A PLA2R-IgG4 Antibody-Based Predictive Model for Assessing Risk Stratification of Idiopathic Membranous Nephropathy

A dynamic online nomogram for predicting renal outcomes of idiopathic membranous nephropathy

BACKGROUND

Because spontaneous remission is common in IMN, and there are adverse effects of immunosuppressive therapy, it is important to assess the risk of progressive loss of renal function before deciding whether and when to initiate immunosuppressive therapy. Therefore, this study aimed to establish a risk prediction model to predict patient prognosis and treatment response to help clinicians evaluate patient prognosis and decide on the best treatment regimen.

METHODS

From September 2019 to December 2020, a total of 232 newly diagnosed IMN patients from three hospitals in Liaoning Province were enrolled. Logistic regression analysis selected the risk factors affecting the prognosis, and a dynamic online nomogram prognostic model was constructed based on extreme gradient boost, random forest, logistic regression machine learning algorithms. Receiver operating characteristic and calibration curves and decision curve analysis were utilized to assess the performance and clinical utility of the developed model.

RESULTS

A total of 130 patients were in the training cohort and 102 patients in the validation cohort. Logistic regression analysis identified four risk factors: course ≥ 6 months, UTP, D-dimer and sPLA2R-Ab. The random forest algorithm showed the best performance with the highest AUROC (0.869). The nomogram had excellent discrimination ability, calibration ability and clinical practicability in both the training cohort and the validation cohort.

CONCLUSIONS

The dynamic online nomogram model can effectively assess the prognosis and treatment response of IMN patients. This will help clinicians assess the patient's prognosis more accurately, communicate with the patient in advance, and jointly select the most appropriate treatment plan.

Predictive value of the domain specific PLA2R antibodies for clinical remission in patients with primary membranous nephropathy: A retrospective study

BACKGROUND

M-type phospholipase A2 receptor (PLA2R) is a major auto-antigen of primary membranous nephropathy(PMN). Anti-PLA2R antibody levels are closely associated with disease severity and therapeutic effectiveness. Analysis of PLA2R antigen epitope reactivity may have a greater predictive value for remission compared with total PLA2R-antibody level. This study aims to elucidate the relationship between domain-specific antibody levels and clinical outcomes of PMN.

METHODS

This retrospective analysis included 87 patients with PLA2R-associated PMN. Among them, 40 and 47 were treated with rituximab (RTX) and cyclophosphamide (CTX) regimen, respectively. The quantitative detection of -immunoglobulin G (IgG)/-IgG4 targeting PLA2R and its epitope levels in the serum of patients with PMN were obtained through time-resolved fluorescence immunoassays and served as biomarkers in evaluating the treatment effectiveness. A predictive PMN remission possibility nomogram was developed using multivariate logistic regression analysis. Discrimination in the prediction model was assessed using the area under the receiver operating characteristic curve (AUC-ROC).Bootstrap ROC was used to evaluate the performance of the prediction model.

RESULTS

After a 6-month treatment period, the remission rates of proteinuria, including complete remission and partial remission in the RTX and CTX groups, were 70% and 70.21% (P = 0.983), respectively. However, there was a significant difference in immunological remission in the PLA2R-IgG4 between the RTX and CTX groups (21.43% vs. 61.90%, P = 0.019). Furthermore, we found differences in PLA2R-CysR-IgG4(P = 0.030), PLA2R-CTLD1-IgG4(P = 0.005), PLA2R-CTLD678-IgG4(P = 0.003), and epitope spreading (P = 0.023) between responders and non-responders in the CTX group. Multivariate logistic analysis showed that higher levels of urinary protein (odds ratio [OR], 0.49; 95% confidence interval [CI], 0.26-0.95; P = 0.035) and higher levels of PLA2R-CTLD1-IgG4 (OR, 0.79; 95%CI,0.62-0.99; P = 0.041) were independent risk factors for early remission. A multivariate model for estimating the possibility of early remission in patients with PMN is presented as a nomogram. The AUC-ROC of our model was 0.721 (95%CI, 0.601-0.840), in consistency with the results obtained with internal validation, for which the AUC-ROC was 0.711 (95%CI, 0.587-0.824), thus, demonstrating robustness.

CONCLUSIONS

Cyclophosphamide can induce immunological remission earlier than rituximab at the span of 6 months. The PLA2R-CTLD1-IgG4 has a better predict value than total PLA2R-IgG for remission of proteinuria at the 6th month.

Quantitative detection and prognostic value of antibodies against M-type phospholipase A2 receptor and its cysteine-rich ricin domain and C-type lectin domains 1 and 6-7-8 in patients with idiopathic membranous nephropathy

BACKGROUND

M-type phospholipase A2 receptor (PLA2R) is the major autoantigen in adult idiopathic membranous nephropathy (IMN). Although reactive epitopes in the PLA2R domains have been identified, the clinical value of these domains recognized by anti-PLA2R antibodies remains controversial. Accordingly, this study aimed to quantitatively detect changes in the concentrations of different antibodies against epitopes of PLA2R in patients with IMN before and after treatment to evaluate the clinical value of epitope spreading.

METHODS

Highly sensitive time-resolved fluorescence immunoassay was used to quantitatively analyze the concentrations of specific IgG and IgG4 antibodies against PLA2R and its epitopes (CysR, CTLD1, CTLD6-7-8) in a cohort of 25 patients with PLA2R-associated membranous nephropathy (13 and 12 in the remission and non-remission groups, respectively) before and after treatment, and the results were analyzed in conjunction with clinical biochemical indicators.

RESULTS

The concentration of specific IgG (IgG4) antibodies against PLA2R and its epitopes (CysR, CTLD1 and CTLD6-7-8) in non-remission group was higher than that in remission group. The multipliers of elevation of IgG (IgG4) antibody were 5.6(6.2) fold, 3.0(24.3) fold, 1.6(9.0) fold, and 4.2(2.6) fold in the non-remission/remission group, respectively. However, the difference in antibody concentrations between the two groups at the end of follow-up was 5.6 (85.2), 1.7 (13.1), 1.0 (5.1), and 1.5 (22.3) times higher, respectively. When detecting concentrations of specific IgG antibodies against PLA2R and its different epitopes, the remission rate was 66.67% for only one epitope at M0 and 36.36% for three epitopes at M0. When detecting concentrations of specific IgG4 antibodies against PLA2R and its different epitopes, the remission rate was 100.00% for only one epitope at M0 and 50.00% for three epitopes at M0. A trivariate logistic regression model for the combined detection of eGFR, anti-CTLD678 IgG4, and urinary protein had an AUC of 100.00%.

CONCLUSION

Low concentrations of anti-CysR-IgG4, anti-CTLD1-IgG4, and anti-CTLD6-7-8-IgG4 at initial diagnosis predict rapid remission after treatment. The use of specific IgG4 against PLA2R and its different epitopes combined with eGFR and urinary protein provides a better assessment of the prognostic outcome of IMN.

Prognostic prediction of idiopathic membranous nephropathy using interpretable machine learning

BACKGROUND

Established prognostic models of idiopathic membranous nephropathy (IMN) were limited to traditional modeling methods and did not comprehensively consider clinical and pathological patient data. Based on the electronic medical record (EMR) system, machine learning (ML) was used to construct a risk prediction model for the prognosis of IMN.

METHODS

Data from 418 patients with IMN were diagnosed by renal biopsy at the Fifth Clinical Medical College of Shanxi Medical University. Fifty-nine medical features of the patients could be obtained from EMR, and prediction models were established based on five ML algorithms. The area under the curve, recall rate, accuracy, and F1 were used to evaluate and compare the performances of the models. Shapley additive explanation (SHAP) was used to explain the results of the best-performing model.

RESULTS

One hundred and seventeen patients (28.0%) with IMN experienced adverse events, 28 of them had compound outcomes (ESRD or double serum creatinine (SCr)), and 89 had relapsed. The gradient boosting machine (LightGBM) model had the best performance, with the highest AUC (0.892 ± 0.052, 95% CI 0.840-0.945), accuracy (0.909 ± 0.016), recall (0.741 ± 0.092), precision (0.906 ± 0.027), and F1 (0.905 ± 0.020). Recursive feature elimination with random forest and SHAP plots based on LightGBM showed that anti-phospholipase A2 receptor (anti-PLA2R), immunohistochemical immunoglobulin G4 (IHC IgG4), D-dimer (D-DIMER), triglyceride (TG), serum albumin (ALB), aspartate transaminase (AST), β2-microglobulin (BMG), SCr, and fasting plasma glucose (FPG) were important risk factors for the prognosis of IMN. Increased risk of adverse events in IMN patients was correlated with high anti-PLA2R and low IHC IgG4.

CONCLUSIONS

This study established a risk prediction model for the prognosis of IMN using ML based on clinical and pathological patient data. The LightGBM model may become a tool for personalized management of IMN patients.

PLA2R-IgG4 antibody as a predictive biomarker of treatment effectiveness and prognostic evaluation in patients with idiopathic membranous nephropathy: a retrospective study

Background

The Kidney Disease Improving Global Outcomes (KDIGO) 2021 guidelines recommend Rituximab (RTX) as the first-line therapy and phospholipase A2 receptor (PLA2R) antibody as a biomarker for remission and prognosis in patients with idiopathic membranous nephropathy (IMN).

Methods

This study was a retrospective analysis of 70 patients with IMN treated with either rituximab (RTX) or cyclophosphamide (CTX) and steroid. Quantitative detection of PLA2R-IgG and PLA2R-IgG4 antibodies at sixth month after treatment, determined using time-resolved fluoroimmunoassay (TRFIA), were used for treatment effectiveness analysis and prognostic evaluation in patients with IMN.

Results

After 12 months of therapy, the remission rate of proteinuria, including complete remission (CR) and partial remission (PR) in the RTX group and the CTX group, were 74% versus 67.5% (P = 0.114), respectively. Both PLA2R-IgG and PLA2R-IgG4 levels were decreased in patients with remission of proteinuria after 6 months of therapy. Receiver operating characteristic curve (ROC) curve analysis exhibited that the AUC of PLA2R-IgG4 and the PLA2R-IgG as laboratory criteria for proteinuria remission were 0.970 versus 0.886 (P = 0.0516), respectively, after 6 months of treatment. The cut-off value of PLA2R-IgG4 was 7.67 RU/mL and the sensitivity and specificity of remission rate at 6th month were 90.9% and 100%, respectively. Furthermore, the AUC of the PLA2R-IgG4 and PLA2R-IgG to predict the outcome after 12 months of treatment were 0.922 versus 0.897 (P = 0.3270), respectively. With the cut-off value of PLA2R-IgG4 being 22.985 RU/mL, the sensitivity and specificity of remission rate at 12th month were 100% and 87.1%, respectively. Logistic regression analysis revealed that the PLA2R-IgG4 level (P = 0.023), the rate of decrease of PLA2R-IgG4 level (P = 0.034), and eGFR level (P = 0.012) were significantly associated with remission.

Conclusions

We found that the patients in the RTX group and CTX group achieved effective remission of proteinuria after 12 months of treatment. PLA2R-IgG4 may be a more effective biomarker for treatment effectiveness analysis and prognostic assessment, compared with anti-PLA2R-IgG for PLA2R associated IMN.

Clinical Evaluation of Antiphospholipase A2 Receptor IgG4 level and Its IgG4-to-IgG Ratio Based on Quantitative Immunoassays in Idiopathic Membranous Nephropathy

Background. Phospholipase A2 receptor (PLA2R), located at the membrane of glomerular podocyte, is the major autoantigen of idiopathic membranous nephropathy (IMN), and its antibodies with a predominant IgG4 subclass lead to pathological lesions. Further studies could be performed to validate the clinical values of PLA2R-IgG, PLA2R-IgG4, and PLA2R-IgG4-to-IgG ratios, as ultrasensitive and quantitative immunoassays for PLA2R antibodies have been well established in our previous work. Methods. A cohort of 58 IMN patients, 30 of whom were followed from 3 to 42 months, was assessed for serum PLA2R-IgG and -IgG4 levels, and the ratio of PLA2R-IgG4/-IgG combined with relative clinicopathological indicators. Results. Serum PLA2R-IgG4 level was significantly correlated with glomerular PLA2R staining. In addition, it was strongly correlated with PLA2R-IgG and its ratio. PLA2R-IgG and -IgG4 levels were both correlated with high-density lipoprotein and erythrocyte sedimentation rates. The ratio at the first diagnosis can predict the remission, and its efficacy overmatched PLA2R-IgG4. In the survival curves, negative results for the ratio or PLA2R-IgG4 at the first diagnosis demonstrated higher remission rates. Conclusion. Serum PLA2R-IgG4 concentration may replace renal PLA2R immunohistochemistry in IMN diagnosis. We propose that the PLA2R-IgG4-to-IgG ratio and PLA2R-IgG4 could be novel indicators for remission prediction in clinical practice.