Exploring Facial Asymmetry Metrics Correlated with Pre-operative SCHNOS Scores Using AI.

Abstract

Facial asymmetry is often overlooked in evaluations of nasal function and aesthetics, despite its potential impact on assessments in facial plastic surgery. This study aims to utilize AI tools to identify facial asymmetry metrics that correlate with both nasal function and aesthetic measures evaluated by pre-op SCHNOS Scores. Two facial landmark detection models were applied to frontal plain facial images of 1,523 patients to extract 506 fiducial points. From these, over 64 million facial elements were computed, including point-to-point and point-to-line distances. Then asymmetry indexes were calculated based on each element with its mirrored counterpart. Finally, Spearman correlation coefficients were used to assess associations between these asymmetry metrics and 13 outcome scores. Facial elements correlated with SCHNOS-O demonstrated modest but statistically significant Spearman correlations (0.185-0.224, p < 10⁻¹¹), particularly those capturing vertical facial height differences relative to a horizontal reference line between the nasal tip and ear base. No meaningful correlations were observed with SCHNOS-C scores. These findings suggest vertical midfacial asymmetry may impact nasal function, whereas facial asymmetry has minimal influence on patients' perception of nasal aesthetics. The study also underscores the potential of AI-based facial analysis as a valuable tool in rhinoplasty evaluation.