A Weakly Supervised Multimodal Framework Integrating IgA Immunofluorescence Patterns and Clinical Features for Prognostic Prediction in IgA Nephropathy

Certificate Output Instructions

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".

Presented the abstract " "
(Abstract co-author(s): )

Back

E-Poster Presentation

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.

E-Poster Format Requirements

PDF file
Layout: Portrait (vertical orientation)
One page only (Dim A4: 210 x 297mm or PPT)
E-Poster can be prepared in PowerPoint (one (1) PowerPoint slide) but must be saved and submitted as PDF file.
File Size: Maximum file size is 2 Megabytes (2 MB)
No hyperlinks, animated images, animations, and slide transitions
Language: English
Include your abstract number
E-posters can include QR codes, tables and photos

E-Poster

Abstract Title *

A Weakly Supervised Multimodal Framework Integrating IgA Immunofluorescence Patterns and Clinical Features for Prognostic Prediction in IgA Nephropathy

Please follow the instructions below to input your abstract title.

Abstract titles should be brief and reflect the content of the abstract.

The title will not be accepted if it exceeds 25 words.
Type in CAPITAL LETTERS.
Lowercase may be used for abbreviations only, for example, mRNA.

Co-author 1

Sai Pan pansai301@126.com First Medical Center of Chinese People’s Liberation Army General Hospital Department of Nephrology Beijing China *

Co-author 2

Conghui Wang nilv120@hotmail.com First Medical Center of Chinese People’s Liberation Army General Hospital Department of Nephrology Beijing China -

Co-author 3

Co-author 4

Co-author 5

Co-author 6

Co-author 7

Co-author 8

Co-author 9

Co-author 10

Co-author 11

Co-author 12

Co-author 13

Co-author 14

Co-author 15

Introduction

IgA nephropathy (IgAN), characterized by mesangial IgA deposition, exhibits heterogeneous progression to kidney failure, necessitating refined prognostic tools. Current models overlook IgA deposition patterns, which may reflect disease activity. This study addresses this gap by developing a multimodal framework combining IgA immunofluorescence (IF) images and clinical data to enhance risk stratification.

Methods

A retrospective-prospective cohort of 488 biopsy-confirmed patients with IgAN (2013–2024) was analyzed. IF images were segmented into patches, processed via ResNet18, and integrated with clinical variables, such as Oxford Classification proteinuria, using dual multi-instance learning pipelines. A Lasso-Cox model fused IF histopathological features (patch labels and probabilities) and clinical parameters to predict survival outcomes (ESRD or >50% eGFR decline)

Results

The multimodal model achieved a C-index of 0.888, surpassing the unimodal IF model (C-index: 0.757) and IgAN international risk tool (C-index: 0.816). The time-dependent analysis demonstrated superior 5- and 7-years area under the curve (0.940 and 0.901, respectively) compared to that of IF-only models (0.740 and 0.793). Kaplan–Meier analysis confirmed significant risk stratification (log-rank P <0.001), with high-risk groups showing accelerated renal function decline

Conclusion

This study establishes a novel framework that quantifies glomerular IgA deposition patterns and integrates them with clinical metrics to predict IgAN progression. The model’s robustness and accuracy highlight the prognostic value of IgA spatial distribution, advocating for its integration into clinical workflows to guide personalized therapy. Future multicenter validation is warranted to address potential biases in staining protocols and enhance generalizability.

Kewords