“Constructing Machine Learning models for Orthodontic Treatment Planning: a comparison of different methods.” (Preprint)

Abstract

-

In this study, we investigated the feasibility of leveraging different machine learning methods to help with clinical decision-making on orthodontic treatment planning, including the decision on extraction, extraction pattern and anchorage pattern.

Setting and Sample Population: a group of 216 patients (156 extractions and 60 non-extraction) was enrolled. 32 input features were identified and used as the input variable. We proposed seven machine learning methods, including Logistic Regression, SVM, Decision Tree, Random Forest, Gaussian NB, KNN Classifier and Neural Network for extraction and two methods including Random Forest and Neural Network for extraction and anchorage pattern.

For extraction decision, neural network yielded the most promising results with 93 % accuracy, followed by Logistic regression (86 % accuracy and 93% precision), SVM and Random Forest (83 % accuracy and 90% precision). Naïve Bayesian classifier and KNN classifier failed to produce accuracy within the acceptable range, but Naïve Bayes demonstrated the highest recall score with 92 %. For the decision on extraction & anchorage pattern neural network proved to be more reliable, with 89 % accuracy on the extraction pattern and 81% accuracy on the extraction& anchorage pattern. Random Forest classifier with 41% accuracy did not show satisfactory results for this task. The most important features for a decision on extraction in this study were Inter incisal angle, crowding in the mandible, U1-FH, L1-NB and crowding in the maxilla.

The results demonstrate that neural network can yield considerable accuracy in a medical diagnosis model. However, other algorithms, such as logistic regression and random forest, can also be considered for simpler tasks such as extraction.