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.
Diabetic Kidney Disease (DKD) is a broad range of renal impairments associated with diabetes mellitus and accounts for about 50% of end-stage renal disease (ESRD), imposing a substantial burden on both patients and society due to the need for regular dialysis therapy. The prognosis for DKD that has progressed to ESRD is poor, and kidney transplantation remains the only curative treatment for ESRD. Therefore, early prevention and treatment of DKD are of utmost importance. While the classical trajectory of DKD has been based on gradual renal decline, new clinical portraits like Rapid Decliner, which is the fast aggravation even in short period, have increased, and the prevention of DKD exacerbations requires the assessment of such atypical cases. While the previous predictions of changes in renal function targeted the traditional clinical picture, no prognostic models considering clinical divergence (i.e., sequential short-term shifts in renal function) have been reported. The purpose of this study is to develop high-precision prognosis prediction based on time-series models reflecting heterogeneous progression especially for DKD.
We integrated health examination data, including urine tests, collected from three clinics and tracked about 10,000 patients over 20 years. We constructed a time-series model based on Transformer architecture targeting the rate of decline in kidney function (eGFR slope). The eGFR slope was calculated based on changes over 2 or 3 year period.
This study targeted 9645 patients and extracted those with mild stages (G1 and G2 at baseline). We evaluated the predictive performance of eGFR slope using metrics like Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE), and clarified key contributors to predict renal function prognosis and features of atypical cases (i.e., Rapid Decliner) from blood test items.
Our study proposed the prediction for renal decline considering heterogeneous trajectory adapting to dynamic changes sequentially.
