Haemoglobin, albumin, lymphocyte, and platelet score as an independent predictor for renal prognosis in IgA nephropathy.

Objective: The haemoglobin, albumin, lymphocyte, and platelet (HALP) score, a convenient and composite laboratory biomarker, can reflect inflammation and systemic nutritional status. This study was performed to investigate the effect of the HALP score on the prognosis of patients with IgA nephropathy (IgAN). Methods: This is a retrospective single centre study that enrolled 895 biopsy-confirmed IgAN patients from June 2019 to June 2022 who were followed for more than 1 year. Kaplan-Meier curves and Cox regression analyses were performed to determine the relationship between HALP and adverse outcomes. The restricted cubic splines was used to identify the possible associations. The optimal cut-off value of HALP for renal poor outcome was identified by the area under the receiver operating characteristic curve (AUC). Results: A total of 895 patients finally participated in the study and were divided into three groups (tertial 1-3) according to the baseline HALP score. More severe clinicopathologic features were observed in the lower HALP group, and Kaplan-Meier analysis showed patients in tertial 1 had a higher risk of kidney failure than the other groups (log-rank=11.02, P= 0.004). Multivariate Cox regression revealed that HALP score was an independent risk factor for renal prognosis in IgAN (adjusted HR: 0.967, 95% CI: 0.945-0.990, P = 0.006). The results of subgroup analysis suggested that HALP was more important in patients under the age of 50, BMI ≤ 23.9 and eGFR ≤ 90 mL/min/1.73 m2. The best cut-off HALP for renal survival was 38.83, sensitivity 72.1%, and specificity 55.9% (AUC: 0.662). Patients were further grouped according to HALP cut-off values and propensity matched. Multivariate Cox regression analysis revealed that HALP remained an independent predictor of IgAN in the matched cohort (HR 0.222, CI: 0.084-0.588, P=0.002). Conclusion: HALP is a novel and potent composite parameter to predict kidney outcome in patients with IgAN.

Podocyte injury as a potential therapeutic target in IgA nephropathy: should pathology guide us?

The Oxford histopathologic classification (MEST-C: scores for lesions indicating active glomerular inflammation, mesangial [M] and endocapillary [E] hypercellularity as well as cellular or fibrocellular crescents [C], and for segmental glomerulosclerosis [S] and interstitial fibrosis and/or tubular atrophy [T]) is useful in helping assess prognosis in patients with IgA nephropathy. Elements of this classification indicative of active glomerular inflammation, endocapillary hypercellularity and crescents, also have been found to be responsive to immunosuppressive therapy, potentially including newer agents specifically targeting mediators of such inflammation. In this issue of Kidney International, Bellur and coworkers identify histopathologic subtypes of segmental glomerulosclerosis in IgA nephropathy showing podocyte injury that also behave like active lesions, including showing improved outcomes with immunosuppression. This podocyte injury, identifiable only by kidney biopsy, may represent a potential therapeutic target in some patients with IgA nephropathy.

Genome-wide analysis of long noncoding RNAs as cis-acting regulators of transcription factor-encoding genes in IgA nephropathy.

BACKGROUND: IgA nephropathy (IgAN) is the most common form of primary glomerulonephritis in the world, but the disease pathogenesis noncoding is yet to be elucidated. Previous studies have revealed regulatory functions for long noncoding RNA (lncRNA) in various diseases; however, the roles of lncRNA in IgAN and regulation of transcription factors (TFs) have been scarcely investigated. METHODS: Renal tissue samples (n = 5) from patients with IgAN and control samples (n = 4) were collected and RNA sequencing (RNA-seq) was performed. Four software programs were employed for lncRNA prediction. GO (Gene Ontology)/KEGG (Kyoto Encyclopedia of Genes and Genomes) were employed for analysis of the identified differentially expressed genes (DEGs). A regulatory network model of DE lncRNA-TF-DEG was developed, and the levels of expression of key lncRNAs, TFs, and corresponding target genes were assessed using qRT-PCR and immunofluorescence. RESULTS: The current study identified 674 upregulated and 1,011 downregulated DE mRNAs and 260 upregulated and 232 downregulated DE lncRNAs in IgAN samples compared with control samples. The upregulated DE mRNAs showed enrichment in cell adhesion and collagen glial fiber organization pathways. The DE lncRNAs-DE mRNAs showing co-expression are associated with transmembrane transport. A novel regulatory network model of lncRNA-TF-DEG has been developed. This study identified seven TFs that are cis-regulated by 6 DE lncRNAs, and show co-expression with 132 DEGs (correlation coefficient ≥ 0.8, P ≤ 0.01), generating 158 pairs that showed co-expression. The lncRNAs NQO1-DT and RP5-1057120.6 were found to be highly expressed in IgAN samples. The TFs vitamin D Receptor (VDR) and NFAT5, along with their target genes were also aberrantly expressed. CONCLUSION: Key lncRNAs and TFs centrally associated with IgAN have been identified in this study. A regulatory network model of lncRNA-TF-mRNA was constructed. Further studies on the genes identified herewith could provide insight into the pathogenesis of IgAN.

Protocol for a systematic review of the application of the kidney failure risk equation and Oxford classification in estimating prognosis in IgA nephropathy.

BACKGROUND: IgA nephropathy (IgAN) is a common cause of chronic kidney disease (CKD) and end-stage renal disease (ESRD). Outcomes are highly variable and predicting risk of disease progression at an individual level is challenging. Accurate risk stratification is important to identify individuals most likely to benefit from treatment. The Kidney Failure Risk Equation (KFRE) has been extensively validated in CKD populations and predicts the risk of ESRD at 2 and 5 years using non-invasive tests; however, its predictive performance in IgAN is unknown. The Oxford classification (OC) describes pathological features demonstrated on renal biopsy that are associated with adverse clinical outcomes that may also inform prognosis. The objective of this systematic review is to compare the KFRE with the OC in determining prognosis in IgAN. METHODS: A systematic review will be conducted and reported in line with PRISMA guidelines (PRISMA-P checklist attached as Additional file 1). Inclusion criteria will be cohort studies that apply the KFRE or OC to determine the risk of CKD progression or ESRD in individuals with IgAN. Multiple databases will be searched in duplicate to identify relevant studies, which will be screened first by title, then by abstract and then by full-text analysis. Results will be collated for comparison. Risk of bias and confidence assessments will be conducted independently by two reviewers, with a third reviewer available if required. DISCUSSION: Identifying individuals at the highest risk of progression to ESRD is challenging in IgAN, due to the heterogeneity of clinical outcomes. Risk prediction tools have been developed to guide clinicians; however, it is imperative that these aids are accurate and reproducible. The OC is based on observations made by specialist renal pathologists and may be open to observer bias, therefore the utility of prediction models incorporating this classification may be diminished, particularly as in the future novel biomarkers may be incorporated into clinical practice. SYSTEMATIC REVIEW REGISTRATION: PROSPERO CRD42022364569.

Molecular characterization of m6A RNA methylation regulators with features of immune dysregulation in IgA nephropathy.

The role of RNA N6-methyladenosine (m6A) modification in immunity is being elucidated. This study aimed to explore the potential association between m6A regulators and the immune microenvironment in IgA nephropathy (IgAN). The expression profiles of 24 m6A regulators in 107 IgAN patients were obtained from the Gene Expression Omnibus (GEO) database. The least absolute shrinkage and selection operator (LASSO) regression and logistic regression analysis were utilized to construct a model for distinguishing IgAN from control samples. Based on the expression levels of m6A regulators, unsupervised clustering was used to identify m6A-induced molecular clusters in IgAN. Gene set enrichment analysis (GSEA) and immunocyte infiltration among different clusters were examined. The gene modules with the highest correlation for each of the three clusters were identified by weighted gene co-expression network analysis (WGCNA). A model containing 10 m6A regulators was developed using LASSO and logistic regression analyses. Three molecular clusters were determined using consensus clustering of 24 m6A regulators. A decrease in the expression level of YTHDF2 in IgAN samples was significantly negatively correlated with an increase in resting natural killer (NK) cell infiltration and was positively correlated with the abundance of M2 macrophage infiltration. The risk scores calculated by the nomogram were significantly higher for cluster-3, and the expression levels of m6A regulators in this cluster were generally low. Immunocyte infiltration and pathway enrichment results for cluster-3 differed significantly from those for the other two clusters. Finally, the expression of YTHDF2 was significantly decreased in IgAN based on immunohistochemical staining. This study demonstrated that m6A methylation regulators play a significant role in the regulation of the immune microenvironment in IgAN. Based on m6A regulator expression patterns, IgAN can be classified into multiple subtypes, which might provide additional insights into novel therapeutic methods for IgAN.

Cross-species single-cell analysis uncovers the immunopathological mechanisms associated with IgA nephropathy progression.

IgA nephropathy (IgAN) represents the main cause of renal failure, while the precise pathogenetic mechanisms have not been fully determined. Herein, we conducted a cross-species single-cell survey on human IgAN and mouse and rat IgAN models to explore the pathogenic programs. Cross-species single-cell RNA sequencing (scRNA-Seq) revealed that the IgAN mesangial cells (MCs) expressed high levels of inflammatory signatures CXCL12, CCL2, CSF1, and IL-34 and specifically interacted with IgAN macrophages via the CXCL12/CXCR4, CSF1/IL-34/CSF1 receptor, and integrin subunit alpha X/integrin subunit alpha M/complement C3 (C3) axes. IgAN macrophages expressed high levels of CXCR4, PDGFB, triggering receptor expressed on myeloid cells 2, TNF, and C3, and the trajectory analysis suggested that these cells derived from the differentiation of infiltrating blood monocytes. Additionally, protein profiling of 21 progression and 28 nonprogression IgAN samples revealed that proteins CXCL12, C3, mannose receptor C-type 1, and CD163 were negatively correlated with estimated glomerular filtration rate (eGFR) value and poor prognosis (30% eGFR as composite end point). Last, a functional experiment revealed that specific blockade of the Cxcl12/Cxcr4 pathway substantially attenuated the glomerulus and tubule inflammatory injury, fibrosis, and renal function decline in the mouse IgAN model. This study provides insights into IgAN progression and may aid in the refinement of IgAN diagnosis and the optimization of treatment strategies.

Accelerated involution of germinal center in palatine tonsils in IgA nephropathy.

BACKGROUND: Altered immunological responses in the palatine tonsils may be involved in the pathogenesis of IgA nephropathy (IgAN). The germinal center serves as the site for antigen-specific humoral immune responses in the palatine tonsils. Germinal center involution is frequently observed in the palatine tonsils of IgAN (IgAN tonsils). However, the pathogenic significance of these characteristic changes remains unclear. This study aimed to investigate the morphological changes in secondary lymphoid follicles in IgAN tonsils and to evaluate the correlation between the morphometric results and the clinicopathological severity of IgAN. METHODS: The tonsils of age-matched patients with recurrent tonsillitis (RT tonsils) were used as controls. The correlation between the degree of lymphoid follicular involution and histopathological severities in clinical or kidney biopsy was evaluated. RESULTS: In total, 87 patients with IgAN were included (48% male, median age 35 years, median estimated glomerular filtration rate: 74 mL/min/1.73 m2). Compared to RT tonsils, IgAN tonsils showed smaller median sizes of lymphoid follicles and germinal centers (P < 0.001). The relative areas of lymphoid follicles (%LFA) and germinal centers (%GCA) in the total tonsillar tissue were smaller in the IgAN tonsils than in the RT tonsils (P < 0.001). In contrast, the median proportion of mantle zones in the total tonsillar tissue was comparable between the groups. A lower %LFA was associated with a longer period from the onset of urinary abnormalities to biopsy diagnosis and higher urinary protein excretion (P = 0.01). %LFA showed significant negative correlations with frequencies of glomeruli with both global and segmental sclerosis. CONCLUSIONS: The present study confirmed accelerated germinal center involution in the tonsils of patients with IgAN. This characteristic change in the IgAN tonsil correlates with heavy proteinuria and advanced chronic histopathological changes in the kidneys, thereby suggesting the involvement of repeated tonsillar immunoreactions during IgAN progression.

[Anti-Proteinuric Effect of GLP1-RA as Add-On to SGLT2-i and ACE-i in a Diabetic Patient with IgA Nephropathy].

Immunoglobulin A (IgA) nephropathy is a common glomerulonephritis, but its treatment remains matter of debate. Recommendation for corticosteroids has been supported, but renin-angiotensin inhibitors, RAAS, and sodium-glucose co-transporter 2 inhibitors (SGLT2i) are increasingly used because of a better benefit/safety balance in comparison with systemic steroids and immunosuppressive treatments. In this case report, a patient with type 2 diabetes (T2DM) and biopsy-proven nephrotic IgA-related nephropathy documented a rapid meaningful reduction of proteinuria and the effect was persistent for 2 years, after receiving the treatment with a GLP1-RA on top of the previous treatment with ACE-inhibitors and SGLT2-i. Considering the beneficial effects of GLP1-RA in diabetes related chronic kidney disease, the present case report supports the notion that these drugs could also represent a beneficial treatment option in IgA nephropathy.

Complement system is overactivated in patients with IgA nephropathy after COVID-19.

IgA nephropathy (IgAN), which has been confirmed as a complement mediated autoimmune disease, is also one form of glomerulonephritis associated with COVID-19. Here, we aim to investigate the clinical and immunological characteristics of patients with IgAN after COVID-19. The level of plasma level of C5a (p < 0.001), soluble C5b-9 (p = 0.018), FHR5 (p < 0.001) were all significantly higher in Group CoV (33 patients with renal biopsy-proven IgAN experienced COVID-19) compared with Group non-CoV (44 patients with IgAN without COVID-19), respectively. Compared with Group non-CoV, the intensity of glomerular C4d (p = 0.017) and MAC deposition (p < 0.001) and Gd-IgA1 deposition (p = 0.005) were much stronger in Group CoV. Our finding revealed that for IgAN after COVID-19, mucosal immune responses to SARS-CoV-2 infection may result in the overactivation of systemic and renal local complement system, and increased glomerular deposition of Gd-IgA1, which may lead to renal dysfunction and promote renal progression in IgAN patients.

Machine learning-based diagnostic prediction of IgA nephropathy: model development and validation study.

IgA nephropathy progresses to kidney failure, making early detection important. However, definitive diagnosis depends on invasive kidney biopsy. This study aimed to develop non-invasive prediction models for IgA nephropathy using machine learning. We collected retrospective data on demographic characteristics, blood tests, and urine tests of the patients who underwent kidney biopsy. The dataset was divided into derivation and validation cohorts, with temporal validation. We employed five machine learning models-eXtreme Gradient Boosting (XGBoost), LightGBM, Random Forest, Artificial Neural Networks, and 1 Dimentional-Convolutional Neural Network (1D-CNN)-and logistic regression, evaluating performance via the area under the receiver operating characteristic curve (AUROC) and explored variable importance through SHapley Additive exPlanations method. The study included 1268 participants, with 353 (28%) diagnosed with IgA nephropathy. In the derivation cohort, LightGBM achieved the highest AUROC of 0.913 (95% CI 0.906-0.919), significantly higher than logistic regression, Artificial Neural Network, and 1D-CNN, not significantly different from XGBoost and Random Forest. In the validation cohort, XGBoost demonstrated the highest AUROC of 0.894 (95% CI 0.850-0.935), maintaining its robust performance. Key predictors identified were age, serum albumin, IgA/C3, and urine red blood cells, aligning with existing clinical insights. Machine learning can be a valuable non-invasive tool for IgA nephropathy.

The predictive value of free thyroxine combined with tubular atrophy/interstitial fibrosis for poor prognosis in patients with IgA nephropathy.

Background: IgA nephropathy (IgAN), the most common type of glomerulonephritis, has great individual differences in prognosis. Many studies showed the relationship between thyroid hormones and chronic kidney disease. However, the relationship between free thyroxine (FT4), as a thyroid hormone, and IgAN is still unclear. This study aimed to evaluate the impact of FT4 on IgAN prognosis. Methods: This retrospective study involved 223 patients with biopsy-proven IgAN. The renal composite outcomes were defined as: (1) ESRD, defined as eGFR < 15 ml/(min·1.73 m2) or initiation of renal replacement therapy (hemodialysis, peritoneal dialysis, renal transplantation); (2) serum creatinine doubled from baseline; (3) eGFR decreased by more than 50% from baseline. The predictive value was determined by the area under the curve (AUC). Kaplan-Meier and Cox proportional hazards analyses assessed renal progression and prognosis. Results: After 38 (26-54) months of follow-up, 23 patients (10.3%) experienced renal composite outcomes. Kaplan-Meier survival curve analysis showed that the renal survival rate of the IgAN patients with FT4<15.18pmol/L was lower than that with FT4≥15.18pmol/L (P < 0. 001). Multivariate Cox regression model analysis showed that FT4 was a protective factor for poor prognosis of IgAN patients, whether as a continuous variable or a categorical variable (HR 0.68, 95%CI 0.51-0.90, P =0.007; HR 0.04, 95%CI 0.01-0.20, P <0.001). ROC curve analysis showed that FT4 combined with t score had a high predictive value for poor prognosis of IgAN patients (AUC=0.881, P<0.001). Conclusion: FT4 was a protective factor for IgAN. In addition, FT4 combined with tubular atrophy/interstitial fibrosis had a high predictive value for poor prognosis of IgAN.

Immune checkpoint inhibitor therapy associated with IgA nephropathy: a case report and literature review.

Immune checkpoint inhibitors (ICIs) dramatically improve the prognosis of many malignancies but at the cost of numerous side effects, which may limit their benefits. Acute kidney injury associated with immune checkpoint inhibitors most frequently are acute tubulointerstitial nephritis (ATIN), but various cases of glomerulonephritis have also been reported. Herein, we report a case of severe IgA nephropathy (IgAN) associated with ICIs and carry out a literature review. IgAN was diagnosed in a median time of 5 months (range 1-12 months) after the initiation of ICIs, with heterogeneous severity, and usually treated by corticosteroid and discontinuation of ICIs. In contrast to our case, renal outcomes in literature were often favorable, with recovery of renal function and a reduction in proteinuria on treatment. Although IgAN related to ICIs is a much rarer complication than ATIN, it may still be underdiagnosed. Careful questioning and screening for asymptomatic hematuria should be performed before using ICIs.

Histological Correlation between Tonsillar and Glomerular Lesions in Patients with IgA Nephropathy Justifying Tonsillectomy: A Retrospective Cohort Study.

Tonsillectomy with steroid pulse therapy (SPT) has been established as an effective treatment for immunoglobulin A nephropathy (IgAN) in Japan. However, the underlying mechanisms supporting tonsillectomy remain unclear. This study assessed palatine tonsils from 77 patients with IgAN, including 14 and 63 who received SPT before and after tonsillectomy, respectively. Tonsils from 21 patients with chronic tonsillitis were analyzed as controls. Specific tonsillar lesions were confirmed in patients with IgAN, correlating with active or chronic renal glomerular lesions and SPT. T-nodule and involution of lymphoepithelial symbiosis scores in tonsils correlated with the incidence of active crescents and segmental sclerosis in the glomeruli, respectively. The study revealed an essential role of the tonsil-glomerular axis in early active and late chronic phases. Moreover, the SPT-preceding group demonstrated no changes in the T-nodule score, which correlated with active crescent formation, but exhibited a considerable shrinkage of lymphatic follicles that produced aberrant IgA1. The study underscores the involvement of innate and cellular immunity in IgAN and advocates for tonsillectomy as a necessary treatment alongside SPT for IgAN, based on a stepwise process.

Characterizing Glomerular Barrier Dysfunction with Patient-Derived Serum in Glomerulus-on-a-Chip Models: Unveiling New Insights into Glomerulonephritis.

Glomerulonephritis (GN) is characterized by podocyte injury or glomerular filtration dysfunction, which results in proteinuria and eventual loss of kidney function. Progress in studying the mechanism of GN, and developing an effective therapy, has been limited by the absence of suitable in vitro models that can closely recapitulate human physiological responses. We developed a microfluidic glomerulus-on-a-chip device that can recapitulate the physiological environment to construct a functional filtration barrier, with which we investigated biological changes in podocytes and dynamic alterations in the permeability of the glomerular filtration barrier (GFB) on a chip. We also evaluated the potential of GN-mimicking devices as a model for predicting responses to human GN. Glomerular endothelial cells and podocytes successfully formed intact monolayers on opposite sides of the membrane in our chip device. Permselectivity analysis confirmed that the chip was constituted by a functional GFB that could accurately perform differential clearance of albumin and dextran. Reduction in cell viability resulting from damage was observed in all serum-induced GN models. The expression of podocyte-specific marker WT1 was also decreased. Albumin permeability was increased in most models of serum-induced IgA nephropathy (IgAN) and membranous nephropathy (MN). However, sera from patients with minimal change disease (MCD) or lupus nephritis (LN) did not induce a loss of permeability. This glomerulus-on-a-chip system may provide a platform of glomerular cell culture for in vitro GFB in formation of a functional three-dimensional glomerular structure. Establishing a disease model of GN on a chip could accelerate our understanding of pathophysiological mechanisms of glomerulopathy.

Shen-yan-yi-hao oral solution ameliorates IgA nephropathy via intestinal IL-17/NF-κB pathway.

ETHNOPHARMACOLOGICAL RELEVANCE: Immunoglobulin A nephropathy (IgAN) is the most common primary glomerulonephritis in the world, it is one of the most common causes of kidney disease and can lead to end-stage kidney disease, however, its pathogenesis is still complicated. The Shen-yan-yi-hao oral solution (SOLI) is an effective prescription for the clinical treatment of IgAN while its specific mechanism remains to be further elucidated. AIM OF THE STUDY: This study investigates SOLI's effects on IgAN in rats, particularly on the intestinal mucosal barrier, and identifies potential therapeutic targets through network pharmacology and molecular docking, validated experimentally. MATERIALS AND METHODS: Target genes for SOLI in IgAN were identified and analysed through molecular docking and KEGG pathway enrichment. An IgAN rat model examined SOLI's effect on renal biomarkers and cytokines involved in specific pathways, ileum mucosal lesions, and the intestinal immune system. The IL-17 pathway's role was studied in IEC-6 cells with SOLI in vitro. RESULT: Rats developed increased proteinuria and kidney damage marked by IgA deposition and inflammation. SOLI treatment significantly ameliorated these symptoms, reduced galactose-deficient Ig A1 (Gd-IgA1), and decreased cytokines like IL-17, TNF-α, IL-6 and IL-1ß etc. SOLI also normalized intestinal tight junction protein expression, ameliorated intestinal damage, and regulated intestinal immune response (focused on IL-17/NF-κB signal pathway). SOLI moderated the abnormally activated IL-17 pathway, which damages intestinal epithelial cells, suggesting IgAN treatment potential. CONCLUSION: SOLI reduces proteinuria and enhances intestinal mucosal function in IgAN rats, kidney protection in the IgAN rat model may initiate from modulating the intestinal IL-17/NF-κB pathway and subsequent Gd-IgA1 accumulation.

External Validation of the International IgA Nephropathy Prediction Tool in Older Adult Patients.

Purpose: The International IgA Nephropathy Prediction Tool (IIgAN-PT) can predict the risk of End-stage renal disease (ESRD) or estimated glomerular filtration rate (eGFR) decline ≥ 50% for adult IgAN patients. Considering the differential progression between older adult and adult patients, this study aims to externally validate its performance in the older adult cohort. Patients and Methods: We analyzed 165 IgAN patients aged 60 and above from six medical centers, categorizing them by their predicted risk. The primary outcome was a ≥50% reduction in estimated glomerular filtration rate (eGFR) or kidney failure. Evaluation of both models involved concordance statistics (C-statistics), time-dependent receiver operating characteristic (ROC) curves, Kaplan-Meier survival curves, and calibration plots. Comparative reclassification was conducted using net reclassification improvement (NRI) and integrated discrimination improvement (IDI). Results: The study included 165 Chinese patients (median age 64, 60% male), with a median follow-up of 5.1 years. Of these, 21% reached the primary outcome. Both models with or without race demonstrated good discrimination (C-statistics 0.788 and 0.790, respectively). Survival curves for risk groups were well-separated. The full model without race more accurately predicted 5-year risks, whereas the full model with race tended to overestimate risks after 3 years. No significant reclassification improvement was noted in the full model without race (NRI 0.09, 95% CI: -0.27 to 0.34; IDI 0.003, 95% CI: -0.009 to 0.019). Conclusion: : Both models exhibited excellent discrimination among older adult IgAN patients. The full model without race demonstrated superior calibration in predicting the 5-year risk.

Medullary sponge kidney with IgA nephropathy: a case report and literature review.

BACKGROUND: Medullary sponge kidney (MSK)is rare in association with glomerulonephritis. We report a patient with medullary sponge kidney, and the kidney biopsy revealed a diagnosis of IgA nephropathy. CASE PRESENTATION: A 27-year-old female presented with hematuria and proteinuria, and imaging studies indicated the presence of medullary spongy kidney. With appropriate preparation, a kidney biopsy was performed. Considering the patient's clinical and pathological characteristics, the final diagnosis was determined to be medullary sponge kidney associated by IgA nephropathy. The combination of corticosteroids and angiotensin receptor blockers (ARBs) proved to be significantly effective in reducing proteinuria in the current case. To the best of our knowledge, this is the first reported case that demonstrates the coexistence of MSK and IgA nephropathy. CONCLUSIONS: Administering precise therapy based on renal pathology can potentially enhance outcomes for patients with renal conditions, necessitating the need for clinicians to be vigilant about differential diagnosis in order to reduce the rates of missed diagnoses and misdiagnosis.

[Automatic classification of immune-mediated glomerular diseases based on multi-modal multi-instance learning].

OBJECTIVE: To develop a multi-modal deep learning method for automatic classification of immune-mediated glomerular diseases based on images of optical microscopy (OM), immunofluorescence microscopy (IM), and transmission electron microscopy (TEM). METHODS: We retrospectively collected the pathological images from 273 patients and constructed a multi-modal multi- instance model for classification of 3 immune-mediated glomerular diseases, namely immunoglobulin A nephropathy (IgAN), membranous nephropathy (MN), and lupus nephritis (LN). This model adopts an instance-level multi-instance learning (I-MIL) method to select the TEM images for multi-modal feature fusion with the OM images and IM images of the same patient. By comparing this model with unimodal and bimodal models, we explored different combinations of the 3 modalities and the optimal methods for modal feature fusion. RESULTS: The multi-modal multi-instance model combining OM, IM, and TEM images had a disease classification accuracy of (88.34±2.12)%, superior to that of the optimal unimodal model [(87.08±4.25)%] and that of the optimal bimodal model [(87.92±3.06)%]. CONCLUSION: This multi- modal multi- instance model based on OM, IM, and TEM images can achieve automatic classification of immune-mediated glomerular diseases with a good classification accuracy.