Long-Term Predictive Modelling of the Craniofacial Complex Using Machine Learning on 2D Cephalometric Radiographs
Objective: This study aimed to predict long-term growth-related changes in skeletal and dental relationships within the craniofacial complex using machine learning (ML) models. Materials and Methods: Cephalometric radiographs from 301 subjects, taken at pre-pubertal (T1, age 11) and post-pubertal st...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | International Dental Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0020653924016411 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592769602813952 |
|---|---|
| author | Michael Myers Michael D. Brown Sarkhan Badirli George J. Eckert Diane Helen-Marie Johnson Hakan Turkkahraman |
| author_facet | Michael Myers Michael D. Brown Sarkhan Badirli George J. Eckert Diane Helen-Marie Johnson Hakan Turkkahraman |
| author_sort | Michael Myers |
| collection | DOAJ |
| description | Objective: This study aimed to predict long-term growth-related changes in skeletal and dental relationships within the craniofacial complex using machine learning (ML) models. Materials and Methods: 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°). Results: 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. Conclusions: 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. |
| format | Article |
| id | doaj-art-14ca3a9f7e914001a0d4c5dee6f16d41 |
| institution | Kabale University |
| issn | 0020-6539 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Dental Journal |
| spelling | doaj-art-14ca3a9f7e914001a0d4c5dee6f16d412025-01-21T04:12:50ZengElsevierInternational Dental Journal0020-65392025-02-01751236247Long-Term Predictive Modelling of the Craniofacial Complex Using Machine Learning on 2D Cephalometric RadiographsMichael Myers0Michael D. Brown1Sarkhan Badirli2George J. Eckert3Diane Helen-Marie Johnson4Hakan Turkkahraman5Department of Orthodontics and Oral Facial Genetics, Indiana University School of Dentistry, Indianapolis, Indiana, USAIndiana University School of Dentistry, Indianapolis, Indiana, USAEli Lilly & Company, Indianapolis, Indiana, USADepartment of Biostatistics and Health Data Science, Indiana University School of Medicine, Indianapolis, Indiana, USADepartment of Orthodontics and Oral Facial Genetics, Indiana University School of Dentistry, Indianapolis, Indiana, USADepartment of Orthodontics and Oral Facial Genetics, Indiana University School of Dentistry, Indianapolis, Indiana, USA; Corresponding author. Department of Orthodontics & Oral Facial Genetics, Indiana University School of Dentistry, 1121 W. Michigan St, Room DS242, Indianapolis, IN 46202-5186, USA.Objective: This study aimed to predict long-term growth-related changes in skeletal and dental relationships within the craniofacial complex using machine learning (ML) models. Materials and Methods: 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°). Results: 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. Conclusions: 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.http://www.sciencedirect.com/science/article/pii/S0020653924016411Artificial intelligenceMachine learningCephalometric analysisCraniofacial complexGrowth and developmentOrthodontics |
| spellingShingle | Michael Myers Michael D. Brown Sarkhan Badirli George J. Eckert Diane Helen-Marie Johnson Hakan Turkkahraman Long-Term Predictive Modelling of the Craniofacial Complex Using Machine Learning on 2D Cephalometric Radiographs International Dental Journal Artificial intelligence Machine learning Cephalometric analysis Craniofacial complex Growth and development Orthodontics |
| title | Long-Term Predictive Modelling of the Craniofacial Complex Using Machine Learning on 2D Cephalometric Radiographs |
| title_full | Long-Term Predictive Modelling of the Craniofacial Complex Using Machine Learning on 2D Cephalometric Radiographs |
| title_fullStr | Long-Term Predictive Modelling of the Craniofacial Complex Using Machine Learning on 2D Cephalometric Radiographs |
| title_full_unstemmed | Long-Term Predictive Modelling of the Craniofacial Complex Using Machine Learning on 2D Cephalometric Radiographs |
| title_short | Long-Term Predictive Modelling of the Craniofacial Complex Using Machine Learning on 2D Cephalometric Radiographs |
| title_sort | long term predictive modelling of the craniofacial complex using machine learning on 2d cephalometric radiographs |
| topic | Artificial intelligence Machine learning Cephalometric analysis Craniofacial complex Growth and development Orthodontics |
| url | http://www.sciencedirect.com/science/article/pii/S0020653924016411 |
| work_keys_str_mv | AT michaelmyers longtermpredictivemodellingofthecraniofacialcomplexusingmachinelearningon2dcephalometricradiographs AT michaeldbrown longtermpredictivemodellingofthecraniofacialcomplexusingmachinelearningon2dcephalometricradiographs AT sarkhanbadirli longtermpredictivemodellingofthecraniofacialcomplexusingmachinelearningon2dcephalometricradiographs AT georgejeckert longtermpredictivemodellingofthecraniofacialcomplexusingmachinelearningon2dcephalometricradiographs AT dianehelenmariejohnson longtermpredictivemodellingofthecraniofacialcomplexusingmachinelearningon2dcephalometricradiographs AT hakanturkkahraman longtermpredictivemodellingofthecraniofacialcomplexusingmachinelearningon2dcephalometricradiographs |