Accuracy of Artificial Intelligence Chatbots Versus Endodontic Residents in Regenerative Endodontic Treatment Knowledge
European Journal of Therapeutics · 11.05.2026
DOI: 10.58600/eurjther3013 ↗Kurz gefasst
Fachartikel in der Zeitschrift European Journal of Therapeutics, online erschienen am 11.05.2026. Verfasst von Merve Gökyar und 2 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Objective
This cross-sectional study aimed to compare the accuracy of artificial intelligence (AI)-based chatbots and endodontic residents regarding their knowledge of regenerative endodontic treatment (RET).
Methods
A 30-item true/false questionnaire was completed by 128 residents (1st–3rd year). The same questions were asked to ChatGPT-4o (OpenAI) and Gemini Advanced (Google DeepMind) in independent chat sessions. Each question was asked twice daily for 10 consecutive days to obtain multiple AI responses. Accuracy rates and group differences were analyzed using the Kruskal–Wallis test with Bonferroni adjustment; agreement was assessed with Fleiss’ Kappa.
Results
AI models demonstrated higher accuracy rates than residents overall (ChatGPT-4o = 82.3%, Gemini Advanced = 83.7%, Residents = 76.3%). Gemini scored significantly higher than all resident groups, while ChatGPT-4o exceeded first-year residents. Residents showed weak consistency (κ = 0.190–0.319), whereas ChatGPT-4o demonstrated substantial agreement (κ = 0.689).
Conclusion
AI-based chatbots may provide useful information in RET and could serve as supplementary tools in dental education. However, their role in clinically related decision-making requires further validation.
Zitieren
APA
Gökyar, M., Özden, İ., & Öveçoğlu, H. S. (2026). Accuracy of Artificial Intelligence Chatbots Versus Endodontic Residents in Regenerative Endodontic Treatment Knowledge. European Journal of Therapeutics. https://doi.org/10.58600/eurjther3013
Vancouver
Gökyar M, Özden İ, Öveçoğlu HS. Accuracy of Artificial Intelligence Chatbots Versus Endodontic Residents in Regenerative Endodontic Treatment Knowledge. European Journal of Therapeutics. 2026. doi:10.58600/eurjther3013
BibTeX
@article{Gkyar2026,
author = {Gökyar, Merve and Özden, İdil and Öveçoğlu, Hesna Sazak},
title = {Accuracy of Artificial Intelligence Chatbots Versus Endodontic Residents in Regenerative Endodontic Treatment Knowledge},
journal = {European Journal of Therapeutics},
year = {2026},
doi = {10.58600/eurjther3013}
}
EUVIMED