Primary membranous nephropathy in the era of autoantibodies and biological therapies

Establishing a differential diagnosis model between primary membranous nephropathy and non-primary membranous nephropathy by machine learning algorithms

CONTEXT

Four algorithms with relatively balanced complexity and accuracy in deep learning classification algorithm were selected for differential diagnosis of primary membranous nephropathy (PMN).

OBJECTIVE

This study explored the most suitable classification algorithm for PMN identification, and to provide data reference for PMN diagnosis research.

METHODS

A total of 500 patients were referred to Luo-he Central Hospital from 2019 to 2021. All patients were diagnosed with primary glomerular disease confirmed by renal biopsy, contained 322 cases of PMN, the 178 cases of non-PMN. Using the decision tree, random forest, support vector machine, and extreme gradient boosting (Xgboost) to establish a differential diagnosis model for PMN and non-PMN. Based on the true positive rate, true negative rate, false-positive rate, false-negative rate, accuracy, feature work area under the curve (AUC) of subjects, the best performance of the model was chosen.

RESULTS

The efficiency of the Xgboost model based on the above evaluation indicators was the highest, which the diagnosis of PMN of the sensitivity and specificity, respectively 92% and 96%.

CONCLUSIONS

The differential diagnosis model for PMN was established successfully and the efficiency performance of the Xgboost model was the best. It could be used for the clinical diagnosis of PMN.

THSD7A as a Promising Biomarker for Membranous Nephrosis

Membranous nephropathy (MN) is an autoimmune disease of the kidney glomerulus and one of the leading causes of nephrotic syndrome. The disease exhibits heterogeneous outcomes with approximately 30% of cases progressing to end-stage renal disease. Traditionally, the standard approach of diagnosing MN involves performing a kidney biopsy. Nevertheless, kidney biopsy is an invasive procedure that poses risks for the patient including bleeding and pain, and bears greater costs for the health system. The clinical management of MN has steadily advanced owing to the identification of autoantibodies to the phospholipase A2 receptor (PLA2R) in 2009 and thrombospondin domain-containing 7A (THSD7A) in 2014 on the podocyte surface. At present, serum anti-PLA2R antibody detection and glomerular PLA2R antigen staining have been used for clinical diagnosis and prognosis, but the related detection of THSD7A has not been widely used in clinical practice. Here, we summarized the emerging knowledge regarding the roles THSD7A plays in MN and its clinical implications as diagnostic, prognostic, and therapeutic response as well as Methods for detecting serum THSD7A antibodies.