EUVIMEDEUVIMED entdecken
Crossref

Leveraging Large Language Models to Enhance Patient Educational Resources in Rhinology

Ariana L Shaari iD, Rebecca A Ho iD, Annie Xu, Disha Patil iD, Lorik Berisha iD, Wayne D Hsueh

Annals of Otology, Rhinology & Laryngology · 2025

DOI: 10.1177/00034894251342969 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Annals of Otology, Rhinology & Laryngology, 2025. Verfasst von Ariana L Shaari und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Otolaryngology-Head & Neck Surgery, Rutgers New Jersey Medical School, Newark, New Jersey, USA. Hauptthemen laut MEDLINE: Patient Education as Topic, Comprehension, Otolaryngology, Language. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

To compare the readability of patient education materials (PEMs) on rhinologic conditions and procedures from the American Rhinologic Society (ARS) with those generated by large language models (LLMs).

Methods

Forty-one PEMs from the ARS were retrieved. Readability was assessed through the Flesch Kincaid Reading Ease (FKRE) and Flesch Kincaid Grade Level (FKGL), in which higher FKRE and lower FKGL scores indicate better readability. Three LLMs—ChatGPT 4.o, Google Gemini, and Microsoft Copilot—were then used to translate each ARS PEM to the recommended sixth-grade reading level. Readability scores were calculated and compared for each translated PEM.

Results

A total of 164 PEMs were evaluated, including 123 generated by LLMs. The original ARS PEMs had a mean FKGL of 10.28, while AI-generated PEMs demonstrated significantly better readability, with a mean FKGL of 8.6 ( P < .0001). Among the AI platforms, Gemini was the most easily readable, reaching a mean FKGL of 7.5 and FKRE of 65.5.

Conclusion

LLMs improved the readability of PEMs, potentially enhancing accessibility to medical information for diverse populations. Despite these findings, healthcare providers and patients should cautiously appraise LLM-generated content, particularly for rhinology conditions and procedures. Level of Evidence: N/A.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Patient Education as TopicComprehensionOtolaryngologyLanguageHumansUnited StatesHealth LiteracyLarge Language Models

Stichwörter der Autor:innen

artificial intelligenceclinical rhinologyhealth literacylarge language modelspatient carepatient education materialsrhinologysurgical education

Autor:innen und Institutionen

  • Department of Otolaryngology-Head & Neck Surgery, Rutgers New Jersey Medical School, Newark, New Jersey, USA.

ORCID-Profile: Ariana L Shaari, Rebecca A Ho, Disha Patil, Lorik Berisha

Zitieren

APA

Shaari, A. L., Ho, R. A., Xu, A., Patil, D., Berisha, L., & Hsueh, W. D. (2025). Leveraging Large Language Models to Enhance Patient Educational Resources in Rhinology. Annals of Otology, Rhinology & Laryngology. https://doi.org/10.1177/00034894251342969

Vancouver

Shaari AL, Ho RA, Xu A, Patil D, Berisha L, Hsueh WD. Leveraging Large Language Models to Enhance Patient Educational Resources in Rhinology. Annals of Otology, Rhinology & Laryngology. 2025. doi:10.1177/00034894251342969

BibTeX
@article{Shaari2025,
  author = {Shaari, Ariana L and Ho, Rebecca A and Xu, Annie and Patil, Disha and Berisha, Lorik and Hsueh, Wayne D},
  title = {Leveraging Large Language Models to Enhance Patient Educational Resources in Rhinology},
  journal = {Annals of Otology, Rhinology & Laryngology},
  year = {2025},
  doi = {10.1177/00034894251342969}
}
Kostenlos starten →