Brush, byte, and bot: quality comparison of artificial intelligence-generated pediatric dental advice across ChatGPT, Gemini, and Copilot

Abstract

Introduction Artificial intelligence (AI) tools such as ChatGPT, Google Gemini, and Microsoft Copilot are increasingly relied upon by parents for immediate guidance on pediatric dental concerns. This study evaluated and compared the response quality of these AI platforms in addressing real-world parental queries related to pediatric dentistry, including early tooth extraction, space maintenance, and the decision to consult a pediatric or a general dentist. Methods A structured 30-question survey was developed and submitted to each AI model, and their responses were anonymized and assessed by pediatric dental experts using a standardized rubric across five key domains: clinical accuracy, clarity, completeness, relevance, and absence of misleading information. Results Statistically significant differences were found across all five domains ( p < .001), with ChatGPT consistently achieving the highest scores. Multivariate analysis (MANOVA) confirmed a strong overall effect of the AI model on response quality (Pillai's Trace = 0.892, p < .001), supporting ChatGPT's superior performance in providing accurate, relevant, and comprehensive pediatric dental advice. Discussion While AI technologies show potential as clinical decision support systems, their variable performance reinforces the need for expert oversight. Future AI development should focus on optimizing response quality and safety to ensure effective and trustworthy digital health communication for pediatric dental care.

Ähnliche Arbeiten