Research Article

EVALUATING THE ACCURACY AND RELIABILITY OF ARTIFICIAL INTELLIGENCE CHATBOTS IN ANSWERING DENTAL SPECIALTY EXAMINATION PERIODONTOLOGY QUESTIONS

Number: Advanced Online Publication Early Pub Date: November 2, 2026
EN TR

EVALUATING THE ACCURACY AND RELIABILITY OF ARTIFICIAL INTELLIGENCE CHATBOTS IN ANSWERING DENTAL SPECIALTY EXAMINATION PERIODONTOLOGY QUESTIONS

Abstract

Background/Aim: Large language models (LLMs) are increasingly utilized by dental students and specialty candidates as supplementary tools for examination preparation. However, their reliability in specialized clinical domains requiring analytical reasoning remains underexplored. This study aimed to comparatively evaluate the accuracy, reliability, and inter-model agreement of three contemporary reasoning-focused LLMs in answering Periodontology questions from the Turkish Dental Specialty Examination (DUS). Materials and Methods: In this cross-sectional in silico study, 100 multiple-choice Periodontology questions administered in past DUS sessions (2012–2026) were selected. The questions were presented in isolated sessions without prior contextual prompting to three models: OpenAI GPT-5.5 Thinking, Anthropic Claude Opus 4.7 (adaptive thinking), and Google Gemini 3.1 Pro. Responses were scored dichotomously against official answer keys. Overall accuracy rates were compared using Cochran's Q test, pairwise agreement was assessed via Cohen's Kappa (k) coefficient, and shared error distributions were analyzed using a two-tailed Binomial test (p<0.05). Results: Overall accuracy rates were 95.0% for ChatGPT 5.5, 93.0% for Claude Opus 4.7, and 92.0% for Gemini 3.1 Pro, with no statistically significant difference among the models (p = 0.311). Pairwise comparisons revealed statistically significant and substantial agreement across all model pairings (p < 0.001): ChatGPT–Gemini (κ = 0.754 ± 0.140), ChatGPT–Claude (κ = 0.646 ± 0.173), and Gemini–Claude (κ = 0.640 ± 0.157). Although shared error distributions did not deviate significantly from random expectation (p > 0.05), ChatGPT and Gemini selected the identical incorrect distractor in all 5 questions they mutually failed (100% shared error rate; p = 0.0625). Conclusion: Contemporary reasoning-capable LLMs demonstrate high accuracy and substantial inter-model consistency on specialty-level Periodontology questions. Nevertheless, the presence of concordant errors indicates shared algorithmic blind spots, underscoring that AI outputs must be supplemented by specialist oversight and evidence-based verification in dental education.

Keywords

References

  1. [1] Perera P, Lankathilaka M. AI in higher education: a literature review of ChatGPT and guidelines for responsible implementation. Int J Res Innov Soc Sci. 2023;7(6):306-314.
  2. [2] Holmes W, Bialik M, Fadel C. Artificial intelligence in education: promises and implications for teaching and learning. Center for Curriculum Redesign.
  3. [3] Çatman FN, Topsakal E, Saatçioğlu Ö. Üniversite Öğrencilerinin Yapay Zekâ Kullanım Düzeylerinin Belirlenmesi. NEEEF. 2025;7(Özel Sayı):317-347
  4. [4] Hocaoğlu H. Investigation of artificial intelligence awareness levels of special education teachers. J Individ Differ Educ. 2025;7(1):1-16.
  5. [5] Çetin P, Onan A. Büyük dil modellerinin tıp eğitiminde soru yanıtlama sistemlerinde kullanımı: Potansiyel, zorluklar ve gelecek yönelimleri. Jismce. 2025;1(1):82-108.
  6. [6] Akbulut K. Evaluation of the competence of artificial intelligence-supported chatbots in answering prosthodontics questions requiring analytical thinking in the Dental Specialty Examination: A cross-sectional study. Turkiye Klinikleri J Dent Sci. 2026;32(1):212.
  7. [7] Rajki Z, Andok M, Radetzky A, Szilczl D. Use of artificial intelligence tools and applications among ecclesiastical journalists. Jel-Kép. 2025;2:77-95.
  8. [8] Hwang GJ, Xie H, Wah BW, Gašević D. Vision, challenges, roles and research issues of artificial intelligence in education. Comput Educ Artif Intell. 2020;1:100001.

Details

Primary Language

English

Subjects

Periodontics

Journal Section

Research Article

Early Pub Date

November 2, 2026

Publication Date

-

Submission Date

September 29, 2026

Acceptance Date

October 27, 2026

Published in Issue

Year 2026 Number: Advanced Online Publication

APA
Akpınar, A. (2026). EVALUATING THE ACCURACY AND RELIABILITY OF ARTIFICIAL INTELLIGENCE CHATBOTS IN ANSWERING DENTAL SPECIALTY EXAMINATION PERIODONTOLOGY QUESTIONS. Cumhuriyet Dental Journal, Advanced Online Publication. https://doi.org/10.7126/cumudj.2049044
AMA
1.Akpınar A. EVALUATING THE ACCURACY AND RELIABILITY OF ARTIFICIAL INTELLIGENCE CHATBOTS IN ANSWERING DENTAL SPECIALTY EXAMINATION PERIODONTOLOGY QUESTIONS. Cumhuriyet Dent J. 2026;(Advanced Online Publication). doi:10.7126/cumudj.2049044
Chicago
Akpınar, Aysun. 2026. “EVALUATING THE ACCURACY AND RELIABILITY OF ARTIFICIAL INTELLIGENCE CHATBOTS IN ANSWERING DENTAL SPECIALTY EXAMINATION PERIODONTOLOGY QUESTIONS”. Cumhuriyet Dental Journal, no. Advanced Online Publication. https://doi.org/10.7126/cumudj.2049044.
EndNote
Akpınar A (November 2, 2026) EVALUATING THE ACCURACY AND RELIABILITY OF ARTIFICIAL INTELLIGENCE CHATBOTS IN ANSWERING DENTAL SPECIALTY EXAMINATION PERIODONTOLOGY QUESTIONS. Cumhuriyet Dental Journal Advanced Online Publication
IEEE
[1]A. Akpınar, “EVALUATING THE ACCURACY AND RELIABILITY OF ARTIFICIAL INTELLIGENCE CHATBOTS IN ANSWERING DENTAL SPECIALTY EXAMINATION PERIODONTOLOGY QUESTIONS”, Cumhuriyet Dent J, no. Advanced Online Publication, Nov. 2026, doi: 10.7126/cumudj.2049044.
ISNAD
Akpınar, Aysun. “EVALUATING THE ACCURACY AND RELIABILITY OF ARTIFICIAL INTELLIGENCE CHATBOTS IN ANSWERING DENTAL SPECIALTY EXAMINATION PERIODONTOLOGY QUESTIONS”. Cumhuriyet Dental Journal. Advanced Online Publication (November 2, 2026). https://doi.org/10.7126/cumudj.2049044.
JAMA
1.Akpınar A. EVALUATING THE ACCURACY AND RELIABILITY OF ARTIFICIAL INTELLIGENCE CHATBOTS IN ANSWERING DENTAL SPECIALTY EXAMINATION PERIODONTOLOGY QUESTIONS. Cumhuriyet Dent J. 2026. doi:10.7126/cumudj.2049044.
MLA
Akpınar, Aysun. “EVALUATING THE ACCURACY AND RELIABILITY OF ARTIFICIAL INTELLIGENCE CHATBOTS IN ANSWERING DENTAL SPECIALTY EXAMINATION PERIODONTOLOGY QUESTIONS”. Cumhuriyet Dental Journal, no. Advanced Online Publication, Nov. 2026, doi:10.7126/cumudj.2049044.
Vancouver
1.Aysun Akpınar. EVALUATING THE ACCURACY AND RELIABILITY OF ARTIFICIAL INTELLIGENCE CHATBOTS IN ANSWERING DENTAL SPECIALTY EXAMINATION PERIODONTOLOGY QUESTIONS. Cumhuriyet Dent J. 2026 Nov. 2;(Advanced Online Publication). doi:10.7126/cumudj.2049044

Cumhuriyet Dental Journal (Cumhuriyet Dent J, CDJ) is the official publication of Cumhuriyet University Faculty of Dentistry. CDJ is an international journal dedicated to the latest advancement of dentistry. The aim of this journal is to provide a platform for scientists and academicians all over the world to promote, share, and discuss various new issues and developments in different areas of dentistry. First issue of the Journal of Cumhuriyet University Faculty of Dentistry was published in 1998. In 2010, journal's name was changed as Cumhuriyet Dental Journal. Journal’s publication language is English.


CDJ accepts articles in English. Submitting a paper to CDJ is free of charges. In addition, CDJ has not have article processing charges.

Frequency: Four times a year (March, June, September, and December)

IMPORTANT NOTICE

All users of Cumhuriyet Dental Journal should visit to their user's home page through the "https://dergipark.org.tr/tr/user" " or "https://dergipark.org.tr/en/user" links to update their incomplete information shown in blue or yellow warnings and update their e-mail addresses and information to the DergiPark system. Otherwise, the e-mails from the journal will not be seen or fall into the SPAM folder. Please fill in all missing part in the relevant field.

Please visit journal's AUTHOR GUIDELINE to see revised policy and submission rules to be held since 2020.