Analysis of Machine Learning-Based Dental Caries Risk Prediction Model at Cairo Hospital, Egypt

Abstract

Introduction: Dental caries is the most common chronic disease in children and adults throughout the world. Prevention of dental caries is very important to maintain healthy teeth and mouth. The aim of this study was to develop and analyze a machine learning (ML)-based dental caries risk prediction model in patients at Cairo Hospital, Egypt.

Methods: Patient data was collected from medical records at Cairo Egypt Hospital. These data include demographic information, oral habits, and dental status. Different ML models, such as random forest, logistic regression, and support vector machine (SVM), were trained and evaluated to predict the risk of dental caries.

Results: The developed ML model showed good performance in predicting the risk of dental caries. The random forest model had the highest accuracy, namely 87%, followed by logistic regression (85%) and SVM (82%).

Conclusion: The ML model developed in this study can be a valuable tool to predict the risk of dental caries and to assist dentists in dental caries prevention efforts.