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.
Writing prior authorization (PA) letter is a time-consuming task. Surveys show 94% of physicians report PA-related delays, sometimes leading to serious adverse events, and 95% report burnout from the process. Large language model, such as ChatGPT, can facilitate this work. However, the quality AI-generated letters must be carefully assessed. We aim to evaluate the quality of PA letters drafted by ChatGPT-5 for commonly used medications requiring PA in Nephrology. Quality was evaluated based on correctness and strength of clinical reasoning.
We created a single standardized prompt and used in 29 different Nephrology scenarios to generate PA letters. Each PA letter was reviewed against four criteria: absence of false statements or hallucinations, correctness of ICD-10 coding, presence and validity of citations, and clinical reasoning, rated on a 4-point Likert scale (illogical, weak, adequate and strong). FDA drug labels, KDIGO guidelines and related randomized controlled trials were used as reference standards.
Across 29 letters, one letter (0.3%) contained false statements mentioning an irrelevant clinical trial. ICD-10 coding was correct in 23 letters (79.31%); most errors were related to CKD staging (stage 3a vs 3b) or to inconsistent definitions (one code with renal involvement and another code without). 27 letters (93.10%) cited valid references, with one letter citing an incorrect trial and another one citing a correct KDIGO guideline with inaccessible link. 26 of 29 letters (89.66%) has strong clinical reasoning, characterized by patient-specific, guideline or FDA label-aligned justifications. Three letters were categorized as adequate reasoning. Opportunity for improvement were citing relevant references and emphasizing special considerations eg. vaccination and REMS compliance for eculizumab.
ChatGPT-5 generated accurate PA letter draft with acceptable clinical reasoning, while errors were rare and most often related to citation validity and ICD-10 specificity.
