Exploring Large Language Models and Explainable Artificial Intelligence for the Generation of Clinical Records and Precision Treatment Planning in Dentistry

• Grant number: 26/04184-9
• Support Opportunities: Scholarships in Brazil - Master
• Start date: April 01, 2026
• End date: March 31, 2028
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Alessandra Alaniz Macedo
• Grantee: Victor Hugo da Silva Lembor
• Host Institution: Faculdade de Filosofia, Ciências e Letras de Ribeirão Preto (FFCLRP). Universidade de São Paulo (USP). Ribeirão Preto , SP, Brazil
• Associated research grant: 24/15912-0 - Multimodal Fusion for Digital Oral Health, AP.R

Abstract

Digital Health in Brazil seeks technological integration to promote equity and quality in access to healthcare services. The original project, "Multimodal Fusion for Digital Oral Health," proposes the integration of imaging and clinical data. However, Multimodal Machine Learning (MML) models often operate as "black boxes," generating clinical distrust. This master's research project aims to address this gap by investigating the use of Large Language Models (LLMs), such as BioBERT and GPT-4, to semantically process unstructured data and generate explainable clinical reports. The methodology proposes the use of domain-specific biomedical LLMs to create dense embeddings, along with the implementation of an Explainable Artificial Intelligence (XAI) layer to justify diagnostic decisions. The validation of the interface and its explainability will follow an innovative multifaceted protocol, combining heuristic and affective metrics. The expected outcome is a prototype clinical record system capable of generating precise treatment plans and reports, thereby increasing trust and efficiency in dental decision-making. (AU)