The purpose of this study is to investigate the facial symmetry aesthetics (FSA) in the Saudi Arabian population using AI. 210 people from a range of demographic backgrounds participated in an observational cross-sectional study that was done at a hospital. Standardized posed photos of the face and smile were taken using a Canon camera utilizing a stratified random sample approach. A Webceph software (Korea) with artificial intelligence was used to evaluate macro, micro, and tiny aesthetic factors. The data were analyzed using paired t-tests, posthoc Bonferroni testing, ANOVA, and descriptive statistics. The computation of intra-class correlation coefficients (ICCs) was utilized to assess the dependability of AI evaluations. All variables had ICCs more than 0.97, indicating exceptional dependability for the AI-based evaluations. Between the Class I and Class III malocclusion groups, there were significant variations in right mandibular body length (p < 0.001), with Class III patients exhibiting greater values. While no significant changes were identified for other characteristics, paired t-tests showed a significant divergence in mandibular body length between the right and left sides (p = 0.001). In Class III malocclusion, there was a significant preference for right deviation in the direction of mandibular deviation (p = 0.005). These results imply that AI is capable of accurately identifying some anatomical characteristics associated with face aesthetics, especially when it comes to differentiating between Class III malocclusions. In conclusion, the Saudi Arabian population's facial symmetry assessments via AI have demonstrated a high degree of reliability and consistency. Notably, the length of the mandible on the right side has emerged as a crucial feature in discriminating between malocclusion classes. The study emphasises how AI might improve the accuracy of assessments of face aesthetics and our knowledge of facial features connected to malocclusion.
Read full abstract