EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access

Evaluating the Effectiveness of Generative AI for the Creation of Patient Education Materials on Coronary Heart Disease: A Comparative Study

Bewertung der Wirksamkeit generativer KI zur Erstellung von Patienteninformationsmaterial zu koronarer Herzkrankheit: Vergleichsstudie

Xiaofang Jiang iD, Jingbang Liu iD, Shanshan Dai iD, Xiawen Mao iD, Rongping Cha iD, Lili Wu iD

JMIR Formative Research · 21.11.2025 · 9 · e78816-e78816

DOI: 10.2196/78816 ↗

Auf einen Blick

Generative KI verkürzte die Erstellung von Patienteninformationsmaterial zu koronarer Herzkrankheit deutlich. Die Lesbarkeit, Verständlichkeit und Handlungsorientierung waren ähnlich wie bei Materialien eines professionellen Teams.

Fragestellung

Wie effektiv sind ChatGPT-4o und DeepSeek R1 für die Erstellung von Patienteninformationsmaterial zu koronarer Herzkrankheit im Vergleich zu einem professionellen medizinischen Team?

Methode

Vergleichsstudie; Erstellung von PEMs im Februar 2025 durch ein professionelles Team sowie mit ChatGPT-4o und DeepSeek R1; Vergleich von Entwicklungszeit, Lesbarkeit, Verständlichkeit, Handlungsorientierung und Genauigkeit.

Ergebnisse

Manuelle Erstellung: 14 Stunden; ChatGPT: 0,62 Stunden; DeepSeek: 0,78 Stunden. Keine signifikanten Unterschiede bei Verständlichkeit und Handlungsorientierung. Bei der Genauigkeit intergruppale Unterschiede (H =7,27; P =.03), aber keine signifikanten Paarvergleiche.

Einschränkungen

4 von 8 Expert:innen bemerkten Genauigkeitsprobleme in den KI-Materialien; mögliche KI-„Halluzinationen“ wurden genannt.

Schlussfolgerung der Autor:innen

Generative KI verbesserte die Effizienz der Erstellung von Patienteninformationsmaterial zu CHD deutlich. Die KI-Texte waren hinsichtlich Lesbarkeit, Verständlichkeit und Handlungsorientierung mit professionell erstellten Materialien vergleichbar; Genauigkeit bleibt ein Problem.

Kernaussagen

  • Erstellung: 14 Stunden manuell vs. 0,62/0,78 Stunden mit KI
  • Keine signifikanten Unterschiede bei Verständlichkeit und Handlungsorientierung
  • Genauigkeit der KI-Materialien bleibt 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

Vergleichsstudie in der Zeitschrift JMIR Formative Research, online erschienen am 21.11.2025. Verfasst von Xiaofang Jiang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Nursing Department, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, 3 East Qingchun Road, Hangzhou, Zhejiang Province, 310000, Chi…. Hauptthemen laut MEDLINE: Patient Education as Topic, Artificial Intelligence, Coronary Disease, Teaching Materials. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Generative artificial intelligence (AI) has shown great potential in various fields, including health care. However, its application for developing patient education materials (PEMs), particularly for those with coronary heart disease (CHD), remains underexplored. Traditional methods for creating these materials are time-consuming and lack personalization, which limit their effectiveness.

Objective

This study aims to explore the effectiveness of generative AI tools (ChatGPT and DeepSeek) at generating PEMs for patients with CHD and to compare them with materials developed by a professional medical team.

Methods

In February 2025, PEMs for patients with CHD were developed using a framework designed by a professional medical team. Structured prompts were used to generate materials through 2 generative AI models—ChatGPT-4o and DeepSeek R1. These AI-generated materials were compared with those created by the medical team in terms of development time, readability, understandability, actionability, and accuracy.

Results

The total time for manual preparation was 14 hours, while ChatGPT and DeepSeek consumed 0.62 hours and 0.78 hours, respectively. Regarding readability, the frequency of difficult words was more variable in manually written and ChatGPT materials, while DeepSeek showed more consistency. The proportion of simple sentences was highest with DeepSeek, followed by ChatGPT, with complete separation between manually written and ChatGPT ( δ =1). Content word frequency was highest in manually written PEMs, while ChatGPT had the lowest but most stable values. Personal pronouns were most frequently used in manually written PEMs, with high variability, and least used in DeepSeek, which was stable. All 3 methods had similar readability levels and reached Chinese elementary school–level readability for the proportions of simple sentences and personal pronouns, with high school–level difficulty of words and content word frequency. The understandability and actionability scores were above 70, with ChatGPT being more stable for understandability and DeepSeek being more stable for actionability. No significant differences were found between groups. In terms of accuracy, intergroup comparisons showed significant differences ( H =7.27, P =.03) but no significant differences in multiple comparisons. The direct comparison between ChatGPT and DeepSeek showed a negligible effect size ( δ =0.02), with no significant difference ( z -score=−0.06, P =.96). Accuracy issues in the AI-generated materials were noted by 4 of 8 experts.

Conclusions

Generative AI significantly improved the efficiency of developing PEMs for patients with CHD. The materials generated by ChatGPT-4o and DeepSeek R1 were comparable to the professionally written ones in terms of readability, understandability, and actionability. However, improvements related to reducing the number of difficult words and increasing content word frequency are needed to enhance readability. The accuracy of AI-generated materials still poses concerns, including potential AI “hallucinations,” and requires review by health care professionals. Generative AI holds considerable potential for generating PEMs, and future research should assess its applicability and effectiveness in real-world patient and family contexts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Patient Education as TopicArtificial IntelligenceCoronary DiseaseTeaching MaterialsHumansComprehensionMaleFemaleHealth Literacy

Stichwörter der Autor:innen

ChatGPTDeepSeekcoronary heart diseasegenerative artificial intelligencelarge language modelspatient education

Autor:innen und Institutionen

  • Nursing Department, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, 3 East Qingchun Road, Hangzhou, Zhejiang Province, 310000, China, 86 13777392684.

ORCID-Profile: Xiaofang Jiang, Jingbang Liu, Shanshan Dai, Xiawen Mao, Rongping Cha, Lili Wu

Zitieren

APA

Jiang, X., Liu, J., Dai, S., Mao, X., Cha, R., & Wu, L. (2025). Evaluating the Effectiveness of Generative AI for the Creation of Patient Education Materials on Coronary Heart Disease: A Comparative Study. JMIR Formative Research, 9, e78816-e78816. https://doi.org/10.2196/78816

Vancouver

Jiang X, Liu J, Dai S, Mao X, Cha R, Wu L. Evaluating the Effectiveness of Generative AI for the Creation of Patient Education Materials on Coronary Heart Disease: A Comparative Study. JMIR Formative Research. 2025;9:e78816-e78816. doi:10.2196/78816

BibTeX
@article{Jiang2025,
  author = {Jiang, Xiaofang and Liu, Jingbang and Dai, Shanshan and Mao, Xiawen and Cha, Rongping and Wu, Lili},
  title = {Evaluating the Effectiveness of Generative AI for the Creation of Patient Education Materials on Coronary Heart Disease: A Comparative Study},
  journal = {JMIR Formative Research},
  year = {2025},
  volume = {9},
  pages = {e78816--e78816},
  doi = {10.2196/78816}
}
Kostenlos starten →