Factors associated with anxiety before endodontic treatment: A pilot cross-sectional study with machine learning predictive algorithms

• Grant number: 25/02266-5
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: May 01, 2025
• End date: February 28, 2026
• Field of knowledge: Health Sciences - Dentistry - Endodontics
• Principal Investigator: Walbert de Andrade Vieira
• Grantee: Maria Fernanda Santos Salvador
• Host Institution: Centro Universitário das Faculdades Associadas de Ensino de São João da Boa Vista (UNIFAE). Prefeitura Municipal de São João da Boa Vista. São João da Boa Vista , SP, Brazil

Abstract

Existing literature shows that endodontic treatment procedures are associated with a high risk of causing dental anxiety. Machine learning (ML) algorithms, a subdivision of artificial intelligence (AI), have gained prominence in the health field for diagnoses, predictions and identification of risk factors for diseases and injuries. Thus, the aims of this study will be to assess the prevalence and level of anxiety of patients undergoing endodontic treatment at the school clinic of the UNIFAE dentistry course and to carry out a pilot study to verify the feasibility of using artificial intelligence algorithms to predict the occurrence of preoperative anxiety. This cross-sectional study will be conducted with patients seen at the dental school clinic of the University Center of the Associated Faculties of Education - FAE. Patients over the age of 18 requiring endodontic treatment on mature permanent teeth will be included. The independent variables used in this study will be collected using questionnaires and/or specific scales. Anxiety at the time of treatment will be assessed using a numerical rating scale, which consists of a scoring system from 0 to 10. The data will undergo an initial pre-processing stage to normalize the database and will be analyzed using Python software. The data will be analyzed using supervised machine learning models such as decision trees, Random Forest, XGBoost and artificial neural networks. To evaluate the predictive performance of the algorithms, the following will be calculated: Area under the curve (AUC), accuracy (ACC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), F1 score. Through this project, it is hoped to increase knowledge about anxiety related to endodontic treatment and expand the application of artificial intelligence in this specialty.