Orthodontics Diagnostic Based on Multinomial Logistic Regression Model

Abstract

The main objective of this study is evaluate the influence of several covariates in the occurrence of two types of vertical jaw dysplasia (open bite and deepbite) in orthodontics field.

The study of vertical jaw dysplasia is of great interest to the community of orthodontists, to ensure long-term stability of treatment, as this envolves complex etiological factors.

In this work we propose to build a multinomial logistic regression model that could assess the probability of an individual have open bite or deepbite taking into account some cephalometric measures of hyoid bone (HB) and some individual characteristics.

The study was conducted in a retrospective evaluation and consisted of 191 individuals random selected from a clinic in the Northern region of Portugal. We evaluated multiple factors in the construction of multinomial logistic regression model with 2 logit functions. The technique used to select variables to be included in the model, was the stepwise technique by choosing the smallest p value for the variable entering in the model.

Of the modeling process through multinomial logistic regression have resulted five position of the hyoid bone that have statistical significance and that can contribute as an auxiliary for the diagnosis of vertical jaw dysplasia.