Using artificial intelligence to analyze emotion and facial action units following facial rejuvenation surgery.

Abstract

There remains a lack of standards in facial rejuvenation procedures, which may be attributed to the subjective measures used to determine surgical outcomes and success. The aim of this study was to evaluate the use of machine learning technology, i.e. FaceReader™, to objectively measure facial rejuvenation surgery outcomes. Using a retrospective study design, we enrolled a cohort of patients undergoing high SMAS facelift with/without additional procedures during a one-year interval. The predictor variable was surgery done (pre- vs. postoperative). The outcome variables were 28 facial action units, happiness, and sadness emotions, detected by FaceReader™. Appropriate statistics were calculated at α = 0.05. The sample comprised of 15 patients (11 females, 15 Caucasians, mean age of 55.7 years). There was an average increase in detected happy emotion from 1.03% to 13.17% (p>0.01). Conversely, the average angry emotion detected decreased from 14.66% to 0.63% (p<0.05). There were no other distinct action unit patterns across the operation. Despite a small sample size, the results of this study suggest that FaceReader™ can be used as an objective outcome assessment tool in patients undergoing high SMAS facelift with/without its adjuncts.