EUVIMEDEUVIMED entdecken
Vergleichsstudie

A Comparative Assessment of Large Language Models in Pediatric Dialysis: Reliability, Quality and Readability

Esra Ensari iD, Esra Nagehan Akyol Onder iD, Pelin Ertan iD

Therapeutic Apheresis and Dialysis · 2025-10 · 29 (5) · 739-746

DOI: 10.1111/1744-9987.70058 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Therapeutic Apheresis and Dialysis, online erschienen am 24.06.2025. Verfasst von Esra Ensari und 2 weiteren Autor:innen. Beteiligte Einrichtung: Ministry of Health Antalya City Hospital, Department of Pediatric Nephrology, Antalya, Turkey. Hauptthemen laut MEDLINE: Comprehension, Renal Dialysis, Language. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 44 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

This study evaluated the reliability, quality, and readability of ChatGPT (OpenAI, San Francisco, CA), Gemini (Google, Mountain View, CA), and Copilot (Microsoft Corp., Washington, DC) which are among the most widely used large language models (LLMs) today in answering frequently asked questions (FAQs) related to pediatric dialysis.

Methods

A total of 45 FAQs were entered into LLM. The Modified DISCERN (mDISCERN) scale assessed reliability; the Global Quality Score (GQS) evaluated quality; and readability was assessed using five metrics: Coleman‐Liau Index (CLI), Simple Measure of Gobbledygook (SMOG), Gunning Fog Index (GFI), Flesch Reading Ease (FRE) and Flesch–Kincaid Grade Level (FKGL). Questions were directed to the chat robots twice, on January 25, 2025, and February 1, 2025.

Results

All three chatbots displayed high reliability, achieving median mDISCERN scores of 5. Quality scores on the GQS were similarly high, with median scores of 5 across platforms; however, Gemini exhibited greater variability (range 1–5) compared to ChatGPT‐4o and Copilot (ranges 3–5). Readability scores revealed that chatbot responses were written at an advanced level.

Conclusion

This study found that LLMs responses to dialysis FAQs were reliable and high quality, but difficult to read; improving readability through expert‐reviewed content could increase their impact on public health.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ComprehensionRenal DialysisLanguageHumansReproducibility of ResultsChildSurveys and QuestionnairesLarge Language Models

Stichwörter der Autor:innen

artificial intelligencechilddialysislarge language model

Autor:innen und Institutionen

  • Ministry of Health Antalya City Hospital, Department of Pediatric Nephrology, Antalya, Turkey.
  • Aksaray University Hospital, Department of Pediatric Nephrology, Aksaray, Turkey.
  • Manisa Celal Bayar University, School of Medicine, Department of Pediatric Nephrology, Manisa, Turkey.

ORCID-Profile: Esra Ensari, Esra Nagehan Akyol Onder, Pelin Ertan

Zitieren

APA

Ensari, E., Onder, E. N. A., & Ertan, P. (2025). A Comparative Assessment of Large Language Models in Pediatric Dialysis: Reliability, Quality and Readability. Therapeutic Apheresis and Dialysis, 29(5), 739-746. https://doi.org/10.1111/1744-9987.70058

Vancouver

Ensari E, Onder ENA, Ertan P. A Comparative Assessment of Large Language Models in Pediatric Dialysis: Reliability, Quality and Readability. Therapeutic Apheresis and Dialysis. 2025;29(5):739-746. doi:10.1111/1744-9987.70058

BibTeX
@article{Ensari2025,
  author = {Ensari, Esra and Onder, Esra Nagehan Akyol and Ertan, Pelin},
  title = {A Comparative Assessment of Large Language Models in Pediatric Dialysis: Reliability, Quality and Readability},
  journal = {Therapeutic Apheresis and Dialysis},
  year = {2025},
  volume = {29},
  number = {5},
  pages = {739--746},
  doi = {10.1111/1744-9987.70058}
}
Kostenlos starten →