ChatGPT jako skuteczne narzędzie do upraszczania dokumentacji medycznej? Próba oceny wykorzystania sztucznej inteligencji do tłumaczenia zaleceń lekarskich na prosty język

With the increasing importance of AI in the daily lives of many citizens, the study examined the potential of using ChatGPT to simplify medical recommendations contained in treatment information sheets. The analysis aims at determining whether ChatGPT-generated medical recommendations based on authentic medical recommendatoons from 20 discharge cards are more understandable to the average patient and whether they follow the principles of plain medical language. The comprehensibility level of the texts was checked using the Jasnopis application. The individual features of the simplified texts were examined based on the scientific recommendations for plain medical language. The study has shown that medical recommendations can be significantly simplified with the help of ChatGPT; however, the simplified texts do not fully comply with the principles of plain medical language, e.g., with regard to specialised terminology.

Authors

Institutions

Publication Details

Journal
Poradnik Językowy
Published
2025-03-28
DOI
https://doi.org/10.33896/porj.2025.2.2
Primary Topic
Text Readability and Simplification
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

ChatGPT jako skuteczne narzędzie do upraszczania dokumentacji medycznej? Próba oceny wykorzystania sztucznej inteligencji do tłumaczenia zaleceń lekarskich na prosty język

Magdalena Łomzik
Poradnik Językowy
Text Readability and Simplification
article

ChatGPT jako skuteczne narzędzie do upraszczania dokumentacji medycznej? Próba oceny wykorzystania sztucznej inteligencji do tłumaczenia zaleceń lekarskich na prosty język

Magdalena Łomzik
article en

Abstract

With the increasing importance of AI in the daily lives of many citizens, the study examined the potential of using ChatGPT to simplify medical recommendations contained in treatment information sheets. The analysis aims at determining whether ChatGPT-generated medical recommendations based on authentic medical recommendatoons from 20 discharge cards are more understandable to the average patient and whether they follow the principles of plain medical language. The comprehensibility level of the texts was checked using the Jasnopis application. The individual features of the simplified texts were examined based on the scientific recommendations for plain medical language. The study has shown that medical recommendations can be significantly simplified with the help of ChatGPT; however, the simplified texts do not fully comply with the principles of plain medical language, e.g., with regard to specialised terminology.

Poradnik Językowy(2/2025(821))
Uniwersytet Komisji Edukacji Narodowej w Krakowie (PL)
Openalex Percentile: Top 97%
Text Readability and Simplification
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.