Evaluation of accuracy, clinical reliability and readability of LLM-based chatbot responses in prosthetic dentistry FAQs

View at Publisher

Ask AI

Bookmark

Share

Key Points

This study aims to compare the responses of multiple LLM-based chatbots regarding prosthetic dentistry FAQs, focusing on accuracy, clinical reliability, and readability.
39 FAQs about fixed, removable, and implant-supported prosthesis were analyzed, with 13 questions in each category.
Responses were generated in Turkish and evaluated by three prosthodontists using a five-point Likert scale.
Inter-rater agreement was calculated using intraclass correlation coefficient, and statistical comparisons were made with Friedman test and Wilcoxon signed-rank tests.
High inter-rater agreement was observed for accuracy (ICC=0.86) and clinical reliability (ICC=0.83).
Significant differences among chatbots were found in accuracy, clinical reliability, and readability outcomes (all p<0.001).
Effect sizes indicated substantial variability between systems, demonstrating inconsistent performance across AI models.

We only have this paper's title and publication details.

Evaluates accuracy and reliability of LLM chatbots in prosthetic dentistry, indicating differences in performance.

No takes yet. Share an insight, caveat, or question.

Tartuk et al. (2026) studied this question.

View at Publisher

Ask AI

Bookmark

Share