EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Decoupled quality and readability in skin cancer education from large language models

Yanping Zhang, Lei Wang, Weiqiang Zhang, Weifeng Lan

Frontiers in Public Health · 20.02.2026 · 14

DOI: 10.3389/fpubh.2026.1777577 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Public Health, online erschienen am 20.02.2026. Verfasst von Yanping Zhang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Plastic Surgery, Longyan First Affiliated Hospital of Fujian Medical University, Longyan, China. Hauptthemen laut MEDLINE: Large Language Models, Comprehension, Skin Neoplasms, Patient Education as Topic. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Large language models (LLMs) are increasingly used by the public to obtain health information, yet the relationship between content quality and readability in LLM-generated patient education remains unclear.

Methods

We benchmarked five LLMs (Doubao, DeepSeek, Wenxin Yiyan, Tongyi Qianwen, and GPT-5) using an identical set of 20 Mandarin Chinese skin-cancer FAQs (100 total outputs). Quality was assessed using c-PEMAT-P and the Global Quality Scale (GQS), and readability was assessed using seven indices (ARI, FRES, GFOG, FKGL, CL, SMOG, and LW). Group differences and correlations were evaluated with appropriate statistical tests.

Results

Models showed comparable understandability/actionability (c-PEMAT-P), while overall quality (GQS) differed, with GPT-5 scoring highest. Readability varied substantially by both model and content category, and no single model performed best across all readability metrics. Correlation analyses indicated that quality and readability were largely decoupled.

Discussion

High-quality outputs do not necessarily have high readability. Optimizing AI-generated skin-cancer education requires multi-faceted strategies that jointly consider model choice and content topic.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsComprehensionSkin NeoplasmsPatient Education as TopicHealth LiteracyHumansChina

Stichwörter der Autor:innen

digital public health communicationhealth information quality (C-PEMAT, GQS)large language models (LLMs)readability assessmentskin cancer education

Autor:innen und Institutionen

  • Department of Plastic Surgery, Longyan First Affiliated Hospital of Fujian Medical University, Longyan, China.
  • Department of Science and Education, Longyan First Hospital, Longyan, China.

Zitieren

APA

Zhang, Y., Wang, L., Zhang, W., & Lan, W. (2026). Decoupled quality and readability in skin cancer education from large language models. Frontiers in Public Health, 14. https://doi.org/10.3389/fpubh.2026.1777577

Vancouver

Zhang Y, Wang L, Zhang W, Lan W. Decoupled quality and readability in skin cancer education from large language models. Frontiers in Public Health. 2026;14. doi:10.3389/fpubh.2026.1777577

BibTeX
@article{Zhang2026,
  author = {Zhang, Yanping and Wang, Lei and Zhang, Weiqiang and Lan, Weifeng},
  title = {Decoupled quality and readability in skin cancer education from large language models},
  journal = {Frontiers in Public Health},
  year = {2026},
  volume = {14},
  doi = {10.3389/fpubh.2026.1777577}
}
Kostenlos starten →