EUVIMEDEUVIMED entdecken
Open Access

Leveraging Large Language Models to Improve the Readability of German Online Medical Texts: Evaluation Study

Amela Miftaroski, Richard Zowalla, Martin Wiesner, Monika Pobiruchin

JMIR AI · 23.01.2026 · 5 · e77149-e77149

DOI: 10.2196/77149 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR AI, online erschienen am 23.01.2026. Verfasst von Amela Miftaroski und 3 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Informatics, Heilbronn University, Max-Planck-Str. 39, Heilbronn, 74081, Germany, 49 7131 504 ext 633. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Patient education materials (PEMs) found online are often written at a complexity level too high for the average reader, which can hinder understanding and informed decision-making. Large language models (LLMs) may offer a solution by simplifying complex medical texts. To date, little is known about how well LLMs can handle simplification tasks for German-language PEMs.

Objective

The study aims to investigate whether LLMs can increase the readability of German online medical texts to a recommended level.

Methods

A sample of 60 German texts originating from online medical resources was compiled. To improve the readability of these texts, four LLMs were selected and used for text simplification: ChatGPT-3.5, ChatGPT-4o, Microsoft Copilot, and Le Chat. Next, readability scores (Flesch reading ease [FRE] and Wiener Sachtextformel [4th Vienna Formula; WSTF]) of the original texts were computed and compared to the rephrased LLM versions. A Student t test for paired samples was used to test the reduction of readability scores, ideally to or lower than the eighth grade level.

Results

Most of the original texts were rated as difficult to quite difficult (average WSTF 11.24, SD 1.29; FRE 35.92, SD 7.64). On average, the LLMs achieved the following average scores: ChatGPT-3.5 (WSTF 9.96, SD 1.52; FRE 45.04, SD 8.62), ChatGPT-4o (WSTF 10.6, SD 1.37; FRE 39.23, SD 7.45), Microsoft Copilot (WSTF 8.99, SD 1.10; FRE 49.0, SD 6.51), and Le Chat (WSTF 11.71, SD 1.47; FRE 33.72, SD 8.58). ChatGPT-3.5, ChatGPT-40, and Microsoft Copilot showed a statistically significant improvement in readability. However, the t tests yielded no statistically significant results for the reduction of scores lower than the eighth grade level.

Conclusions

LLMs can improve the readability of PEMs in German. This moderate improvement can support patients reading PEMs online. LLMs demonstrated their potential to make complex online medical text more accessible to a broader audience by increasing readability. This is the first study to evaluate this for German online medical texts.

Schlagwörter

Stichwörter der Autor:innen

AILLMartificial intelligencehealth informationlarge language modelspatient education materialreadability

Autor:innen und Institutionen

  • Faculty of Informatics, Heilbronn University, Max-Planck-Str. 39, Heilbronn, 74081, Germany, 49 7131 504 ext 633.
  • Research and Innovation Center for Cognitive Service Systems (KODIS), Fraunhofer Institute for Industrial Engineering, Stuttgart, Germany.
  • Consumer Health Informatics Special Interest Group, German Association for Medical Informatics, Biometry and Epidemiology (GMDS) e.V., Cologne, Germany.

Zitieren

APA

Miftaroski, A., Zowalla, R., Wiesner, M., & Pobiruchin, M. (2026). Leveraging Large Language Models to Improve the Readability of German Online Medical Texts: Evaluation Study. JMIR AI, 5, e77149-e77149. https://doi.org/10.2196/77149

Vancouver

Miftaroski A, Zowalla R, Wiesner M, Pobiruchin M. Leveraging Large Language Models to Improve the Readability of German Online Medical Texts: Evaluation Study. JMIR AI. 2026;5:e77149-e77149. doi:10.2196/77149

BibTeX
@article{Miftaroski2026,
  author = {Miftaroski, Amela and Zowalla, Richard and Wiesner, Martin and Pobiruchin, Monika},
  title = {Leveraging Large Language Models to Improve the Readability of German Online Medical Texts: Evaluation Study},
  journal = {JMIR AI},
  year = {2026},
  volume = {5},
  pages = {e77149--e77149},
  doi = {10.2196/77149}
}
Kostenlos starten →