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.
Large language models (LLMs) such as ChatGPT, Claude, and DeepSeek are increasingly used by medical residents. Their ability to provide rapid, comprehensive responses has raised the question of whether they may substitute or complement traditional tutoring. However, while LLMs can generate what may seem as comprehensive information rapidly, it is not clear if their outputs can deliver the basic clinical concepts that are essential for safe clinical practice as clinical tutors usually provide. This gap may be particularly more evident in highly specialized areas of medicine as dialysis, where applying theoretical knowledge to clinical decision-making is critical. To date, few studies have examined whether information gained from LLMs translates into clinically usable judgment compared with tutor-led instruction. None have assessed that in learning Dialysis. This study aims evaluate the extent to which medical residents are able to apply knowledge gained from LLMs versus a human tutor when confronted with dialysis-related clinical scenarios.
We conducted a prospective educational study with six internal medicine residents with limited previous exposure to dialysis. Each resident was handed two sets of dialysis-related questions: Tutor set (T): 5 questions on core principles (e.g., intradialytic hypotension, dialysate sodium, anemia management, infection prevention).LLM set (L): 5 questions on applied clinical management (e.g., recurrent hyperkalemia, PD–HD transition, AV fistula dysfunction, dialysis adequacy, uremic pruritus). Residents were given time to read through the questions meant for the LLM. Following that they were given the same amount of time to be with the clinical tutor who would teach them about core concept related to the second set of questions. Residents then completed a 10-scenario multiple-choice test (S1–S10), with each scenario mapped to either a Tutor or LLM-derived question.
There was no difference in mean Clinical performance between Tutor and LLM-linked scenarios.
We conclude that LLMs can lead to safe translation of basic clinical concepts. However,further studies with more complex concepts and more complicated clinical scenarios may be more helpful. Future studies with larger sample size and increased number of items tested over a longer period of time are rapidly needed to help understand the role LLms can provide when it comes to medical education and the safe translation of concepts learned into clinical practice.
