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.
Competing risk modeling is essential in renal transplantation, as it captures the interplay and dynamics of adverse transplant outcomes, such as graft failure and death with a functioning graft. The accurate prediction of these risks is crucial for identifying high-risk patients and optimizing clinical management strategies. This study aimed to develop and compare the performance of statistical and machine learning models in predicting these competing risks, ultimately enhancing clinical decision-making for transplant recipients.
Data were collected from a retrospective cohort of renal transplant recipients at the Ethiopian National Kidney Transplant Center between 2015 and 2022. Various machine learning models, including Random Survival Forest for Competing Risk (RSFCR) and Cox Boost for Competing Risk (CBCR), and statistical models, such as cause-specific hazard and Fine-Gray sub-distributional hazard models, were employed to analyze the competing transplant outcomes. Methodological strategies, such as inverse probability weighting imbalance handling and cross-validation techniques, were utilized to ensure robust model validation and to enhance the reliability of the findings.
The median graft survival time was 33 months, with 3-month, 1-year, and 3-year survival rates of 0.969, 0.939, and 0.898, respectively. The cumulative incidence of graft failure was 9.4%, whereas the cumulative incidence of death with a functioning graft was 8.2%. Key findings indicate that blood urea nitrogen levels, tacrolimus metabolism rates, and rejection episodes are significant predictors of renal graft failure. In contrast, cardiovascular complications, the number of post-transplant admissions, and tacrolimus metabolism rates are significant predictors of death with a functioning graft. The random survival forest for competing risks showed outstanding predictive performance; however, its complexity highlights the need for ongoing efforts, such as developing user-friendly interfaces, to enhance its interpretability for clinicians.
This study emphasizes the need for accurate prediction of the competing risks of graft failure and death in renal transplant recipients. Although machine learning models show strong predictive performance, statistical models offer valuable interpretability. Integrating these findings into clinical practice can help clinicians tailor monitoring and therapeutic strategies for transplant recipients.
