Predicting the Sagittal Occlusal Achievement of Compensatory Treatment for Skeletal Class III Malocclusion Using Machine Learning
- 주제(키워드) Malocclusion , Angle Class III , Orthodontics , Artificial Intelligence , Machine Learning , Decision Trees , XGBoost
- 주제(DDC) 617.6
- 발행기관 아주대학교 임상치의학대학원
- 지도교수 Hwa Sung Chae
- 발행년도 2026
- 학위수여년월 2026. 2
- 학위명 석사
- 학과 및 전공 임상치의학대학원 임상치의학과
- 실제URI http://www.dcollection.net/handler/ajou/000000035648
- 본문언어 영어
- 저작권 아주대학교 논문은 저작권에 의해 보호받습니다.
초록/요약
Objectives This study aimed to develop a machine learning (ML) model to predict camouflage orthodontic treatment success in patients with skeletal Class III malocclusion and to identify key predictors for treatment planning. Materials and Methods Overall, 100 adult patients aged < 50 years with skeletal Class III malocclusion treated using camouflage orthodontics were retrospectively analyzed. Treatment success was defined by: an overjet exceeding 2 mm, proper canine relationship, and appropriate molar relationship (as applicable). Four ML algorithms—Random Forest, Classification and Regression Trees, Neural Network, and XGBoost—were trained and evaluated using fivefold cross-validation. Cephalometric variables were analyzed before and after treatment, and model performance was assessed using the area under the curve, F1 score, and Matthews correlation coefficient. Results XGBoost demonstrated the highest predictive performance across all metrics, suggesting better generalization. A decision tree model showed that the sagittal position of the lower incisors (L1_x) and palatal length (Palatal L) were the most influential predictors. An L1_x of less than 76 mm and a Palatal L of 41 mm or greater were strongly associated with treatment success. Conclusion ML algorithms, particularly XGBoost, can predict the success of camouflage treatment for skeletal Class III malocclusion. Key predictors can guide treatment planning and support artificial intelligence-assisted orthodontic decisions. --- Key words : Malocclusion, Angle Class III; Orthodontics, Corrective; Artificial Intelligence; Machine Learning; Decision Trees; XGBoost
more목차
I. INTRODUCTION 1
II. MATERIALS AND METHODS 3
A. Study Population 3
B. Data Analysis 4
C. Machine Learning 7
III. RESULTS 9
IV. DISCUSSION 14
V. CONCLUSION 17
REFERENCES 18
SUPPLEMENTS Etc. 21
국문요약 27
