Perceived Age and Attractiveness Using Facial Recognition Software in Rhinoplasty Patients: A Proof-of-Concept Study

Abstract

: Artificial intelligence (Al)-based analyses may serve as a more objective tool for measuring cosmetic improvements following aesthetic plastic surgery. This preliminary proof-of-concept study utilized a novel commercial facial recognition software to assess perceived changes in age and attractiveness among patients receiving rhinoplasty. This study was a retrospective evaluation of three-dimensional photographs of patients who underwent rhinoplasty by the senior author (DS). Both pre- and post-operative (> 12-month follow-up) Vectra three-dimensional images (Canfield Scientific, Parsippany, NJ) were assessed using Haystack AI Software (Haystack AI, New York, NY). Facial attractiveness (score 1–10) and apparent age were predicted. A retrospective chart review of demographic variables was additionally performed. 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. One hundred twenty-four patients receiving rhinoplasty met the study criteria (average age: 35.58). Overall, rhinoplasty was associated with increases in Al-rated attractiveness (+0.28, P = 0.03) and decreases in perceived age relative to the patient’s true age (−1.03 years, P = 0.03). Greater decreases in postoperative perceived age were achieved in patients who appeared older than their actual age preoperatively (P < 0.001). Facial recognition software was successfully used to evaluate improvements in perceived age and attractiveness in patients undergoing aesthetic rhinoplasty. Patients were perceived by the software as younger and more attractive following rhinoplasty. Age reversal was greatest among patients who appeared much older than their actual age at the time of surgery. Level of Evidence: IV

Exploring artificial intelligence from a clinical perspective: A comparison and application analysis of two facial age predictors trained on a large‐scale Chinese cosmetic patient database

“…Indeed, its acceptance, reliable results, and application verification in the field of plastic surgery as the concept of AI-perceived age have already been widely acknowledged. 1,5,29 The limitations of this study are as follows. Owing to the uneven distribution of patients in the face database used for the model training, there were few males, and the age distribution was severely imbalanced.…”

“…With the aging of human society, aging and anti-aging have emerged as research hotspots in plastic surgery and aesthetic medicine. 1 Facial aging-a significant component of overall body aging-is a fundamental biological rule that has significant psychological and sociological implications. 2,3 The distinctive changes of facial aging are frequently utilized as a crucial reference when attempting to estimate an individual's age.…”

“…With the aging of human society, aging and anti‐aging have emerged as research hotspots in plastic surgery and aesthetic medicine 1 . Facial aging—a significant component of overall body aging—is a fundamental biological rule that has significant psychological and sociological implications 2,3 .…”

“…The former contributes to accurate assessment, and the latter helps doctors better understand which part of the face should be focused on and improved. Research efforts are mainly concentrated in the field of computer science because the application of artificial intelligence (AI) is limited by the demands for algorithm development expertise and model training resources 1 . To date, no comparative analytical work has been published on these two types of age‐prediction models from the standpoint of clinical applicability.…”

Artificial intelligence in plastic surgery: current developments and future perspectives

“…AI uses deep learning methods to extract facial features and uses CNN to evaluate apparent age [35] and facial attractiveness [36] . ML is also used to assess facial beauty based on facial proportions according to features like the golden ratio, texture, shape, and color [37] . These techniques provide an objective assessment of patient aesthetic improvement after surgery.…”