Artificial intelligence in orthodontics: clinical maturity, evidence gaps, and emerging applications-a narrative review.
13 affiliations
- 1Ziauddin University, Karachi, Pakistan.
- 2Dow International Dental College, Karachi, Pakistan.
- 3Shaheed Zulfikar Ali Bhutto Institute of Science and Technology University, Karachi, Pakistan.
- 4Rashid Latif Dental College, Lahore, Pakistan.
- 5Army Medical College, Rawalpindi, Pakistan.
- 6Bacha Khan Dental College, Mardan, Pakistan.
- 7Khyber Medical University, Peshawar, Pakistan.
- 8Margalla Institute of Health Sciences, Rawalpindi, Pakistan.
- 9Hamdan Bin Mohammed College of Dental Medicine (HBMCDM), Mohammed Bin Rashid University of Medicine and Health Sciences (MBRU), Dubai, United Arab Emirates.
- 10Future University in Egypt, Cairo, Egypt.
- 11University Hospital Schleswig-Holstein, Kiel, Germany.
- 12King Salman International University, El-Tor, Egypt.
- 13University Hospital Bonn, Bonn, Germany. [email protected].
Abstract
Artificial intelligence (AI) is rapidly transforming orthodontics by enhancing diagnostic accuracy, supporting clinical decision-making, and facilitating digital workflows. This narrative review provides a comprehensive overview of current AI technologies and their applications in orthodontics, including diagnostic imaging, treatment planning, treatment monitoring, patient communication, education, and emerging generative AI tools. The available evidence indicates that automated cephalometric landmark detection and cone-beam computed tomography (CBCT) segmentation have among the most advanced technical and external-validation evidence bases in orthodontic AI, whereas digital-model analysis has demonstrated high technical performance but more limited independent validation. However, no application met the predefined criteria for higher clinical maturity because prospective clinical effectiveness remained insufficiently established. Other emerging or experimental applications include AI-assisted treatment planning, remote monitoring, large language models (LLMs), and robotic systems, for which evidence remains predominantly retrospective, technical, feasibility-based, or early clinical. However, much of the current evidence is derived from retrospective studies, technical validation investigations, and proof-of-concept reports, with limited prospective clinical data demonstrating improvements in treatment quality, efficiency, or long-term patient outcomes. Important challenges remain regarding data quality, algorithmic bias, external validation, explainability, patient privacy, and regulatory oversight. Overall, AI should currently be regarded as a clinician-supervised decision-support tool rather than a replacement for professional expertise. Future progress is likely to depend on robust prospective clinical trials, transparent reporting, and responsible integration of AI into evidence-based orthodontic practice and the broader digital transformation of dentistry.
Related
- Advances in Multimodal Artificial Intelligence in Radiology: Data Integration, Foundation Models, and Clinical Applications-A Narrative Review.
- Generative Artificial Intelligence in Health Research and Care: A Narrative Review of Applications and Implications for Alzheimer’s Disease and Related Dementia
- Artificial Intelligence and Anatomical Variation: A Narrative Review of Detection, Classification, and Educational Applications.
- Artificial Intelligence in Liver Transplantation: Clinical Applications, Challenges, and Future Directions
- Clinical Translation of Artificial Intelligence in Oncology: Real-World Validation, Workflow Integration, and Precision Medicine Applications
BibTeX
@article{chandio2026artificial,
title = {{Artificial intelligence in orthodontics: clinical maturity, evidence gaps, and emerging applications-a narrative review.}},
author = {Kanza Chandio and Laiba Iftikhar and Anum Shehzad and Ifrah Rao and Minahil Waseem and Muhammad Anas and Muhammad Farrukh and Ammar Al Shalabi and Sameh Talaat and Sinan Sen and Fatma Hassanein and Tarek Elshazly},
journal = {The Saudi dental journal},
year = {2026},
month = oct,
doi = {10.1007/s44445-026-00249-6},
url = {https://europepmc.org/article/MED/42853348},
note = {CC BY},
}
RIS
TY - JOUR
TI - Artificial intelligence in orthodontics: clinical maturity, evidence gaps, and emerging applications-a narrative review.
AU - Kanza Chandio
AU - Laiba Iftikhar
AU - Anum Shehzad
AU - Ifrah Rao
AU - Minahil Waseem
AU - Muhammad Anas
AU - Muhammad Farrukh
AU - Ammar Al Shalabi
AU - Sameh Talaat
AU - Sinan Sen
AU - Fatma Hassanein
AU - Tarek Elshazly
PY - 2026
DA - 2026/10/09
JO - The Saudi dental journal
DO - 10.1007/s44445-026-00249-6
UR - https://europepmc.org/article/MED/42853348
AB - Artificial intelligence (AI) is rapidly transforming orthodontics by enhancing diagnostic accuracy, supporting clinical decision-making, and facilitating digital workflows. This narrative review provides a comprehensive overview of current AI technologies and their applications in orthodontics, including diagnostic imaging, treatment planning, treatment monitoring, patient communication, education, and emerging generative AI tools. The available evidence indicates that automated cephalometric landmark detection and cone-beam computed tomography (CBCT) segmentation have among the most advanced technical and external-validation evidence bases in orthodontic AI, whereas digital-model analysis has demonstrated high technical performance but more limited independent validation. However, no application met the predefined criteria for higher clinical maturity because prospective clinical effectiveness remained insufficiently established. Other emerging or experimental applications include AI-assisted treatment planning, remote monitoring, large language models (LLMs), and robotic systems, for which evidence remains predominantly retrospective, technical, feasibility-based, or early clinical. However, much of the current evidence is derived from retrospective studies, technical validation investigations, and proof-of-concept reports, with limited prospective clinical data demonstrating improvements in treatment quality, efficiency, or long-term patient outcomes. Important challenges remain regarding data quality, algorithmic bias, external validation, explainability, patient privacy, and regulatory oversight. Overall, AI should currently be regarded as a clinician-supervised decision-support tool rather than a replacement for professional expertise. Future progress is likely to depend on robust prospective clinical trials, transparent reporting, and responsible integration of AI into evidence-based orthodontic practice and the broader digital transformation of dentistry.
SN - 1013-9052
SN - 1658-3558
ER -