EUVIMEDEUVIMED entdecken
Scoping ReviewOpen Access

Automated Approaches of Text Simplification of Patient Education Materials: Scoping Review

Automatisierte Ansätze zur Textvereinfachung von Patient:innen-Informationsmaterialien: Scoping Review

Cornelia Krenn iD, Christine Loder iD, Natalie Berger iD, Klaus Jeitler iD, Thomas Semlitsch iD, Andrea Siebenhofer iD, Denise Wilfling iD

Journal of Medical Internet Research · 07.05.2026 · 28 · e88365

DOI: 10.2196/88365 ↗

Auf einen Blick

Das Scoping Review ordnet Studien zu KI-gestützter Textvereinfachung von Patient:innen-Informationsmaterialien ein. LLMs senkten die Textkomplexität, doch Inhaltsgenauigkeit und Verständlichkeit blieben unzureichend abgesichert.

Fragestellung

Welche Evidenz gibt es zu automatisierten Sprachverarbeitungstechnologien zur Vereinfachung von Patient:innen-Informationsmaterialien für Laien?

Methode

Scoping Review nach JBI und PRISMA-ScR; Suche in 5 Datenbanken von 2019 bis Mai 2025 plus Referenz- und Grauliteratursuche; thematische Synthese.

Ergebnisse

31 eingeschlossene Studien zu verschiedenen LLMs, darunter GPT-Serien, Gemini, Bard, Claude, Copilot und Llama. GPT-4.0 zeigte die konsistentesten Verbesserungen in Lesbarkeitsmaßen; die Ziel-RGL blieb jedoch schwierig.

Einschränkungen

Keine Risikof-bias-Bewertung; Verständlichkeit nur durch Expert:innen beurteilt; keine Studie prüfte sprachliche Korrektheit.

Schlussfolgerung der Autor:innen

Dies ist das erste Scoping Review zu automatisierten Technologien zur Textvereinfachung von PEMs. LLMs sollten derzeit nur assistiv eingesetzt werden; eine Expertenprüfung bleibt vor der Weitergabe erforderlich.

Kernaussagen

  • 31 Studien zu LLMs und anderen KI-Tools
  • GPT-4.0 verbesserte Lesbarkeitsmaße am konsistentesten
  • Inhaltsgenauigkeit und Laienverständlichkeit bleiben kritisch

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Scoping Review in der Zeitschrift Journal of Medical Internet Research, online erschienen am 07.05.2026. Verfasst von Cornelia Krenn und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute of General Practice and Evidence-based Health Services Research, Medical University of Graz, Graz, Austria. Hauptthemen laut MEDLINE: Patient Education as Topic, Artificial Intelligence, Automation. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 97 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Patient education materials (PEMs) often exceed the American Medical Association’s (AMA) recommended sixth-grade reading grade level (RGL). While artificial intelligence (AI) offers potential for automated text simplification, concerns persist regarding linguistic quality, content fidelity, and the understandability of simplified PEMs by laypeople.

Objective

This scoping review maps existing evidence on automated language processing technologies for simplifying PEMs for laypeople.

Methods

Following the Joanna Briggs Institute (JBI) methodology and the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guideline, 5 bibliographic databases (Ovid MEDLINE, Embase, CINAHL, PsycInfo, and IEEE Xplore) were systematically searched from 2019 to May 2025, supplemented by reference screening and gray literature searches. Eligible sources were peer-reviewed empirical studies published in English that examined large language models (LLMs), AI-supported writing assistants, AI-based conversational agents, or AI-supported tools designed for automatic text simplification of PEMs. Targeted outcomes included linguistic quality (ie, linguistic comprehensibility, linguistic correctness) and content fidelity (ie, factual accuracy, factual completeness) of simplified PEMs. Excluded sources comprised rule-based systems, manual text simplification, non-laypeople target groups, and technology-focused performance metrics. Results were synthesized via thematic analysis across the domains of targeted outcomes. In accordance with JBI methodology, a risk-of-bias assessment was not performed.

Results

A total of 31 eligible studies met the inclusion criteria, examining various LLMs, including OpenAI’s GPT series, Gemini, Bard, Claude, Copilot, and Llama. Specifically, GPT-4.0 achieved the most consistent improvements in standardized readability metrics (eg, the Flesch-Kincaid Grade Level [FKGL]). However, achieving predefined target RGLs remained challenging across all LLMs, particularly at lower RGLs. Findings on content fidelity were inconsistent: despite high content similarity scores, content accuracy was often compromised.

Conclusions

This is the first scoping review to comprehensively synthesize evidence on automated technologies for text simplification in PEMs. The review identified 2 critical validation gaps. First, no study examined the linguistic correctness (eg, grammar and typographical errors) of automatically simplified PEMs. Second, and most notably, the understandability of the simplified PEMs was assessed exclusively by experts, with no empirical evaluation involving laypeople. Although LLMs effectively reduce text complexity as measured by objective readability metrics, reliance on these formulas represents a critical limitation, as they serve merely as structural proxies. Improvements in readability do not guarantee the maintenance of content accuracy or laypeople’s understandability. Current evidence is further limited by the lack of systematic prompt quality evaluation and the predominant focus on English-language PEMs in US contexts, restricting generalizability. This review provides a foundation for future research by highlighting the need for validated evaluation frameworks that encompass layperson testing and content verification. For clinical practice, LLMs should currently serve as assistive tools, with mandatory expert review remaining essential to verify content fidelity before disseminating LLM-simplified PEMs to laypeople.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Patient Education as TopicArtificial IntelligenceAutomationHumansLarge Language Models

Stichwörter der Autor:innen

artificial intelligenceautomatic text simplificationcontent fidelitylarge language modelslinguistic qualitypatient education materials

Autor:innen und Institutionen

  • Institute of General Practice and Evidence-based Health Services Research, Medical University of Graz, Graz, Austria.
  • Institute for Medical Informatics, Statistics and Documentation, Medical University of Graz, Graz, Austria.
  • Institute of General Practice, Goethe University Frankfurt am Main, Frankfurt, Germany.
  • Institute of Nursing and Health Sciences, Medical University of Graz, Graz, Austria.

ORCID-Profile: Cornelia Krenn, Christine Loder, Natalie Berger, Klaus Jeitler, Thomas Semlitsch, Andrea Siebenhofer, Denise Wilfling

Zitieren

APA

Krenn, C., Loder, C., Berger, N., Jeitler, K., Semlitsch, T., Siebenhofer, A., & Wilfling, D. (2026). Automated Approaches of Text Simplification of Patient Education Materials: Scoping Review. Journal of Medical Internet Research, 28, e88365. https://doi.org/10.2196/88365

Vancouver

Krenn C, Loder C, Berger N, Jeitler K, Semlitsch T, Siebenhofer A, et al. Automated Approaches of Text Simplification of Patient Education Materials: Scoping Review. Journal of Medical Internet Research. 2026;28:e88365. doi:10.2196/88365

BibTeX
@article{Krenn2026,
  author = {Krenn, Cornelia and Loder, Christine and Berger, Natalie and Jeitler, Klaus and Semlitsch, Thomas and Siebenhofer, Andrea and Wilfling, Denise},
  title = {Automated Approaches of Text Simplification of Patient Education Materials: Scoping Review},
  journal = {Journal of Medical Internet Research},
  year = {2026},
  volume = {28},
  pages = {e88365},
  doi = {10.2196/88365}
}
Kostenlos starten →