Related Experiment Video
Updated: Jul 2, 2025
07:11
Treatment of Facial Deformities using 3D Planning and Printing of Patient-Specific Implants
Published on: May 23, 2020
7.4K
Machine learning-based decision support system for orthognathic diagnosis and treatment planning
Wen Du1,2, Wenjun Bi3, Yao Liu1
1State Key Laboratory of Oral Diseases & National Center for Stomatology & National Clinical Research Center for Oral Diseases, West China Hospital of Stomatology, Sichuan University, Chengdu, 610041, Sichuan, China.
BMC Oral Health
|February 28, 2024
Summary
Machine learning accurately diagnoses and plans surgeries for dento-maxillofacial deformities. This AI system improves diagnostic efficiency, especially in resource-limited settings, aiding treatment outcomes.
Area of Science:
- Oral and Maxillofacial Surgery
- Artificial Intelligence in Medicine
- Medical Diagnostics
Background:
- Dento-maxillofacial deformities present common clinical challenges.
- Orthodontic-orthognathic surgery is the standard treatment, requiring precise diagnosis and planning.
- Accurate diagnosis and surgical planning are crucial for optimal patient outcomes.
Purpose of the Study:
- To develop and validate a machine learning-based decision support system for treating dento-maxillofacial malformations.
- To compare the diagnostic performance of various machine learning algorithms.
- To evaluate an AI-driven approach for orthognathic surgical planning.
Main Methods:
- Trained diagnostic models using five machine learning algorithms on CT data from 574 patients.
- Compared diagnostic performance metrics (accuracy, sensitivity, specificity, AUC) against expert diagnoses.
- Utilized an adaptive artificial bee colony algorithm for surgical plan generation and evaluated it with maxillofacial surgeons on 50 patients.
Main Results:
- The extreme gradient boosting model achieved >90% diagnostic success for most deformities (except maxillary overdevelopment at 89.27%).
- Area Under the Curve (AUC) exceeded 0.88 across all diagnostic categories.
- AI-generated surgical plans showed no statistically significant difference compared to actual surgical plans, with median scores improving post-interaction.
Conclusions:
- Machine learning algorithms demonstrate high efficacy in diagnosing dento-maxillofacial deformities.
- AI-driven systems are effective for orthognathic surgical planning, enhancing diagnostic efficiency.
- This technology holds particular promise for improving care in medical centers with limited resources.
