Predictive 3D Modeling of Orthognathic Surgery Outcomes Using Machine Learning Algorithms: A Systematic Review

Abstract

Background: Orthognathic surgery is one of the main corrective treatments in patients with maxillofacial deformities, performed for functional or aesthetic reasons. The aim of this systematic review is to examine and analyze studies published between 2020 and 2025 on the use of machine learning algorithms in 3D modeling to predict orthognathic surgery outcomes.
Materials and Methods: This study is a systematic review of articles published between 2021 and 2025. To find relevant articles, the Google Scholar and PubMed databases were searched. The reference lists of relevant articles were also manually checked to ensure comprehensiveness of the search. Inclusion criteria for the systematic review were original studies published between 2020 and 2025, studies that used machine learning or deep learning algorithms to predict orthognathic surgery outcomes using 3D modeling, articles published in English, and studies with access to the full text of the article.
Results: A total of 42 articles were identified. After careful review, 13 articles were included as eligible studies in the final analysis. The flow chart of study selection in PRISMA format is provided. All studies used machine learning algorithms such as deep neural networks, reinforcement learning, random forest, or graph-based models to predict orthognathic surgery outcomes. Most studies used 3D facial models or CBCT images for preoperative design and prediction of postoperative outcomes. All studies were assessed based on quality criteria.
Conclusion: The findings of this review demonstrate that new digital technologies, particularly artificial intelligence, 3D modeling, and virtual planning, are playing an increasingly important role in the transformation of maxillofacial and cosmetic surgical care.