Related Experiment Video
Updated: Jun 14, 2026
07:32
Measuring Maxillary Posterior Tooth Movement: A Model Assessment using Palatal and Dental Superimposition
Published on: February 23, 2024
AI in orthodontic treatment planning: a systematic review comparing learning approaches
By Martin Baxmann1, Márton Zsoldos2, Krisztina Kárpáti2
1Department of Orthodontics and Paediatric Dentistry, Faculty of Dentistry, University of Szeged, Szeged, H-6720, Hungary. info@orthodentix.de.
BMC Oral Health
|June 13, 2026
Summary
Artificial intelligence (AI) systems show promise in orthodontic treatment planning, often matching expert clinician accuracy for specific tasks. However, further validation is needed before widespread clinical adoption.
Area of Science:
- Orthodontics
- Artificial Intelligence
- Machine Learning
- Clinical Decision Support
Background:
- Orthodontic diagnosis and treatment planning involve complex decisions with practitioner variability.
- Artificial intelligence (AI) is increasingly applied to aid these complex clinical decisions.
- This review evaluates AI and knowledge-based systems in orthodontic treatment planning.
Purpose of the Study:
- To evaluate AI and knowledge-based systems for orthodontic treatment planning.
- To compare AI system performance against expert clinicians.
- To examine how learning approaches affect AI accuracy, interpretability, and clinical integration.
Main Methods:
- Systematic search of major databases (PubMed, Embase, Scopus, etc.) up to October 2025.
- Included studies used AI/knowledge-based systems with real patient data for diagnosis/planning.
- Risk of bias assessed using ROBINS-I; findings synthesized narratively.
Main Results:
- Nineteen studies met criteria, mostly using supervised machine learning for extraction decisions or classification.
- AI systems reported accuracies often exceeding 80%, sometimes surpassing 90% compared to experts.
- Knowledge-based systems offered transparency, while data-driven models showed higher performance; moderate to serious risk of bias noted.
Conclusions:
- AI systems can approximate expert orthodontic decision-making for specific tasks.
- Current evidence is limited by methodological weaknesses and lack of prospective validation.
- AI should be considered adjunctive decision-support tools, not autonomous planners, pending further research.
