Assessment of ChatGPT-Generated Endodontic Patient Education Materi als: A Readability and Accuracy Analysis
Academia Journal of Medicine · 12.06.2026 · 9 (1) · 210-214
DOI: 10.48165/ajm.2026.9.01.43 ↗Kurz gefasst
Fachartikel in der Zeitschrift Academia Journal of Medicine, online erschienen am 12.06.2026. Verfasst von Perisetty Dinesh Kumar und 4 weiteren Autor:innen.
Themen: Selbstmanagement bei chronischen Erkrankungen, Künstliche Intelligenz in der Pflege
Abstract (Originalsprache)
Background
The increasing use of artificial intelligence–based conversational models such as ChatGPT has transformed the way patients access healthcare-related information. In endodontics, patients frequently seek online educational material regarding root canal treatment and related conditions. However, the readability and scientific accuracy of AI generated dental information remain uncertain.
Aim
To evaluate the readability and scientific accuracy of ChatGPT-generated patient education materials related to common endodontic conditions and procedures. Materials and Methods: A cross-sectional analytical study was conducted using 100 patient oriented responses generated by ChatGPT. Ten standardized endodontic prompts related to root canal treatment, dental abscess, infected teeth, post-treatment care, and treatment complications were entered ten separate times under identical settings. The generated responses were collected without modification. Readability assessment was performed using the Flesch Reading Ease Score, Flesch–Kincaid Grade Level, SMOG Index, and Gunning Fog Index. Scientific accuracy and quality of information were independently evaluated by three experienced endodontists using a structured 5-point Likert scale assessing accuracy, completeness, clarity, misleading information, and clinical usefulness. Statistical analysis was performed using descriptive statistics and Cohen’s kappa test for inter-examiner reliability.
Results
ChatGPT-generated educational materials demonstrated moderate to high readability, with most responses corresponding to a secondary school reading level. The majority of responses showed good scientific accuracy, clarity, and clinical usefulness. However, certain responses lacked comprehensive explanations regarding procedural complications and emergency management. Minor inconsistencies and oversimplified information were observed in selected outputs. Inter-examiner agreement among evaluators was high.
Conclusion
ChatGPT demonstrated promising potential in generating readable and reasonably accurate endodontic patient education materials. Nevertheless, professional verification by dental experts remains necessary before clinical use to ensure reliability and prevent dissemination of incomplete or misleading information.
Zitieren
APA
Kumar, P. D., Nahata, S., Bhatt, S., Sagar, S., & Rajan, M. (2026). Assessment of ChatGPT-Generated Endodontic Patient Education Materi als: A Readability and Accuracy Analysis. Academia Journal of Medicine, 9(1), 210-214. https://doi.org/10.48165/ajm.2026.9.01.43
Vancouver
Kumar PD, Nahata S, Bhatt S, Sagar S, Rajan M. Assessment of ChatGPT-Generated Endodontic Patient Education Materi als: A Readability and Accuracy Analysis. Academia Journal of Medicine. 2026;9(1):210-214. doi:10.48165/ajm.2026.9.01.43
BibTeX
@article{Kumar2026,
author = {Kumar, Perisetty Dinesh and Nahata, Shrenik and Bhatt, Sumit and Sagar, Sai and Rajan, Milind},
title = {Assessment of ChatGPT-Generated Endodontic Patient Education Materi als: A Readability and Accuracy Analysis},
journal = {Academia Journal of Medicine},
year = {2026},
volume = {9},
number = {1},
pages = {210--214},
doi = {10.48165/ajm.2026.9.01.43}
}
EUVIMED