Performance of GPT-4 Vision on kidney pathology exam questions.

OBJECTIVES: ChatGPT (OpenAI, San Francisco, CA) has shown impressive results across various medical examinations, but its performance in kidney pathology is not yet established. This study evaluated proficiencies of GPT-4 Vision (GPT-4V), an updated version of the platform with the ability to analyze images, on kidney pathology questions and compared its responses with those of nephrology trainees. METHODS: Thirty-nine questions (19 text-based questions and 20 with various kidney biopsy images) designed specifically for the training of nephrology fellows were employed. RESULTS: GPT-4V displayed comparable accuracy rates in the first and second runs (67% and 72%, respectively, P = .50). The aggregated accuracy, however-particularly, the consistent accuracy-of GPT-4V was lower than that of trainees (72% and 67% vs 79%). Both GPT-4V and trainees displayed comparable accuracy in responding to image-based and text-only questions (55% vs 79% and 81% vs 78%, P = .11 and P = .67, respectively). The consistent accuracy in image-based, directly asked questions for GPT-4V was 29%, much lower than its 88% consistency on text-only, directly asked questions (P = .02). In contrast, trainees maintained similar accuracy in directly asked image-based and text-based questions (80% vs 77%, P = .65). Although the aggregated accuracy for correctly interpreting images was 69%, the consistent accuracy across both runs was only 39%. The accuracy of GPT-4V in answering questions with correct image interpretation was significantly higher than for questions with incorrect image interpretation (100% vs 0% and 100% vs 33% for the first and second runs, P = .001 and P = .02, respectively). CONCLUSIONS: The performance of GPT-4V in handling kidney pathology questions, especially those including images, is limited. There is a notable need for enhancement in GPT-4V proficiency in interpreting images.

IgG4-related kidney disease: Clinicopathologic features, differential diagnosis, and mimics.

IgG4-related kidney disease (IgG4-RKD) encompasses all forms of kidney disease that are part of IgG4-related disease (IgG4-RD). First recognized as IgG4-related tubulointerstitial nephritis (IgG4-TIN), and then IgG4-related membranous glomerulonephritis (IgG4-MGN), we now recognize additional patterns of interstitial nephritis, glomerular disease, and vascular disease that can be seen as part of IgG4-RKD. The clinical presentation is variable and can include acute or chronic kidney injury, proteinuria or nephrotic syndrome, mass lesion(s), and obstruction. While usually associated with other organ involvement by IgG4-RD, kidney-alone involvement is present in approximately 20 % of IgG4-RKD. Compared to IgG4-RD overall, patients with IgG4-RKD are more likely to show increased serum IgG4 or IgG, and more likely to have hypocomplementemia. In this review, we extensively cover other types of autoimmune and plasma cell-rich interstitial nephritis, mass forming inflammatory diseases of the kidney, and other mimics of IgG4-TIN, in particular ANCA-associated disease.

A Machine Learning-Driven Virtual Biopsy System For Kidney Transplant Patients.

In kidney transplantation, day-zero biopsies are used to assess organ quality and discriminate between donor-inherited lesions and those acquired post-transplantation. However, many centers do not perform such biopsies since they are invasive, costly and may delay the transplant procedure. We aim to generate a non-invasive virtual biopsy system using routinely collected donor parameters. Using 14,032 day-zero kidney biopsies from 17 international centers, we develop a virtual biopsy system. 11 basic donor parameters are used to predict four Banff kidney lesions: arteriosclerosis, arteriolar hyalinosis, interstitial fibrosis and tubular atrophy, and the percentage of renal sclerotic glomeruli. Six machine learning models are aggregated into an ensemble model. The virtual biopsy system shows good performance in the internal and external validation sets. We confirm the generalizability of the system in various scenarios. This system could assist physicians in assessing organ quality, optimizing allograft allocation together with discriminating between donor derived and acquired lesions post-transplantation.

The Banff 2022 Kidney Meeting Report: Reappraisal of microvascular inflammation and the role of biopsy-based transcript diagnostics.

The XVI-th Banff Meeting for Allograft Pathology was held at Banff, Alberta, Canada, from 19th to 23rd September 2022, as a joint meeting with the Canadian Society of Transplantation. To mark the 30th anniversary of the first Banff Classification, premeeting discussions were held on the past, present, and future of the Banff Classification. This report is a summary of the meeting highlights that were most important in terms of their effect on the Classification, including discussions around microvascular inflammation and biopsy-based transcript analysis for diagnosis. In a postmeeting survey, agreement was reached on the delineation of the following phenotypes: (1) "Probable antibody-mediated rejection (AMR)," which represents donor-specific antibodies (DSA)-positive cases with some histologic features of AMR but below current thresholds for a definitive AMR diagnosis; and (2) "Microvascular inflammation, DSA-negative and C4d-negative," a phenotype of unclear cause requiring further study, which represents cases with microvascular inflammation not explained by DSA. Although biopsy-based transcript diagnostics are considered promising and remain an integral part of the Banff Classification (limited to diagnosis of AMR), further work needs to be done to agree on the exact classifiers, thresholds, and clinical context of use.

The Banff 2022 Kidney Meeting Work Plan: Data-driven refinement of the Banff Classification for renal allografts.

The XVIth Banff Meeting for Allograft Pathology was held in Banff, Alberta, Canada, from September 19 to 23, 2022, as a joint meeting with the Canadian Society of Transplantation. In addition to a key focus on the impact of microvascular inflammation and biopsy-based transcript analysis on the Banff Classification, further sessions were devoted to other aspects of kidney transplant pathology, in particular T cell-mediated rejection, activity and chronicity indices, digital pathology, xenotransplantation, clinical trials, and surrogate endpoints. Although the output of these sessions has not led to any changes in the classification, the key role of Banff Working Groups in phrasing unanswered questions, and coordinating and disseminating results of investigations addressing these unanswered questions was emphasized. This paper summarizes the key Banff Meeting 2022 sessions not covered in the Banff Kidney Meeting 2022 Report paper and also provides an update on other Banff Working Group activities relevant to kidney allografts.

Recurrent atypical antiglomerular basement membrane nephritis in the kidney transplant.

Atypical antiglomerular basement membrane (anti-GBM) nephritis can be defined as linear GBM staining for monotypic or polytypic immunoglobulin (Ig) by immunofluorescence (IF) without a diffuse crescentic pattern. We describe the clinicopathologic features of 6 patients (18 biopsies) in this first series of recurrent atypical anti-GBM nephritis after kidney transplantation. Recurrent glomerulonephritis occurred at a mean of 3.8 months posttransplant (range 1-7 months). Three index biopsies were for clinical indication, and 3 were protocol biopsies. Glomerular histologic changes were mild, with 2 showing segmental endocapillary hypercellularity, 1 focal glomerular microangiopathy, and the others no significant glomerular histologic changes. All 6 allografts showed monotypic linear glomerular Ig staining by IF: IgG kappa (n = 2), IgG lambda, IgA kappa, IgA lambda, and IgM lambda. Follow-up biopsies were available for 5 patients and showed similar histologic and IF findings without evidence of significant progression. No patients had detectable serum anti-GBM antibody or monoclonal proteins. The mean serum creatinine level on follow-up (24-62 months posttransplant) was 1.8 (range 0.93-2.77) mg/dL; no grafts were lost to recurrent disease. This series demonstrates that monotypic atypical anti-GBM recurs in the allograft and supports the idea that this disease is due to a circulating monoclonal protein.

Banff Digital Pathology Working Group: Image Bank, Artificial Intelligence Algorithm, and Challenge Trial Developments.

The Banff Digital Pathology Working Group (DPWG) was established with the goal to establish a digital pathology repository; develop, validate, and share models for image analysis; and foster collaborations using regular videoconferencing. During the calls, a variety of artificial intelligence (AI)-based support systems for transplantation pathology were presented. Potential collaborations in a competition/trial on AI applied to kidney transplant specimens, including the DIAGGRAFT challenge (staining of biopsies at multiple institutions, pathologists' visual assessment, and development and validation of new and pre-existing Banff scoring algorithms), were also discussed. To determine the next steps, a survey was conducted, primarily focusing on the feasibility of establishing a digital pathology repository and identifying potential hosts. Sixteen of the 35 respondents (46%) had access to a server hosting a digital pathology repository, with 2 respondents that could serve as a potential host at no cost to the DPWG. The 16 digital pathology repositories collected specimens from various organs, with the largest constituent being kidney (n = 12,870 specimens). A DPWG pilot digital pathology repository was established, and there are plans for a competition/trial with the DIAGGRAFT project. Utilizing existing resources and previously established models, the Banff DPWG is establishing new resources for the Banff community.

Clinicopathologic Spectrum of Lysozyme-Associated Nephropathy.

Introduction: Lysozyme-associated nephropathy (LyN), a rare cause of kidney injury in patients with chronic myelomonocytic leukemia (CMML), has not been well described to date. We report the clinicopathologic spectrum of LyN from a multi-institutional series. Method: We identified 37 native kidney biopsies with LyN and retrospectively obtained clinicopathologic data. Results: Thirty-seven patients had a median age of 74 years and included 78% males. Their most common presentation was acute kidney injury (AKI) or AKI on chronic kidney disease (CKD) (66%) with median estimated glomerular filtration rate (eGFR) of 21.7 ml/min per 1.73 m2, and proteinuria of 1.7 g. A minority (15%) had partial Fanconi syndrome. Serum lysozyme levels were elevated in all tested. Hematologic disorder (n = 28, 76%) was the most common etiology, including CMML (n = 15), acute myeloid leukemia (n = 5), and myelodysplastic syndrome (MDS) (n = 5). Nonhematologic causes (n = 5, 14%), included metastatic neuroendocrine carcinoma (n = 3), sarcoidosis, and leprosy. Etiology was unknown in 4 (11%). Pathology showed proximal tubulopathy with abundant hypereosinophilic intracytoplasmic inclusions, with characteristic staining pattern by lysozyme immunostain. Mortality was high (8/30). However, among the 22 alive, including 85% treated, 7 had improved kidney function, including 1 who discontinued dialysis and 6 with increase in eGFR >15 ml/min per 1.73 m2 compared with eGFR at the time of biopsy. Conclusion: Increased awareness of the full clinicopathologic spectrum of LyN may lead to prompt diagnosis, earlier treatment, and potentially improved outcome of this rare entity.

COVID-19 and Glomerular Diseases.

COVID-19 is a systemic disease, and the kidney is one of the target organs of infection. Kidney injury is common and can occur in up to 40% of patients. Several glomerular diseases have been reported in association with COVID-19. Some are likely related to COVID-19 whereas many are likely coincidental. Glomerular diseases that are frequently reported in COVID-19 and have a plausible mechanistic explanation are likely to be related to COVID-19. In contrast, glomerular diseases that are seldom reported and have no known plausible mechanism, are likely to be unrelated. Collapsing glomerulopathy (CG) is by far the most prevalent. Its association with COVID-19, resembling HIV and CG, led to the newly proposed term "COVID-19 associated nephropathy" or "COVAN." High-risk APOL1 genotypes are the major risk factor in COVAN patients. Podocytopathy, membranous nephropathy (MN), pauci-immune crescentic glomerulonephritis (GN), and thrombotic microangiopathy (TMA) are also reported. In kidney allografts, CG remains the most common glomerular pathology. Patients typically present with acute kidney injury (AKI) or abnormal urinary findings at the time of or shortly after COVID-19 diagnosis. Treatment of glomerular disease in patients with COVID-19 is challenging. Providers should cautiously consider balancing risks and benefit of immunosuppression, particularly in patients with active diseases. Short-term outcomes vary but generally remain poor with high morbidity and mortality. Future study of long-term outcomes is needed to improve our understanding of glomerular disease associated with COVID-19.

Soluble and cell-based markers of immune checkpoint inhibitor-associated nephritis.

BACKGROUND: Non-invasive biomarkers of immune checkpoint inhibitor-associated acute tubulointerstitial nephritis (ICI-nephritis) are urgently needed. Because ICIs block immune checkpoint pathways that include cytotoxic T lymphocyte antigen 4 (CTLA4), we hypothesized that biomarkers of immune dysregulationpreviously defined in patients with congenital CTLA4 deficiency, including elevated soluble interleukin-2 receptor alpha (sIL-2R) and flow cytometric cell-based markers of B and T cell dysregulation in peripheral blood may aid the diagnosis of ICI-nephritis. METHODS: A retrospective cohort of patients diagnosed with ICI-nephritis was compared with three prospectively enrolled control cohorts: ICI-treated controls without immune-related adverse events, patients not on ICIs with hemodynamic acute kidney injury (hemodynamic AKI), and patients not on ICIs with biopsy proven acute interstitial nephritis from other causes (non-ICI-nephritis). sIL-2R level and flow cytometric parameters were compared between groups using Wilcoxon rank sum test or Kruskal-Wallis test. Receiver operating characteristic curves were generated to define the accuracy of sIL-2R and flow cytometric biomarkers in diagnosing ICI-nephritis. The downstream impact of T cell activation in the affected kidney was investigated using archived biopsy samples to evaluate the gene expression of IL2RA, IL-2 signaling, and T cell receptor signaling in patients with ICI-nephritis compared with other causes of drug-induced nephritis, acute tubular injury, and histologically normal controls. RESULTS: sIL-2R level in peripheral blood was significantly higher in patients with ICI-nephritis (N=24) (median 2.5-fold upper limit of normal (ULN), IQR 1.9-3.3), compared with ICI-treated controls (N=10) (median 0.8-fold ULN, IQR 0.5-0.9, p<0.001) and hemodynamic AKI controls (N=6) (median 0.9-fold-ULN, IQR 0.7-1.1, p=0.008). A sIL-2R cut-off point of 1.75-fold ULN was highly diagnostic of ICI-nephritis (area under the curve >96%) when compared with either ICI-treated or hemodynamic AKI controls. By peripheral blood flow cytometry analysis, lower absolute CD8+T cells, CD45RA+CD8+ T cells, memory CD27+B cells, and expansion of plasmablasts were prominent features of ICI-nephritis compared with ICI-treated controls. Gene expressions for IL2RA, IL-2 signaling, and T cell receptor signaling in the kidney tissue with ICI-nephritis were significantly higher compared with controls. CONCLUSION: Elevated sIL-2R level and flow cytometric markers of both B and T cell dysregulation may aid the diagnosis of ICI-nephritis.

Relapsing and Remitting Proliferative Glomerulonephritis With Monoclonal Immunoglobulin Deposits in Association With Infection and Vaccination: A Case Report.

Proliferative glomerulonephritis with monoclonal immunoglobulin deposits (PGNMID) is the second most common monoclonal gammopathy of renal significance. Rates of progression to kidney failure as well as rates of recurrence after kidney transplantation are high, especially in the absence of treatment. Treatment is usually targeted toward the abnormal clone, but even in the absence of an identifiable clone, empiric treatment is still recommended to avoid worsening prognosis. In this report, we present an unusual course of a PGNMID case with a relapsing and remitting pattern of illness, likely triggered by infection and vaccination. The patient in this case showed subsequent improvement after each episode, with stable kidney function over the years. This case report highlights the importance of investigating possible recent infectious exposures or vaccinations as potential triggers for this disease. This association should be considered for future patients with PGNMID, especially when there is no identifiable clone to help guide therapy.

Color Vision Deficiency Survey in Anatomic Pathology.

OBJECTIVES: To learn what color vision-deficient pathologists and cytotechnologists consider their most significant problems and advantages as well as any accommodations. METHODS: An anonymous online survey developed for practicing pathologists and cytotechnologists regarding their experiences with stains was sent to the members of 4 national societies. RESULTS: We received 377 responses. Twenty-three people, all men, identified themselves as color vision deficient, with 22 reporting red-green color vision deficiency and 1 reporting uncertain type. Eight pathologists and cytotechnologists indicated that they thought that their color vision deficiency conferred advantages to them, including a greater appreciation of morphology, with less confusion resulting from variations in stain quality or intensity. Nineteen pathologists and cytotechnologists thought that their color vision deficiency conferred disadvantages; the most common disadvantages stated were the identification of eosinophils and acid-fast bacilli. Other difficulties included interpretation of RBCs and nucleoli and sometimes Alcian blue, Brown and Brenn, Congo red, crystal violet, Fite, Giemsa, mucicarmine, periodic acid-Schiff, and fluorescence in situ hybridization stains. Only 2 of the color vision-deficient pathologists and cytotechnologists found digital slides more difficult than glass slides. CONCLUSIONS: Color vision-deficient pathologists and cytotechnologists report that they have developed approaches to viewing slides that do not compromise their interpretations. Digital pathology may provide several approaches for aiding color vision-deficient pathologists with the interpretation of certain stains.

Posttransplant recurrence of calcium oxalate crystals in patients with primary hyperoxaluria: Incidence, risk factors, and effect on renal allograft function.

Primary hyperoxaluria (PH) is a metabolic defect that results in oxalate overproduction by the liver and leads to kidney failure due to oxalate nephropathy. As oxalate tissue stores are mobilized after transplantation, the transplanted kidney is at risk of recurrent disease. We evaluated surveillance kidney transplant biopsies for recurrent calcium oxalate (CaOx) deposits in 37 kidney transplants (29 simultaneous kidney and liver [K/L] transplants and eight kidney alone [K]) in 36 PH patients and 62 comparison transplants. Median follow-up posttransplant was 9.2 years (IQR: [5.3, 15.1]). The recurrence of CaOx crystals in surveillance biopsies in PH at any time posttransplant was 46% overall (41% in K/L, 62% in K). Higher CaOx crystal index (which accounted for biopsy sample size) was associated with higher plasma and urine oxalate following transplant (p < .01 and p < .02, respectively). There was a trend toward higher graft failure among PH patients with CaOx crystals on surveillance biopsies compared with those without (HR 4.43 [0.88, 22.35], p = .07). CaOx crystal deposition is frequent in kidney transplants in PH patients. The avoidance of high plasma oxalate and reduction of CaOx crystallization may decrease the risk of recurrent oxalate nephropathy following kidney transplantation in patients with PH. This study was approved by the IRB at Mayo Clinic.

Genomics Integration Into Nephrology Practice.

RATIONALE & OBJECTIVE: The etiology of kidney disease remains unknown in many individuals with chronic kidney disease (CKD). We created the Mayo Clinic Nephrology Genomics Clinic to improve our ability to integrate genomic and clinical data to identify the etiology of unexplained CKD. STUDY DESIGN: Retrospective study. SETTING & PARTICIPANTS: An essential component of our program is the Nephrology Genomics Board which consists of nephrologists, geneticists, pathologists, translational omics scientists, and trainees who interpret the patient's clinical and genetic data. Since September 2016, the Board has reviewed 163 cases (15 cystic, 100 glomerular, 6 congenital anomalies of kidney and urinary tract (CAKUT), 20 stones, 15 tubulointerstitial, and 13 other). ANALYTICAL APPROACH: Testing was performed with targeted panels, single gene analysis, or analysis of kidney-related genes from exome sequencing. Variant classification was obtained based on the 2015 American College of Medical Genetics and Genomics and the Association for Molecular Pathology guidelines. RESULTS: A definitive genetic diagnosis was achieved for 50 families (30.7%). The highest diagnostic yield was obtained in individuals with tubulointerstitial diseases (53.3%), followed by congenital anomalies of the kidney and urological tract (33.3%), glomerular (31%), cysts (26.7%), stones (25%), and others (15.4%). A further 20 (12.3%) patients had variants of interest, and variant segregation, and research activities (exome, genome, or transcriptome sequencing) are ongoing for 44 (40%) unresolved families. LIMITATIONS: Possible overestimation of diagnostic rate due to inclusion of individuals with variants with evidence of pathogenicity but classified as of uncertain significance by the clinical laboratory. CONCLUSIONS: Integration of genomic and research testing and multidisciplinary evaluation in a nephrology cohort with CKD of unknown etiology or suspected monogenic disease provided a diagnosis in a third of families. These diagnoses had prognostic implications, and often changes in management were implemented.

Progressive decline of function in renal allografts with normal 1-year biopsies: Gene expression studies fail to identify a classifier.

Histologic findings on 1-year biopsies such as inflammation with fibrosis and transplant glomerulopathy predict renal allograft loss by 5 years. However, almost half of the patients with graft loss have a 1-year biopsy that is either normal or has only interstitial fibrosis. The goal of this study was to determine if there was a gene expression profile in these relatively normal 1-year biopsies that predicted subsequent decline in renal function. Using transcriptome microarrays we measured intragraft mRNA levels in a retrospective Discovery cohort (170 patients with a normal/minimal fibrosis 1-year biopsy, 54 with progressive decline in function/graft loss and 116 with stable function) and developed a nested 10-fold cross-validated gene classifier that predicted progressive decline in renal function (positive predictive value = 38 ± 34%%; negative predictive value = 73 ± 30%, c-statistic = .59). In a prospective, multicenter Validation cohort (270 patients with Normal/Interstitial Fibrosis [IF]), the classifier had a 20% positive predictive value, 85% negative predictive value and .58 c-statistic. Importantly, the majority of patients with graft loss in the prospective study had 1-year biopsies scored as Normal or IF. We conclude predicting graft loss in many renal allograft recipients (i.e., those with a relatively normal 1-year biopsy and eGFR > 40) remains difficult.