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.
Calcific uremic arteriolopathy (CUA), also known as calciphylaxis, is a rare yet devastating vascular disorder that predominantly affects patients with chronic kidney disease (CKD), particularly those with end-stage kidney disease (ESKD) receiving dialysis. The disease progresses rapidly and is associated with an extremely poor prognosis, while effective therapeutic options remain limited. Consequently, early identification and timely intervention are critical to improving patient outcomes.
Currently, the diagnosis of CUA relies primarily on skin biopsy—a method hindered by its invasiveness, lengthy diagnostic process, and contraindications in patients with severe infection or coagulation abnormalities. These limitations often delay early diagnosis and appropriate management. To overcome this diagnostic gap, we developed and validated an interpretable machine learning model based on routine laboratory parameters and derived indices to predict the risk of CUA in hemodialysis patients. This model aims to facilitate the early recognition of high-risk individuals and provide data-driven support for clinical decision-making.
We retrospectively analyzed electronic medical records of hemodialysis patients diagnosed with CUA at Zhongda Hospital, Southeast University, between 2017 and 2025. Candidate predictors were screened using Least Absolute Shrinkage and Selection Operator (LASSO) regression followed by multivariate logistic regression. Seven machine learning classifiers were developed and compared. Model performance was comprehensively assessed using the area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, F1-score, calibration curves, and decision curve analysis. The optimal model was interpreted using SHapley Additive exPlanations (SHAP) values to enhance transparency and deployed as an interactive web-based prediction tool via the Heroku platform to assist clinical application.
A total of 444 hemodialysis patients were included, comprising 133 patients with CUA and 311 controls. Six key predictors were identified—history of secondary hyperparathyroidism, serum albumin, alkaline phosphatase, neutrophil-to-lymphocyte ratio (NLR), white blood cell count, and C-reactive protein (CRP). Among all models, the CatBoost-based classifier demonstrated the best performance, achieving an AUROC of 0.805 in the test cohort, with excellent calibration and clinical utility.
We established an interpretable, high-performing machine learning model for predicting calciphylaxis in hemodialysis patients using readily available clinical and laboratory data. This model enables early risk stratification, bridges the current diagnostic gap, and provides a valuable tool to support precision clinical decision-making in chronic kidney disease care.
