Long-Term Predictive Modelling of the Craniofacial Complex Using Machine Learning on 2D Cephalometric Radiographs

• Published in: International dental journal Vol. 75; no. 1; pp. 236 - 247
• Main Authors: Myers, Michael, Brown, Michael D., Badirli, Sarkhan, Eckert, George J., Johnson, Diane Helen-Marie, Turkkahraman, Hakan
• Format: Journal Article
• Language: English
• Published: England Elsevier Inc 01.02.2025; Elsevier
• Subjects: Adolescent; Adolescent Development - physiology; Artificial intelligence; Body Size - physiology; Cephalometric analysis; Cephalometry - methods; Cephalometry - statistics & numerical data; Child; Craniofacial complex; Dentistry; Face - diagnostic imaging; Growth and development; Humans; Incisor - diagnostic imaging; Incisor - growth & development; Machine learning; Male; Mandible - diagnostic imaging; Mandible - growth & development; Maxilla - diagnostic imaging; Maxilla - growth & development; Orthodontics; Predictive Learning Models; Predictive Value of Tests; Puberty; Radiography - methods; Radiography - statistics & numerical data; Random Allocation; Random Forest; Regression Analysis; Reproducibility of Results; Retrospective Studies; Scientific Research Reports; Skull Base - diagnostic imaging; Skull Base - growth & development; Growth and development; Cephalometric analysis; Artificial intelligence; Orthodontics; Machine learning; Craniofacial complex
• ISSN: 0020-6539; 1875-595X; 1875-595X
• DOI: 10.1016/j.identj.2024.12.023

This study aimed to predict long-term growth-related changes in skeletal and dental relationships within the craniofacial complex using machine learning (ML) models. Cephalometric radiographs from 301 subjects, taken at pre-pubertal (T1, age 11) and post-pubertal stages (T2, age 18), were analysed. Three ML models—Lasso regression, Random Forest, and Support Vector Regression (SVR)—were trained on a subset of 240 subjects, while 61 subjects were used for testing. Model performance was evaluated using mean absolute error (MAE), intraclass correlation coefficients (ICCs), and clinical thresholds (2 mm or 2°). MAEs for skeletal measurements ranged from 1.36° (maxilla to cranial base angle) to 4.12 mm (mandibular length), and for dental measurements from 1.26 mm (lower incisor position) to 5.40° (upper incisor inclination). ICCs indicated moderate to excellent agreement between actual and predicted values. The highest prediction accuracy within the 2 mm or 2° clinical thresholds was achieved for maxilla to cranial base angle (80%), lower incisor position (75%), and maxilla to mandible angle (70%). Pre-pubertal measurements and sex consistently emerged as the most important predictive factors. ML models demonstrated the ability to predict post-pubertal values for maxilla to cranial base, mandible to cranial base, maxilla to mandible angles, upper and lower incisor positions, and upper face height with a clinically acceptable margin of 2 mm or 2°. Prediction accuracy was higher for skeletal relationships compared to dental relationships over the 8-year growth period. Pre-pubertal values of the measurements and sex emerged consistently as the most important predictors of the post-pubertal values.