Role of Artificial Intelligence and Machine Learning in Facial Aesthetic Surgery: A Systematic Review
Brooke Stephanian, Sabin Karki, Kirin Debnath, Mikhail Saltychev, Monica Rossi-Meyer, Cherian K. Kandathil, Sam P. Most
Abstract
Objective: To analyze the quality of artificial intelligence (AI) and machine learning (ML) tools developed for facial aesthetic surgery. Data Sources: Medline, Embase, CINAHL, Central, Scopus, and Web of Science databases were searched in February 2024. Study Selection: All original research in adults undergoing facial aesthetic surgery was included. Pilot reports, case reports, case series ( n < 5), conference proceedings, letters (except research letters and brief reports), and editorials were excluded. Main Outcomes and Measures: Facial aesthetic surgery procedures employing AI and ML tools to measure improvements in diagnostic accuracy, predictive outcomes, precision patient counseling, and the scope of facial aesthetic surgery procedures where these tools have been implemented. Results: Out of 494 initial studies, 66 were included in the qualitative analysis. Of these, 42 (63.6%) were of “good” quality, 20 (30.3%) were of “fair” quality, and 4 (6.1%) were of “poor” quality. Conclusion: AI improves diagnostic accuracy, predictive capabilities, patient counseling, and facial aesthetic surgery treatment planning.