Artificial Intelligence-guided development of Bioactive Glass-modified 3D-printable resins and their physicomechanical performance after erosive challeng

• Grant number: 25/15872-0
• Support Opportunities: Scholarships abroad - Research Internship - Doctorate
• Start date: April 01, 2026
• End date: March 31, 2027
• Field of knowledge: Health Sciences - Dentistry - Dental Materials
• Principal Investigator: Linda Wang
• Grantee: Mylena Proença Costa
• Supervisor: Patricia Nobrega Rodrigues Pereira
• Host Institution: Faculdade de Odontologia de Bauru (FOB). Universidade de São Paulo (USP). Bauru , SP, Brazil
• Institution abroad: University of Florida, Gainesville (UF), United States
• Associated to the scholarship: 23/14306-6 - Interaction of universal dentin bonding systems of non carious cervical lesions: a randomized clinical controlled trial and analyses of anti-proteolytic activity by in situ zymography and in vitro characterization of physical mechanical properties, BP.DR

Abstract

The increasing prevalence of erosive tooth wear (ETW), particularly affecting posterior occlusal surfaces, presents a significant clinical challenge due to the progressive loss of dental structure and the consequent impairment of function and esthetics. Indirect restorations produced via 3D printing, combined with the incorporation of bioactive components capable of mitigating erosive damage, represent a promising strategy for the rehabilitation of such cases. This study aims to optimize and characterize 3D-printable resins modified by the incorporation of bioactive glass particles using an Artificial Neural Network (ANN) approach by AI/ML (Artificial Intelligence/Machine Learning). Two types of bioactive glass (S-PRG and BioMin F) will be incorporated into a commercial resin at different concentrations to develop formulations capable of maintaining printability while enhancing mechanical performance and resistance to erosive degradation. The study will be divided into two phases: Phase 1 will evaluate resin viscosity (V), volumetric polymerization shrinkage (VPS), degree of conversion (DC), and flexural strength (FS). An ANN model will integrate these properties to predict optimized formulations. Phase 2 will assess the performance of selected resin formulations before and after an erosive challenge (0.1% citric acid), analyzing volumetric stability (VS), flexural strength (FS), elastic modulus (EM), and surface topography (ST) via optical profilometry. For the quantitative tests, statistical analysis will be performed using two-way ANOVA followed by Tukey's post-hoc test (¿ = 0.05) to determine significant differences among the experimental groups and conditions. The combination of advanced AI/ML modeling with systematic experimental validation will accelerate the development of bioactive, erosion-resistant, 3D-printable dental materials, reducing development time, costs, and material waste.