An Intelligent System for Prediction of Orthodontic Treatment Outcome

Abstract

It is important for orthodontists to predict the treatment outcome prior to establishing a treatment plan. Many studies have been conducted to create a predictive model of the treatment outcome for different orthodontic disorders using traditional regression techniques. This paper investigates viability of applying artificial neural networks in constructing a model for prediction of treatment outcomes of patients with Class II malocclusion. We developed two models to assess the treatment success by estimating the value of the Peer Assessment Rating (PAR) index from initial orthodontic measurements. We evaluated the performance of the neural network models on 205 patients, and the results are compared with previous linear regression models.