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.
Administrative health data has become increasingly vital for clinical research by enabling large-scale epidemiological investigations, health services evaluation, and medical risk prediction modeling. However, leveraging administrative data across local, provincial, and international platforms presents distinct challenges that are yet to be well-documented. Our work developing kidney failure risk prediction models has progressed from institutional research databases to provincial administrative health data at ICES (Ontario, Canada), and recently to Epic Cosmos, an international multi-center EHR data network. We present lessons learned to inform future administrative health data research in nephrology and beyond.
We documented data science workflows across three platforms: (1) a proprietary institutional research database with manually extracted EHR data, (2) linked administrative health data from ICES, and (3) Epic Cosmos (de-identified EHR international data, primarily comprising >1,500 U.S. health centers). For each platform, we documented access protocols, data characteristics, technological infrastructure, and challenges in defining kidney disease concepts. Issues concerning clinical, laboratory, data science, and statistics perspectives were synthesized into thematic insights.
Five main insights emerged. (1) Data quality and concept definition: Administrative data frequently requires proxy-based concept ascertainment (e.g., kidney failure) rather than direct clinical observation, introducing systematic constraints and often necessitating algorithmic solutions. (2) Computation and workflow optimization: Processing inefficiencies during cohort assembly frequently delayed analyses and prohibited rapid experiment repetition or modification; most were addressed through platform specific program optimization and staged processing. (3) Level of support: Successful platform navigation required expertise from nephrology, laboratory medicine, epidemiology, data architecture, and data science, with platforms exhibiting variability in the level of support provided across these domains. (4) Data provenance versus technological accessibility: Platforms presented a trade-off between well-validated and traceable data sources versus modern and flexible research infrastructure. (5) Technological ecosystem transitions: Legacy systems frequently conflicted with contemporary technology stacks, generating friction in research workflows.
Administrative data can offer substantial advantages in scale, structure, and quality, but our experience revealed a lack of standardization across databases that complicates reproducing research. For nephrologists embarking on similar work, we recommend early engagement with data science collaborators, realistic timeline planning, and investment in computational infrastructure. These insights may help guide standardization of administrative data for scalable, reproducible nephrology research enabling more rapid development and validation of medical risk prediction models and population health.
