Abstract
Artificial Intelligence-Based Modeling Can Predict Face Shape Based on Underlying Craniomaxillofacial Bone: A Systematic Review and Meta-Analysis
Department of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
Trauma and Injury Research Center, Iran University of Medical Sciences, Tehran, Iran
Dermatol Rev/Przegl Dermatol 2026, 113, 231–235
The complex three-dimensional anatomy of the craniofacial skeleton and the overlying soft tissue structures often makes reconstruction of facial deformities difficult. Therefore, new techniques such as artificial intelligence may be helpful in estimating or determining the desired three-dimensional shape of the face. This study aimed to determine the diagnostic accuracy of artificial intelligence in predicting facial shape based on craniomaxillofacial structures. Eight studies were identified from international databases, including PubMed, Embase, Web of Science, and the Cochrane Library, up to May 31, 2025, using relevant keywords and predefined inclusion and exclusion criteria. Statistical analysis was performed using Stata version 17. The diagnostic accuracy of artificial intelligence-based modeling in craniofacial deformities was 88% (effect size: 0.88; 95% confidence interval: 0.72–1.05). Artificial intelligence modeling for predicting three-dimensional facial shape using skull shape and additional metadata from large datasets of head computed tomography images showed high diagnostic accuracy.
Keywords
artificial intelligence, facial reconstruction, face shape, deep learning, craniomaxillofacial structures
Coverage in
Integrated with

