The role of generative artificial intelligence in debunking misinformation about pediatric dentistry

• Grant number: 25/16631-7
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: October 01, 2025
• End date: September 30, 2026
• Field of knowledge: Health Sciences - Dentistry - Pediatric Dentistry
• Principal Investigator: Matheus Lotto de Almeida Souza
• Grantee: Pedro Henrique Vieira Cruz
• Host Institution: Faculdade de Odontologia de Bauru (FOB). Universidade de São Paulo (USP). Bauru , SP, Brazil

Abstract

The use of generative artificial intelligence (AI) chatbots has been transforming users' health information seeking behavior. However, little is known about the potential of these tools to debunk inaccurate information on oral health. Therefore, this project aims to analyze the use of generative AI chatbots in refuting falsehoods related to Pediatric Dentistry, assessing their effectiveness in providing accurate information on children's oral health. Initially, guiding questions will be developed, based on Prompt Engineering, addressing fact-checking, explanations, and opinions. These questions will be constructed from 18 previously identified false contents on Pediatric Dentistry. The answers obtained will be evaluated by two independent, trained, and calibrated examiners through content analysis, with the aim of classifying them as reinforcing or refuting the falsehoods. Finally, the results will be analyzed using QDA Miner and SPSS software, with graphical representations to illustrate qualitative data, along with descriptive statistics and group comparison tests (P<0.05).