QS6: Improvements In Perceived Age And Attractiveness Following Aesthetic Rhinoplasty Using Facial Recognition And Artificial Intelligence

PURPOSE: Facial recognition software may serve as a more objective tool for measuring aesthetic improvements following facial plastic surgery. This study utilized a novel facial recognition and artificial intelligence software in order to assess perceived changes in age and attractiveness amongst patients receiving rhinoplasty. METHODS: This study was a retrospective evaluation of 3D photographs of patients who underwent aesthetic rhinoplasty alone by the senior author (DS). Both pre- and post-operative (>12-month follow-up) Vectra 3D images (Canfield Scientific, Parsippany, NJ) were assessed using Haystack Artificial Intelligence Software (Haystack AI, New York, NY). Facial attractiveness (score 1-10) and apparent age were predicted. Paired t-tests were used to compare age and attractiveness scores before and after surgery. Multivariate linear regression was performed to identify factors associated with age and attractiveness scores. RESULTS: Forty patients receiving rhinoplasty met the study criteria (average age 48.3). Overall, rhinoplasty was associated with increases in AI-rated attractiveness (+0.58, p = 0.004) and decreases in perceived age relative to the patient’s true age (-1.62 years, p = 0.021). Greater decreases in post-operative perceived age were achieved in patients who appeared older than their actual age pre-operatively (p = 0.04). AI age predictions were also closer to true patient age post-operatively (+1.71 years) than they were pre-operatively (+3.33 years). CONCLUSION: Facial recognition software was successfully implemented to evaluate improvements in perceived age and attractiveness in patients undergoing aesthetic rhinoplasty. Using this technology, patients were found to appear more attractive and younger after rhinoplasty. Additionally, age reversal was greatest among patients who appeared older than their actual age at the time of surgery.