Machine learning based orthodontic treatment planning for mixed dentition borderline cases suffering from moderate to severe crowding: An experimental research study.

Abstract

Pedodontists and general practitioners may need support in planning the early orthodontic treatment of patients with mixed dentition, especially in borderline cases. The use of machine learning algorithms is required to be able to consistently make treatment decisions for such cases. This study aimed to use machine learning algorithms to facilitate the process of deciding whether to choose serial extraction or expansion of maxillary and mandibular dental arches for early treatment of borderline patients suffering from moderate to severe crowding. The dataset of 116 patients who were previously treated by senior orthodontists and divided into two groups according to their treatment modalities were examined. Machine Learning algorithms including Multilayer Perceptron, Linear Logistic Regression, k-nearest Neighbors, Naïve Bayes, and Random Forest were trained on this dataset. Several metrics were used for the evaluation of accuracy, precision, recall, and kappa statistic. The most important 12 features were determined with the feature selection algorithm. While all algorithms achieved over 90% accuracy, Random Forest yielded 95% accuracy, with high reliability values (kappa = 0.90). The employment of machine learning methods for the treatment decision with or without extraction in the early treatment of patients in the mixed dentition can be particularly useful for pedodontists and general practitioners.