Authors: Zečević, Anđelka 
Ćulafić, Milica
Stojković, Stefan
Affiliations: Computer Science 
Mathematical Institute of the Serbian Academy of Sciences and Arts 
Title: On Simplification of Discharge Summaries in Serbian: Facing the Challenges
Journal: Workshop Proceedings
Conference: 1st Workshop on Patient-Oriented Language Processing, CL4Health 2024 at LREC-COLING 2024, Torino, Italy, 20 May 2024
Issue Date: 2024
ISBN: 978-2-493814-25-8
Abstract: 
The simplified information page (SIP) is a simplified discharge summary created to mitigate health risks caused by low medical comprehension. One of the most critical aspects of medical comprehension concerns interpreting medication instructions such as proper dosing, frequency, and duration. In our work, we examine the capacities of mainstream Large Language Models (LLMs) such as ChatGPT and Gemini to generate SIP-like medication-oriented pages based on the provided discharge summaries. We are sharing the initial qualitative assessments of our study based on a small collection of discharge summaries in Serbian, pointing to noticed inaccuracies, unfaithful content, and language quality. Hopefully, these findings might be helpful in addressing the multilingual perspective of patient-oriented language.
Keywords: discharge summary | LLMs | patient safety | text simplification
Publisher: European Language Resources Association (ELRA)

Show full item record

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.