Evaluation of facial attractiveness for patients with malocclusion: a machine-learning technique employing Procrustes.

Objective: To establish an objective method for evaluating facial attractiveness from a set of orthodontic photographs.
Materials and Methods: One hundred eight malocclusion patients randomly selected from six universities in China were randomly divided into nine groups, with each group containing an equal number of patients with Class I, II, and III malocclusions. Sixty-nine expert Chinese orthodontists ranked photographs of the patients (frontal, lateral, and frontal smiling photos) before and after orthodontic treatment from "most attractive" to "least attractive" in each group. A weighted mean ranking was then calculated for each patient, based on which a three-point scale was created. Procrustes superimposition was conducted on 101 landmarks identified on the photographs. A support vector regression (SVR) function was set up according to the coordinate values of identified landmarks of each photographic set and its corresponding grading. Its predictive ability was tested for each group in turn.
Results: The average coincidence rate obtained for comparisons of the subjective ratings with the SVR evaluation was 71.8% according to 18 verification tests.
Conclusions: Geometric morphometrics combined with SVR may be a prospective method for objective comprehensive evaluation of facial attractiveness in the near future.