Application of Machine Learning for Etiological Investigation of Non-Carious Cervical Lesions

• Grant number: 23/11321-4
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: July 01, 2024
• End date: June 30, 2025
• Field of knowledge: Health Sciences - Dentistry
• Principal Investigator: Bruna Santos Honório Tonin
• Grantee: Lucas Eduardo Kava
• Host Institution: Faculdade de Odontologia de Ribeirão Preto (FORP). Universidade de São Paulo (USP). Ribeirão Preto , SP, Brazil

Abstract

Non-carious cervical lesions (NCCLs) are clinical conditions characterized by the loss of dental structurein the cemento-enamel junction region. Although they have been extensively studied in dentistry,there is no consensus in the literature on the etiological origins of this type of lesion, which arecurrently considered multifactorial but require different clinical interventions for treatment and prevention.The objective of this research is to correlate variables of individuals with NCCLs with information on clinical and behavioral aspects such as diet, physical and mental health, parafunctional habits, chewing, and oral hygiene. For data collection, a questionnaire on habits, lifestyle, and diet will be applied together with previously performed clinical data collection (anamnesis, medical and dental history, intraoral scanning, and bite force analysis). The results of traditional techniques will be compared with those of machine learning models in the analysis of variables, and it is expected that these results will provide support for a better understanding of the etiology of non-carious lesions, impacting the diagnosis, correct intervention, and better guidance of the population to prevent premature aging of teeth.