive therapy other than anti-rejection drugs, and CMV infection in the year preceding the time PcP as independently associated with the occurrence of PcP. PcP was associated with an increased risk of subsequent chronic rejection (27% vs. 3%; p = 0.001) and return to dialysis (20% vs. 3%; p = 0.002). The occurrence of CMV infection and a low lymphocyte count could redefine the indications for continuation or reinitiation of anti-Pneumocystis prophylaxis.

Automated Urinary Chemokine Assays for Noninvasive Detection of Kidney Transplant Rejection: A Prospective Cohort Study.

RATIONALE & OBJECTIVE: Prior studies have demonstrated the diagnostic potential of urinary chemokines C-X-C motif ligand 9 (CXCL9) and CXCL10 for kidney transplant rejection. However, their benefit in addition to clinical information has not been demonstrated. We evaluated the diagnostic performance for detecting acute rejection of urinary CXCL9 and CXCL10 when integrated with clinical information. STUDY DESIGN: Single-center prospective cohort study. SETTING & PARTICIPANTS: We analyzed 1,559 biopsy-paired urinary samples from 622 kidney transplants performed between April 2013 and July 2019 at a single transplant center in Belgium. External validation was performed in 986 biopsy-paired urinary samples. TESTS COMPARED: We quantified urinary CXCL9 (uCXCL9) and CXCL10 (uCXCL10) using an automated immunoassay platform and normalized the values to urinary creatinine. Urinary chemokines were incorporated into a multivariable model with routine clinical markers (estimated glomerular filtration rate, donor-specific antibodies, and polyoma viremia) (integrated model). This model was then compared with the tissue diagnosis according to the Banff classification for acute rejection. OUTCOME: Acute rejection detected on kidney biopsy using the Banff classification. RESULTS: Chemokines integrated with routine clinical markers had high diagnostic value for detection of acute rejection (n=150) (receiver operating characteristic area under the curve 81.3% [95% CI, 77.6-85.0]). The integrated model would help avoid 59 protocol biopsies per 100 patients when the risk for rejection is predicted to be below 10%. The performance of the integrated model was similar in the external validation cohort. LIMITATIONS: The cross-sectional nature obviates investigating the evolution over time and prediction of future rejection. CONCLUSIONS: The use of an integrated model of urinary chemokines and clinical markers for noninvasive monitoring of rejection could enable a reduction in the number of biopsies. Urinary chemokines may be useful noninvasive biomarkers whose use should be further studied in prospective randomized trials to clarify their role in guiding clinical care and the use of biopsies to detect rejection after kidney transplantation. PLAIN-LANGUAGE SUMMARY: Urinary chemokines CXCL9 and CXCL10 have been suggested to be good noninvasive biomarkers of kidney transplant rejection. However, defining a context of use and integration with clinical information is necessary before clinical implementation can begin. In this study, we demonstrated that urinary chemokines CXCL9 and CXCL10, together with clinical information, have substantial diagnostic accuracy for the detection of acute kidney transplant rejection. Application of urinary chemokines together with clinical information may guide biopsy practices following kidney transplantation and potentially reduce the need for kidney transplant biopsies.

An observational cohort study of histological screening for BK polyomavirus nephropathy following viral replication in plasma.

Systematic screening for BKPyV-DNAemia has been advocated to aid prevention and treatment of polyomavirus associated nephropathy (PyVAN), an important cause of kidney graft failure. The added value of performing a biopsy at time of BKPyV-DNAemia, to distinguish presumptive PyVAN (negative SV40 immunohistochemistry) and proven PyVAN (positive SV40) has not been established. Therefore, we studied an unselected cohort of 950 transplantations, performed between 2008-2017. BKPyV-DNAemia was detected in 250 (26.3%) transplant recipients, and positive SV40 in 91 cases (9.6%). Among 209 patients with a concurrent biopsy at time of first BKPyV-DNAemia, 60 (28.7%) biopsies were SV40 positive. Plasma viral load showed high diagnostic value for concurrent SV40 positivity (ROC-AUC 0.950, 95% confidence interval 0.916-0.978) and the semiquantitatively scored percentage of tubules with evidence of polyomavirus replication (pvl score) (0.979, 0.968-0.988). SV40 positivity was highly unlikely when plasma viral load is below 4 log10 copies/ml (negative predictive value 0.989, 0.979-0.994). In SV40 positive patients, higher plasma BKPyV-DNA load and higher pvl scores were associated with slower viral clearance from the blood (hazard ratio 0.712, 95% confidence interval 0.604-0.839, and 0.327, 0.161-0.668, respectively), whereas the dichotomy positivity/negativity of SV40 immunohistochemistry did not predict viral clearance. Although the pvl score offers some prognostic value for viral clearance on top of plasma viral load, the latter provided good guidance for when a biopsy was unnecessary to exclude PyVAN. Thus, the distinction between presumptive and proven PyVAN, based on SV40 immunohistochemistry, has limited clinical value. Hence, management of BKPyV-DNAemia and immunosuppression reduction should be weighed against the risk of occurrence of rejection, or exacerbation of rejection observed concomitantly.

Transcriptional and spatial profiling of the kidney allograft unravels a central role for FcyRIII+ innate immune cells in rejection.

Rejection remains the main cause of premature graft loss after kidney transplantation, despite the use of potent immunosuppression. This highlights the need to better understand the composition and the cell-to-cell interactions of the alloreactive inflammatory infiltrate. Here, we performed droplet-based single-cell RNA sequencing of 35,152 transcriptomes from 16 kidney transplant biopsies with varying phenotypes and severities of rejection and without rejection, and identified cell-type specific gene expression signatures for deconvolution of bulk tissue. A specific association was identified between recipient-derived FCGR3A+ monocytes, FCGR3A+ NK cells and the severity of intragraft inflammation. Activated FCGR3A+ monocytes overexpressed CD47 and LILR genes and increased paracrine signaling pathways promoting T cell infiltration. FCGR3A+ NK cells overexpressed FCRL3, suggesting that antibody-dependent cytotoxicity is a central mechanism of NK-cell mediated graft injury. Multiplexed immunofluorescence using 38 markers on 18 independent biopsy slides confirmed this role of FcγRIII+ NK and FcγRIII+ nonclassical monocytes in antibody-mediated rejection, with specificity to the glomerular area. These results highlight the central involvement of innate immune cells in the pathogenesis of allograft rejection and identify several potential therapeutic targets that might improve allograft longevity.

Selective Arterial Embolization of Pseudoaneurysms and Arteriovenous Fistulas after Partial Nephrectomy: Safety, Efficacy, and Mid-Term Outcomes.

The primary objective was to evaluate the clinical success rate after endovascular embolization of iatrogenic vascular lesions caused during partial nephrectomy. The secondary objective was to evaluate the technical success and to assess potential effects on renal function. We retrospectively included consecutive patients from our center who underwent selective embolization to treat iatrogenic renal arterial lesions induced during partial nephrectomy between June 2010 and June 2020. The technical and clinical success rates and renal outcomes were collected. We identified 25 patients with 47 pseudoaneurysms and nine arteriovenous fistulas. Among them, eight were treated by coils only, eight by liquid embolization agents only, and nine by both. The technical success rate was 96% after the first attempt and 100% after the second attempt. The median follow-up was 27.1 ± 24.3 months. Clinical success, defined as no need for further hemostatic surgery during follow-up, was also obtained in 96% and 100% of patients with one and two attempts, respectively. Renal function estimated by the modification of diet in renal disease equation did not change significantly despite a mean 13.8% ± 15.1% decrease in kidney functional volume estimated by angiography. No complications were attributable to the endovascular treatment. No significant difference was found across embolization agents; however, the subgroup sizes were small. Endovascular embolization is safe and effective for treating iatrogenic arterial lesions after partial nephrectomy: success rates are high, complications are infrequent, and renal function is maintained. Recommendations by interventional radiology societies are needed to standardize this treatment.

Automated evaluation with deep learning of total interstitial inflammation and peritubular capillaritis on kidney biopsies.

BACKGROUND: Interstitial inflammation and peritubular capillaritis are observed in many diseases on native and transplant kidney biopsies. A precise and automated evaluation of these histological criteria could help stratify patients' kidney prognoses and facilitate therapeutic management. METHODS: We used a convolutional neural network to evaluate those criteria on kidney biopsies. A total of 423 kidney samples from various diseases were included; 83 kidney samples were used for the neural network training, 106 for comparing manual annotations on limited areas to automated predictions, and 234 to compare automated and visual gradings. RESULTS: The precision, recall and F-score for leukocyte detection were, respectively, 81%, 71% and 76%. Regarding peritubular capillaries detection the precision, recall and F-score were, respectively, 82%, 83% and 82%. There was a strong correlation between the predicted and observed grading of total inflammation, as for the grading of capillaritis (r = 0.89 and r = 0.82, respectively, all P < .0001). The areas under the receiver operating characteristics curves for the prediction of pathologists' Banff total inflammation (ti) and peritubular capillaritis (ptc) scores were respectively all above 0.94 and 0.86. The kappa coefficients between the visual and the neural networks' scores were respectively 0.74, 0.78 and 0.68 for ti ≥1, ti ≥2 and ti ≥3, and 0.62, 0.64 and 0.79 for ptc ≥1, ptc ≥2 and ptc ≥3. In a subgroup of patients with immunoglobulin A nephropathy, the inflammation severity was highly correlated to kidney function at biopsy on univariate and multivariate analyses. CONCLUSION: We developed a tool using deep learning that scores the total inflammation and capillaritis, demonstrating the potential of artificial intelligence in kidney pathology.

Deep learning automation of MEST-C classification in IgA nephropathy.

BACKGROUND: Although the MEST-C classification is among the best prognostic tools in immunoglobulin A nephropathy (IgAN), it has a wide interobserver variability between specialized pathologists and others. Therefore we trained and evaluated a tool using a neural network to automate the MEST-C grading. METHODS: Biopsies of patients with IgAN were divided into three independent groups: the Training cohort (n = 42) to train the network, the Test cohort (n = 66) to compare its pixel segmentation to that made by pathologists and the Application cohort (n = 88) to compare the MEST-C scores computed by the network or by pathologists. RESULTS: In the Test cohort, >73% of pixels were correctly identified by the network as M, E, S or C. In the Application cohort, the neural network area under the receiver operating characteristics curves were 0.88, 0.91, 0.88, 0.94, 0.96, 0.96 and 0.92 to predict M1, E1, S1, T1, T2, C1 and C2, respectively. The kappa coefficients between pathologists and the network assessments were substantial for E, S, T and C scores (kappa scores of 0.68, 0.79, 0.73 and 0.70, respectively) and moderate for M score (kappa score of 0.52). Network S and T scores were associated with the occurrence of the composite survival endpoint (death, dialysis, transplantation or doubling of serum creatinine) [hazard ratios 9.67 (P = .006) and 7.67 (P < .001), respectively]. CONCLUSIONS: This work highlights the possibility of automated recognition and quantification of each element of the MEST-C classification using deep learning methods.

Modulation of Monocyte Response by MicroRNA-15b/106a/374a During Antibody-mediated Rejection in Kidney Transplantation.

BACKGROUND: Increasing evidence suggest that microRNAs are involved in the physiopathology of acute or chronic renal disease. In kidney transplantation, as key regulators of cellular homeostasis, microRNAs may be involved in the regulation of immune cell function and the allograft response. Here, we investigated the change in circulating microRNA expression profile and their involvement in the profound transcriptional changes associated with antibody-mediated rejection (AMR). METHODS: Blood samples were collected at the time of the 710 kidney allograft biopsies at 4 European transplant centers. Messenger RNA and microRNA profiling analyses were performed in a discovery-to-validation study within 3 independent cohorts encompassing N = 126, N = 135, and N = 416 patients, respectively. RESULTS: Compared with samples with no AMR, 14 microRNAs were significantly decreased in AMR samples. Among them, expression levels of microRNA-15b, microRNA-106a, and microRNA-374a gradually decreased with the severity of AMR lesions. From their in silico-predicted target genes, a high proportion proved to be significantly upregulated in the paired transcriptomic analysis. Gene ontology analyses of microRNA-15b/-106a/-374a suggested enrichment in myeloid-related pathways, which was further refined by in silico and ex vivo transcriptomic analyses, showing a specific origin from classical CD14 + monocytes. Finally, human CD14 + monocytes were subjected to transduction by antago-microRNAs to mimic AMR pathology. MicroRNA-15b/-106a/-374a impairment resulted in cellular activation with an increased expression of CD69, CRIM1, IPO7, and CAAP1, direct and common targets of the 3 microRNAs. CONCLUSIONS: Together, our data provide new insights into circulating microRNAs as markers and key players in AMR, and they suggest monocyte involvement in this process.

European Society of Organ Transplantation Consensus Statement on Testing for Non-Invasive Diagnosis of Kidney Allograft Rejection.

To address the need for improved biomarkers for kidney transplant rejection, European Society of Organ Transplantation (ESOT) convened a dedicated working group comprised of experts in kidney transplant biomarkers to review literature pertaining to clinical and subclinical acute rejection to develop guidelines in the screening and diagnosis of acute rejection that were subsequently discussed and voted on during the Consensus Conference that took place in person in Prague. The findings and recommendations of the Working Group on Molecular Biomarkers of Kidney Transplant Rejection are presented in this article.

MicroRNAs in kidney injury and disease.

MicroRNAs (miRNAs) are small non-coding RNAs that regulate gene expression by degrading or repressing the translation of their target messenger RNAs. As miRNAs are critical regulators of cellular homeostasis, their dysregulation is a crucial component of cell and organ injury. A substantial body of evidence indicates that miRNAs are involved in the pathophysiology of acute kidney injury (AKI), chronic kidney disease and allograft damage. Different subsets of miRNAs are dysregulated during AKI, chronic kidney disease and allograft rejection, which could reflect differences in the physiopathology of these conditions. miRNAs that have been investigated in AKI include miR-21, which has an anti-apoptotic role, and miR-214 and miR-668, which regulate mitochondrial dynamics. Various miRNAs are downregulated in diabetic kidney disease, including the miR-30 family and miR-146a, which protect against inflammation and fibrosis. Other miRNAs such as miR-193 and miR-92a induce podocyte dedifferentiation in glomerulonephritis. In transplantation, miRNAs have been implicated in allograft rejection and injury. Further work is needed to identify and validate miRNAs as biomarkers of graft function and of kidney disease development and progression. Use of combinations of miRNAs together with other molecular markers could potentially improve diagnostic or predictive power and facilitate clinical translation. In addition, targeting specific miRNAs at different stages of disease could be a promising therapeutic strategy.

Association of Predicted HLA T-Cell Epitope Targets and T-Cell-Mediated Rejection After Kidney Transplantation.

RATIONALE & OBJECTIVE: The relationship between human leukocyte antigen (HLA) molecular mismatches and T-cell-mediated rejection (TCMR) is unknown. We investigated the associations between the different donor HLA-derived T-cell targets and the occurrence of TCMR and borderline histologic changes suggestive of TCMR after kidney transplantation. STUDY DESIGN: Retrospective cohort study. SETTING & PARTICIPANTS: All kidney transplant recipients at a single center between 2004 and 2013 with available biopsy data and a DNA sample for high-resolution HLA donor/recipient typing (N = 893). EXPOSURE: Scores calculated by the HLA matching algorithm PIRCHE-II and HLA eplet mismatches. OUTCOME: TCMR, borderline changes suggestive of TCMR, and allograft failure. ANALYTICAL APPROACH: Multivariable cause-specific hazards models were fit to characterize the association between HLA epitopes targets and study outcomes. RESULTS: We found 277 patients developed TCMR, and 134 developed only borderline changes suggestive of TCMR on at least 1 biopsy. In multivariable analyses, only the PIRCHE-II scores for HLA-DRB1 and HLA-DQB1 were independently associated with the occurrence of TCMR and with allograft failure; this was not the case for HLA class I molecules. If restricted to rejection episodes within the first 3 months after transplantation, only the T-cell epitope targets originating from the donor's HLA-DRB1 and HLA-DQB1, but not class I molecules, were associated with the early acute TCMR. Also, the median PIRCHE-II score for HLA class II was statistically different between the patients with TCMR compared to the patients without TCMR (129 [IQR, 60-240] vs 201 [IQR, 96-298], respectively; P < 0.0001). These differences were not observed for class I PIRCHE-II scores. LIMITATIONS: Observational clinical data and residual confounding. CONCLUSIONS: In the absence of HLA-DSA, HLA class II but not class I mismatches are associated with early episodes of acute TCMR and allograft failure. This suggests that current immunosuppressive therapies are largely able to abort the most deleterious HLA class I-directed alloimmune processes; however, alloresponses against HLA-DRB1 and HLA-DQB1 molecular mismatches remain insufficiently suppressed. PLAIN-LANGUAGE SUMMARY: Genetic differences in the human leukocyte antigen (HLA) complex between kidney transplant donors and recipients play a central role in T-cell-mediated rejection (TCMR), which can lead to failure of the transplanted kidney. Evaluating this genetic disparity (mismatch) in the HLA complex at the molecular (epitope) level could contribute to better prediction of the immune response to the donor organ posttransplantation. We investigated the associations of the different donor HLA-derived T-cell epitope targets and scores obtained from virtual crossmatch algorithms with the occurrence of TCMR, borderline TCMR, and graft failure after kidney transplantation after taking into account the influence of donor-specific anti-HLA antibodies. This study illustrates the greater importance of the molecular mismatches in class II molecules compared to class I HLA molecules.

Biological pathways and comparison with biopsy signals and cellular origin of peripheral blood transcriptomic profiles during kidney allograft pathology.

Kidney transplant injury processes are associated with molecular changes in kidney tissue, primarily related to immune cell activation and infiltration. How these processes are reflected in the circulating immune cells, whose activation is targeted by strong immunosuppressants, is poorly understood. To study this, we analyzed the molecular alterations in 384 peripheral blood samples from four European transplant centers, taken at the time of a kidney allograft biopsy, selected for their phenotype, using RNA-sequencing. In peripheral blood, differentially expressed genes in 136 rejection and 248 no rejection samples demonstrated upregulation of glucocorticoid receptor and nucleotide oligomerization domain-like receptor signaling pathways. Pathways enriched in antibody-mediated rejection (ABMR) were strongly immune-specific, whereas pathways enriched in T cell-mediated rejection were less immune related. In polyomavirus infection, upregulation of mitochondrial dysfunction and interferon signaling pathways was seen. Next, we integrated the blood results with transcriptomics of 224 kidney allograft biopsies which showed consistently upregulated genes per phenotype in both blood and biopsy. In single-cell RNASeq (scRNASeq) analysis of seven kidney allograft biopsies, the consistently overexpressed genes in ABMR were mostly expressed by infiltrating leukocytes in the allograft. Similarly, in peripheral blood scRNASeq analysis, these genes were overexpressed in ABMR in immune cell subtypes. Furthermore, overexpression of these genes in ABMR was confirmed in independent cohorts in blood and biopsy. Thus, our results highlight the immune activation pathways in peripheral blood leukocytes at the time of kidney allograft pathology, despite the use of current strong immunosuppressants, and provide a framework for future therapeutic interventions.

Circulating Donor-Specific Anti-HLA Antibodies Associate With Immune Activation Independent of Kidney Transplant Histopathological Findings.

Despite the critical role of cytokines in allograft rejection, the relation of peripheral blood cytokine profiles to clinical kidney transplant rejection has not been fully elucidated. We assessed 28 cytokines through multiplex assay in 293 blood samples from kidney transplant recipients at time of graft dysfunction. Unsupervised hierarchical clustering identified a subset of patients with increased pro-inflammatory cytokine levels. This patient subset was hallmarked by a high prevalence (75%) of donor-specific anti-human leukocyte antigen antibodies (HLA-DSA) and histological rejection (70%) and had worse graft survival compared to the group with low cytokine levels (HLA-DSA in 1.7% and rejection in 33.7%). Thirty percent of patients with high pro-inflammatory cytokine levels and HLA-DSA did not have histological rejection. Exploring the cellular origin of these cytokines, we found a corresponding expression in endothelial cells, monocytes, and natural killer cells in single-cell RNASeq data from kidney transplant biopsies. Finally, we confirmed secretion of these cytokines in HLA-DSA-mediated cross talk between endothelial cells, NK cells, and monocytes. In conclusion, blood pro-inflammatory cytokines are increased in kidney transplant patients with HLA-DSA, even in the absence of histology of rejection. These observations challenge the concept that histology is the gold standard for identification of ongoing allo-immune activation after transplantation.

Human Monocyte-Derived Suppressor Cell Supernatant Induces Immunoregulatory Effects and Mitigates xenoGvHD.

Recently developed cell-based therapies have shown potential for graft-versus-host disease (GvHD) mitigation. Our team previously developed a protocol to generate human monocyte-derived suppressor Cells (HuMoSC), a subpopulation of CD33+ suppressor cells of monocytic origin. CD33+HuMoSC successfully reduced xenoGvHD severity in NOD/SCID/IL-2Rγc-/- (NSG) mice. While CD33+ HuMoSC culture supernatant inhibits T cell activation and proliferation, the recovery of CD33+ HuMoSC immunosuppressive cells and the subsequent production of their supernatant is limited. An attractive solution would be to use both the CD33+ and the large number of CD14+ cells derived from our protocol. Here, we assessed the immunoregulatory properties of the CD14+HuMoSC supernatant and demonstrated that it inhibited both CD4 and CD8 T cell proliferation and decreased CD8 cytotoxicity. In vivo, injection of CD14+HuMoSC supernatant reduced xenoGvHD in NSG mice. Furthermore, CD14+HuMoSC supernatant maintained its immunoregulatory properties in an inflammatory environment. Proteomic and multiplex analyses revealed the presence of immunosuppressive proteins such as GPNMB, galectin-3 and IL-1R(A) Finally, CD14+HuMoSC supernatant can be produced using good manufacturing practices and be used as complement to current immunosuppressive drugs. CD14+HuMoSC supernatant is thus a promising therapy for preventing GvHD. .

Forecasting of Patient-Specific Kidney Transplant Function With a Sequence-to-Sequence Deep Learning Model.

Importance: Like other clinical biomarkers, trajectories of estimated glomerular filtration rate (eGFR) after kidney transplant are characterized by intra-individual variability. These fluctuations hamper the distinction between alarming graft functional deterioration or harmless fluctuation within the patient-specific expected reference range of eGFR. Objective: To determine whether a deep learning model could accurately predict the patient-specific expected reference range of eGFR after kidney transplant. Design, Setting, and Participants: A multicenter diagnostic study consisted of a derivation cohort of 933 patients who received a kidney transplant between 2004 and 2013 with 100 867 eGFR measurements from University Hospitals Leuven, Belgium, and 2 independent test cohorts: with 39 999 eGFR measurements from 1 170 patients, 1 from University Hospitals Leuven, Belgium, receiving transplants between 2013 and 2018 and 1 from Hannover Medical School, Germany, receiving transplants between 2003 and 2007. Patients receiving a single kidney transplant, with consecutive eGFR measurements were included. Data were analyzed from February 2019 to April 2021. Exposures: In the derivation cohort 100 867 eGFR measurements were available for analysis and 39 999 eGFR measurements from the independent test cohorts. Main Outcomes and Measures: A sequence-to-sequence model was developed for prediction of a patient-specific expected range of eGFR, based on previous eGFR values. The primary outcome was the performance of the deep learning sequence-to-sequence model in the 2 independent cohorts. Results: In this diagnostic study, a total of 933 patients in the training sets (mean [SD] age, 53.5 [13.3] years; 570 male [61.1%]) and 1170 patients in the independent test sets (cohort 1 [n = 621]: mean [SD] age, 58.5 [12.1] years; 400 male [64.4%]; cohort 2 [n = 549]: mean [SD] age, 50.1 [13.0] years; 316 male [57.6%]) who received a single kidney transplant most frequently from deceased donors, the sequence-to-sequence models accurately predicted future patient-specific eGFR trajectories within the first 3 months after transplant, based on the previous graft eGFR values (root mean square error, 6.4-8.9 mL/min/1.73 m2). The sequence-to-sequence model predictions outperformed the more conventional autoregressive integrated moving average prediction model, at all input/output number of eGFR values. Conclusions and Relevance: In this diagnostic study, a sequence-to-sequence deep learning model was developed and validated for individual forecasting of kidney transplant function. The patient-specific sequence predictions could be used in clinical practice to guide physicians on deviations from the expected intra-individual variability, rather than relating the individual results to the reference range of the healthy population.

Selective Arterial Embolization with N-Butyl Cyanoacrylate Prior to CT-Guided Percutaneous Cryoablation of Kidney Malignancies: A Single-Center Experience.

The study's purpose was to assess the safety, feasibility and efficiency of selective arterial embolization (SAE) using N-butyl cyanoacrylate (NBCA) glue before percutaneous cryoablation (PCA) of renal malignancies in patients whose tumor characteristics and/or comorbidities resulted in an unacceptable risk of bleeding. In this single-center retrospective study of 19 consecutive high-risk patients (median age, 74 years) with renal malignancies managed in 2017-2020 by SAE with NBCA followed by PCA, data about patients, tumor and procedures characteristics, complications, renal function and hemoglobin concentration before and after treatment, as well as recurrence were collected. Charlson comorbidity index was ≥4 in 89.5% of patients. Ten patients were treated by antiplatelet and/or anticoagulant therapy. Median tumor largest diameter was 3.75 cm (range, 1-6.5 cm) and R.E.N.A.L. nephrometry score was ≥7 in 80%, indicating substantial tumor complexity. No major complications were recorded and minor complications occurred in 7 patients. No residual tumor was found at 6-week imaging follow-up in 18/19 patients. Tumor recurrence was visible in 1/16 patients at 6-month imaging follow-up. No significant difference was found for renal function after treatment (p = 0.07), whereas significant decrease in hemoglobin concentration was noted (p = 0.00004), although it was relevant for only one patient who required only blood transfusion and no further intervention. SAE prior to PCA is safe and effective for managing renal malignancies in high-risk patients.

Integrative Omics Analysis Unravels Microvascular Inflammation-Related Pathways in Kidney Allograft Biopsies.

In solid-organ transplantation, microRNAs (miRNAs) have emerged as key players in the regulation of allograft cells function in response to injury. To gain insight into the role of miRNAs in antibody-mediated rejection, a rejection phenotype histologically defined by microvascular inflammation, kidney allograft biopsies were subjected to miRNA but also messenger RNA (mRNA) profiling. Using a unique multistep selection process specific to the BIOMARGIN study (discovery cohort, N=86; selection cohort, N=99; validation cohort, N=298), six differentially expressed miRNAs were consistently identified: miR-139-5p (down) and miR-142-3p/150-5p/155-5p/222-3p/223-3p (up). Their expression level gradually correlated with microvascular inflammation intensity. The cell specificity of miRNAs target genes was investigated by integrating their in vivo mRNA targets with single-cell RNA sequencing from an independent allograft biopsy cohort. Endothelial-derived miR-139-5p expression correlated negatively with MHC-related genes expression. Conversely, epithelial-derived miR-222-3p overexpression was strongly associated with degraded renal electrolyte homeostasis and repressed immune-related pathways. In immune cells, miR-150-5p regulated NF-κB activation in T lymphocytes whereas miR-155-5p regulated mRNA splicing in antigen-presenting cells. Altogether, integrated omics enabled us to unravel new pathways involved in microvascular inflammation and suggests that metabolism modifications in tubular epithelial cells occur as a consequence of antibody-mediated rejection, beyond the nearby endothelial compartment.

A kidney discard decision strategy based on zero-time histology analysis could lead to an unjustified increase in the organ turndown rate among ECD.

The utility of zero-time kidney biopsies (KB) in deciding to accept expanded criteria donor (ECD) kidneys remains controversial. However, zero-time histology is one of the main causes for discarding kidneys in the United States. In a single-centre study, we examined the utility and impact on outcome of the use of frozen section zero-time KB among ECD. Ninety-two zero-time KB were analysed for accept/discard decision between 2005 and 2015 among ECD. 53% of kidneys were rejected after zero-time KB analysis; there was no difference in individual clinical and biological data between accepted/rejected groups. However, histology of rejected kidneys showed more sclerotic glomeruli (20% vs. 8%; P < 0.001), increased interstitial fibrosis (1.25 ± 0.12 vs. 0.47 ± 0.09; P < 0.0001), more arteriosclerosis (2.14 ± 0.17 vs. 1.71 ± 0.11; P = 0.0032) and arteriolar hyalinosis (2.15 ± 0.12 vs. 1.55 ± 0.11; P = 0.0006). Using propensity score matching, we generated a group of 42 kidney allograft recipients who received a transplant matched for donor zero-time histology and clinical characteristics with donors whose kidneys were rejected. Interestingly, their 1- and 5-year graft survival and function were similar to the global cohort of ECD recipients. In conclusion, when performed, zero-time KB was a decisive element for kidney discard decision. However, adverse zero-time histology was not associated with poorer graft survival and kidney function among ECD.