Applying artificial intelligence to assess the impact of orthognathic treatment on facial attractiveness and estimated age

Abstract

This observational study aimed to use artificial intelligence to describe the impact of orthognathic treatment on facial attractiveness and age appearance. Pre- and post-treatment photographs (n=2164) of 146 consecutive orthognathic patients were collected for this longitudinal retrospective single-centre study. Every image was annotated with patient-related data (age; sex; malocclusion; performed surgery). For every image, facial attractiveness (score: 0-100) and apparent age were established with dedicated convolutional neural networks trained on >0.5million images for age estimation and with >17million ratings for attractiveness. Results for pre- and post-treatment photographs were averaged for every patient separately, and apparent age compared to real age (appearance). Changes in appearance and facial attractiveness were statistically examined. Analyses were performed on the entire sample and subgroups (sex; malocclusion; performed surgery). According to the algorithms, most patients' appearance improved with treatment (66.4%), resulting in younger appearance of nearly 1year [mean change: -0.93years (95% confidence interval (CI): -1.50; -0.36); p=0.002), especially after profile-altering surgery. Orthognathic treatment had similarly a beneficial effect on attractiveness in 74.7% [mean difference: 1.22 (95% CI: 0.81; 1.63); p<0.001], especially after lower jaw surgery. This investigation illustrates that artificial intelligence might be considered to score facial attractiveness and apparent age in orthognathic patients.

Keywords: attractiveness; convolutional neural networks; facial appearance; malocclusion; orthognathic surgery.