Okan Turgut, H Melike Bayram* and Emre Bayram

Associate Professor, Tokat Gaziosmanpasa University, Faculty of Dentistry, Department of Endodontics, Tokat, Turkiye

*Corresponding Author: Huda Melike Bayram, Associate Professor, Tokat Gaziosmanpasa University, Faculty of Dentistry, Department of Endodontics, Tokat, Turkiye.

Received: August 25, 2025; Published: September 10, 2025

Abstract

Aim: Objective: This study aimed to evaluate the performance of three large language models (LLMs)-Grok, ChatGPT, and DeepSeekin managing traumatic dental injuries (TDIs) based on their alignment with the International Association of Dental Traumatology (IADT) 2020 clinical guidelines.

Materials and Methods: Twenty open-ended prompts were constructed to reflect real-life TDI scenarios, aligned with the 2020 IADT guidelines. Each model was queried once per prompt with no re-prompting or interaction refinement. Responses were evaluated by a trained rater using a five-criteria rubric: scientific accuracy, reliability of information, comprehensibility, level of detail, and clinical applicability. Scoring was performed using a 3-point ordinal scale. One-way ANOVA and post-hoc comparisons were applied for statistical analysis.

Results: Grok outperformed both ChatGPT and DeepSeek in scientific accuracy, detail level, and information reliability (p < 0.001). ChatGPT and DeepSeek showed relatively higher scores in comprehensibility (p = 0.007). For clinical applicability, only the Grok– DeepSeek comparison was statistically significant (p = 0.016). Total score comparisons were substantial across all model pairs (p < 0.001).

Conclusion: Large language models exhibit distinct strengths across clinical performance metrics. Grok appears more suitable for guideline-based clinical decision support in TDI management, whereas ChatGPT and DeepSeek may be better suited for educational and communicative purposes. Purpose-driven model selection and continuous performance monitoring are recommended for safe and effective clinical integration.

Keywords: Artificial Intelligence; Large Language Models; Traumatic Dental Injuries; Clinical Decision Support; Guideline Adherence; IADT Guidelines

References

1. Thurzo A., et al. “Impact of artificial intelligence on dental education: a review and guide for curriculum update”. Education Science1 (2023): 150.
2. Ahmed N., et al. “Artificial intelligence techniques: analysis, application, and outcome in dentistry-a systematic review”. BioMed Research International 3 (2021): 9751564.
3. Filice RW., et al. “Evaluating artificial intelligence systems to guide purchasing decisions”. Journal of the American College of Radiology 11 (2020): 1405-1409.
4. Türker H., et al. “Fabrication of Customized dental guide by stereolithography method and evaluation of dimensional accuracy with artificial neural networks”. Journal of the Mechanical Behavior of Biomedical Materials 3 (2022): 105071.
5. Bourguignon C., et al. “International Association of Dental Traumatology guidelines for the management of traumatic dental injuries: 1. Fractures and luxations”. Dental Traumatology 4 (2020): 314-330.
6. Day PF., et al. “International Association of Dental Traumatology guidelines for the management of traumatic dental injuries: 3. Injuries in the primary dentition”. Dental Traumatology 4 (2020): 343-359.
7. Meng X., et al. “The application of large language models in medicine: A scoping review”. iScience 5 (2024): 109713.
8. Alkalbani AM., et al. “A Systematic Review of Large Language Models in Medical Specialties: Applications, Challenges and Future Directions”. (2025).
9. Hartman V., et al. “Developing and evaluating large language model–generated emergency medicine handoff notes”. JAMA Network Open 12 (2024): e2448723-e2448723.
10. Shool S., et al. “A systematic review of large language model (LLM) evaluations in clinical medicine”. BMC Medical Informatics and Decision Making 1 (2025): 117.
11. Wang L., et al. “Accuracy of large language models when answering clinical research questions: Systematic review and network meta-analysis”. Journal of Medical Internet Research 2 (2025): e64486.
12. Sivaramakrishnan G., et al. “Assessing the power of AI: a comparative evaluation of large language models in generating patient education materials in dentistry”. BDJ Open 1 (2025): 59.
13. Ozdemir ZM., et al. “Evaluating the Accuracy, Reliability, Consistency, and Readability of Different Large Language Models in Restorative Dentistry”. Journal of Esthetic and Restorative Dentistry (2025).
14. Tam TYC., et al. “A framework for human evaluation of large language models in healthcare derived from literature review”. NPJ Digital Medicine 1 (2024): 258.
15. Haltaufderheide J., et al. “The ethics of ChatGPT in medicine and healthcare: a systematic review on Large Language Models (LLMs)”. NPJ Digital Medicine 1 (2024): 183.
16. Asgari E., et al. “A framework to assess clinical safety and hallucination rates of LLMs for medical text summarisation”. NPJ Digital Medicine 1 (2025): 274.

Citation

Citation: H Melike Bayram., , et al. “Comparative Evaluation of Artificial Intelligence Models for Traumatic Dental Injuries Based on Clinical Guideline Adherence".Acta Scientific Dental Sciences 9.10 (2025): 09-14.

Copyright

Copyright: © 2025 H Melike Bayram., , et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.