Related Experiment Video
Updated: Aug 16, 2026
07:32
Measuring Maxillary Posterior Tooth Movement: A Model Assessment using Palatal and Dental Superimposition
Published on: February 23, 2024
Validity of Using Artificial Intelligence to Predict Skeletal Maturation in Orthodontic Treatment: A Systematic
Gita Gayatri1,2, Endah Mardiati2, Ani Melani3,4
1Doctoral Program, Faculty of Medicine, Universitas Padjadjaran, Bandung, Indonesia.
European Journal of Dentistry
|August 14, 2026
Summary
Artificial intelligence (AI) shows promise for skeletal maturation assessment using cervical vertebral maturation (CVM) and hand-wrist radiography. While AI models demonstrate good performance, further studies are needed for routine clinical use.
Area of Science:
- Radiology
- Artificial Intelligence
- Orthodontics
Background:
- Skeletal maturation assessment is crucial in orthodontics and pediatric dentistry.
- Current methods rely on manual interpretation of radiographs, which can be subjective.
- AI offers potential for objective and efficient skeletal age estimation.
Purpose of the Study:
- To systematically review and evaluate AI and rule-based methods for skeletal maturation assessment.
- To assess the performance and clinical validation of AI in analyzing cervical vertebral maturation (CVM) and hand-wrist radiographs.
- To compare AI-derived classifications with expert assessments.
Main Methods:
- Systematic review following PRISMA 2020 guidelines, registered in PROSPERO.
- PICOS framework for study selection (experimental, RCTs, observational studies using AI on CVM or hand-wrist radiographs).
- Systematic search across major databases (PubMed, Scopus, EBSCOhost, SpringerLink) from 2015-2025; QUADAS-2 for quality assessment; meta-analysis for CVM studies.
Main Results:
- Seven studies met criteria (5 CVM, 2 hand-wrist).
- CVM-based AI models showed moderate to high performance (pooled accuracy 80%, kappa up to 0.985), comparable to human experts in some cases.
- Hand-wrist AI models demonstrated high agreement with experts (r up to 0.98, MAE < 6 months).
Conclusions:
- AI shows potential as a diagnostic support tool for skeletal maturation assessment.
- Performance varies by AI model and validation setting; hand-wrist models show stable reproducibility.
- Further prospective, multicenter studies are necessary before routine clinical implementation due to limited evidence and heterogeneity.
