Related Experiment Video
Updated: Aug 13, 2025
07:32
Author Spotlight: 3D Movement Assessment of Maxillary Posterior Teeth in Clear Aligner Treatment
Published on: February 23, 2024
1.2K
Machine Learning Predictive Model as Clinical Decision Support System in Orthodontic Treatment Planning
Jahnavi Prasad1, Dharma R Mallikarjunaiah1, Akshai Shetty1
1Department of Orthodontics and Dentofacial Orthopedics, DAPM R V Dental College and Hospital, Bengaluru 560078, Karnataka, India.
Dentistry Journal
|January 20, 2023
Summary
Machine learning models can predict orthodontic diagnosis and treatment plans with 84% accuracy. Advanced algorithms like Decision Tree and Random Forest show high efficacy, potentially aiding clinical decision support.
Area of Science:
- Orthodontics
- Artificial Intelligence
- Medical Informatics
Background:
- Orthodontic diagnosis and treatment planning require extensive clinical expertise.
- Machine learning (ML) offers pattern recognition capabilities for rapid expertise acquisition.
- ML can potentially reduce errors and variability in clinical decision-making.
Purpose of the Study:
- To develop a machine learning (ML) predictive model for orthodontic diagnosis and treatment planning.
- To assess the accuracy and efficacy of ML models in predicting treatment outcomes.
- To explore ML as a Clinical Decision Support System in orthodontics.
Main Methods:
- Utilized 700 orthodontic patient case records from the past decade.
- Developed four ML predictive model layers using seven algorithms.
- Split data into training and testing sets with 33 input and 11 output variables.
- Compared ML-predicted treatment plans against expert orthodontist decisions.
Main Results:
- The ML model achieved an overall average accuracy of 84% in predicting treatment plans.
- Decision Tree, Random Forest, and XGB classifier algorithms demonstrated the highest accuracy, ranging from 87-93%.
- ML models showed comparable efficacy to expert orthodontists in treatment planning.
Conclusions:
- Machine learning models show significant potential in orthodontic diagnosis and treatment planning.
- ML can serve as a valuable Clinical Decision Support System, enhancing accuracy and efficiency.
- Further development of ML in orthodontics is warranted for future clinical applications.
