Orthodontics and Dentofacial Orthopedics

State of the evidence

The evidence establishes that clear aligner treatment (CAT) has limitations in predictability, particularly for complex movements, often requiring attachments to improve retention and movement control 1,3,4. AI and machine learning are demonstrating high accuracy in landmark identification and diagnosis, potentially matching or exceeding human experts 5,7,10. Precision in miniscrew placement is significantly enhanced through the use of CBCT-based stereolithographic surgical guides 9, though the reproducibility of 3D printing versus milling varies 8. Overall, the field is shifting toward a hybrid of AI-driven decision support and high-precision digital fabrication 6,7,10.

Key findings

• Clear aligners often fail to achieve planned tooth movements (torque, tip, rotation) without the use of composite attachments 3,4. 3 4
• Machine learning models can perform as well as or better than human experts in orthodontic landmark identification and diagnosis 7. 7
• Bayesian-based decision support systems can effectively assist general practitioners in assessing the need for orthodontic treatment 6. 6
• Stereolithographic surgical guides based on CBCT data significantly increase the precision of orthodontic miniscrew insertion and reduce root contact risk 9. 9
• AI applications in treatment planning can reduce inter- and intra-clinician variability and error 5,10. 5 10
• The predictability of clear aligners is lower in extraction cases, requiring multivariate analysis to understand the factors affecting movement 2. 2

Where the evidence disagrees

• Discrepancies exist regarding the relative precision and reproducibility of 3D printing versus milling for surgical guides 8.
• While AI shows high accuracy in controlled studies, there is a noted need for extensive upfront validation before clinical implementation of auto-segmentation tools 5,7.

Open opportunities

What the research supports that no idea in the catalog takes yet.

• AI-driven 'Refinement Predictor' for Clear Aligners

  Papers 2,4 highlight the gap between planned and achieved movement; a tool that predicts the likelihood of needing a refinement stage based on initial geometry could optimize planning.

• Automated Attachment Placement Optimizer

  Since attachments are critical for predictability 3 but their placement is a challenge, an AI tool that suggests optimal attachment shapes and positions based on the specific tooth movement required is missing.

• GP-to-Specialist Triage System for Orthodontic Need

  P5 demonstrates a Bayesian system for general practitioners to assess treatment needs; this could be scaled into a commercial triage platform to streamline referrals to orthodontists.

• CBCT-Integrated Real-time Miniscrew Navigation

  While static guides exist 9, the evidence on navigation techniques suggests a move toward dynamic guidance to further reduce root contact risk.

References

1. 1.Efficacy of clear aligners in controlling orthodontic tooth movement: A systematic reviewGabriele Rossini, Simone Parrini, Tommaso Castroflorio et al. · 2014 · 853 citations
2. 2.The predictability of orthodontic tooth movements through clear aligner among first-premolar extraction patients: a multivariate analysisLinghuan Ren, Lu Liu, Zhouqiang Wu et al. · 2022 · 99 citations
3. 3.Attachments for the Orthodontic Aligner Treatment—State of the Art—A Comprehensive Systematic ReviewMaciej Jedliński, Marta Mazur, Mario Greco et al. · 2023 · 66 citations
4. 4.Evaluation of Tooth Movement Accuracy with Aligners: A Prospective StudyVincenzo D’Antò, Rosaria Bucci, Vincenzo De Simone et al. · 2022 · 56 citations
5. 5.Artificial intelligence for orthodontic diagnosis and treatment planning: A scoping reviewRellyca Sola Gracea, Nicolas Winderickx, Michiel Vanheers et al. · 2024 · 60 citations
6. 6.Bayesian-Based Decision Support System for Assessing the Needs for Orthodontic TreatmentBhornsawan Thanathornwong · 2018 · 93 citations
7. 7.Machine learning in orthodontics: Challenges and perspectivesJialing Liu, Ye Chen, Shihao Li et al. · 2021 · 65 citations
8. 8.Assessment of the reproducibility and precision of milling and 3D printing surgical guidesSueli Mukai, Eduardo Mukai, José Arnaldo Santos-Junior et al. · 2021 · 95 citations
9. 9.Precise insertion of orthodontic miniscrews with a stereolithographic surgical guide based on cone beam computed tomography data: a pilot study.Camillo Morea, Jorge Elias Hayek, Cesar Oleskovicz et al. · 2011 · 38 citations
10. 10.Machine Learning Predictive Model as Clinical Decision Support System in Orthodontic Treatment PlanningJahnavi Prasad, Dharma Mallikarjunaiah, Akshai Shetty et al. · 2022 · 40 citations