LAUSR

BACKGROUND Patients desire facelifting procedures to look younger, refreshed, and attractive. Unfortunately, there are few objective studies assessing the success of types of facelift procedures and ancillary techniques. OBJECTIVES The authors sought to utilize convolutional neural network algorithms alongside patient-reported FACE-Q outcomes to evaluate perceived age reduction and patient satisfaction following various facelift techniques. METHODS Standardized preoperative and postoperative (1-year) images of patients who underwent facelift procedures were analyzed by 4 neural networks to estimate age reduction after surgery (n = 105). FACE-Q surveys were employed to measure patient-reported facial aesthetic outcome. We compared (1) facelift procedure type: skin-only vs superficial musculoaponeurotic system (SMAS)-plication, vs SMAS-ectomy; and (2) ancillary techniques: fat grafting (malar) vs no fat grafting. Outcomes were based on complications, estimated age-reduction, and patient satisfaction. RESULTS The neural network preoperative age accuracy score demonstrated that all neural networks were accurate in identifying our patients' ages (mean score = 100.4). SMAS-ectomy and SMAS-plication had significantly greater age-reduction (5.85 and 5.35 years, respectively) compared with skin-only (2.95 years, P < 0.05). Fat grafting compared to no fat grafting demonstrated 2.1 more years of age reduction. Facelift procedure type did not affect FACE-Q scores; however, patients who underwent fat grafting had a higher satisfaction with outcome (78.1 ± 8 vs 69 ± 6, P < 0.05) and decision to have the procedure (83.0 ± 6 vs 72 ± 9, P < 0.05). CONCLUSIONS Artificial intelligence algorithms can reliably estimate the reduction in apparent age after facelift surgery. Facelift technique, like SMAS-ectomy or SMAS-plication, and specific technique, like fat grafting, were found to enhance facelifting outcomes and patient satisfaction.