Utilization of Machine Learning Methods for Predicting Orthodontic Treatment Length

Treatment duration is one of the most important factors that patients consider when deciding whether to undergo orthodontic treatment or not. This study aimed build and compare machine learning (ML) models for prediction length identify affecting using ML approach. Records 518 who had successfully finished were used in this study. Seventy percent patient data training models, thirty testing these models. We applied compared nine machine-learning algorithms: simple linear regression, modified polynomial K nearest neighbor, decision tree, bagging regressor, random forest, gradient boosting adaboost regression. then calculated importance features with highest performance. The best overall performance was obtained through regressor regression methods. predicting age, crowding, artificial intelligence case difficulty score, overjet, overbite. Without information, several algorithms showed comparable length. Bagging including malocclusion, provided.