Back
For best output, select "Paper Size" as "A4" and "Margin" as "0" or "None".
To save or print to PDF, please select Print Destination > Save as PDF, enable Background Graphics under "More Settings", then click "Save".
During the congress, E-Posters will be accessible to all participants on the congress website 24/7, as well as in the E-poster stations in the congress center.
Preparing your E-Poster
Please review the E-Poster format requirements carefully when preparing your E-Poster. Should your E-Poster not meet the mentioned requirements, it may not be displayed as described above.
E-Poster Submission Deadline
Please prepare and upload your E-Poster no later than March 14, 2026 11.59PM CET. After this date, you will no longer be able to prepare and upload your E-poster and it will not be displayed and accessible on the congress website.
Please follow the instructions below to input your abstract title.
Abstract titles should be brief and reflect the content of the abstract.
Primary membranous nephropathy (PMN) is the leading cause of adult nephrotic syndrome. Current risk stratification relies on six-month changes in proteinuria, estimated glomerular filtration rate (eGFR), and anti-phospholipase A2 receptor (PLA2R) antibody levels, lacks accurate baseline prognostic tools. We aimed to develop an early and precise subtyping system to identify heterogeneous PMN subgroups using machine learning.
We enrolled 1,109 biopsy-proven PMN adults from Southern China (2010-2022), with a follow-up of at least two years. The primary endpoint was end-stage renal disease (ESRD) or ≥50% eGFR decline. The secondary endpoint was all-cause mortality. Unsupervised hierarchical clustering (Ward’s method), principal component analysis, and decision tree modeling were employed to integrate key baseline features for subtype identification and validation.
Three distinct subtypes were identified: Cluster 1a (low-risk) had the mildest disease, frequent conservative treatment (41·3%), and the best prognosis(only 11.0% experienced primary endpoint, while 54.9% showed eGFR decline <20%). Cluster 2 (high-risk) featured oldest age, highest comorbidities, most severe pathology, most intensive immunosuppression (72·3%), and poorest prognosis (69.2%experienced primary endpoint, HR=3·538, 95%CI:1·803–6·943 vs. Cluster 1a). Cluster 1b (moderate-risk) showed nephrotic proteinuria, hyperlipidemia, intermediate clinicopathological severity, and poorer prognosis than Cluster 1a (HR=1·532, 95%CI:1·036–2·265). The new classification achieved 0·821 accuracy for the primary endpoint, outperforming conventional methods. A decision tree model incorporating eGFR, mean blood pressure (MBP), urine β2-microglobulin (β2M), glomerulosclerosis percentage, total protein (TP), fibrinogen (Fbg), and segmental glomerulosclerosis percentage achieved effective risk stratification, with Area Under the Curve (AUC) of 0·882 (training) and 0·856 (validation).
The three novel phenotypes identified by machine learning-based clustering demonstrated superior predictive performance compared to conventional methods. This approach enables accurate identification of heterogeneous PMN patients, thereby optimizing clinical decision-making and prognostic assessment.
