Related Experiment Video
Updated: May 17, 2025
Guided Endodontics: Three-Dimensional Planning and Template-Aided Preparation of Endodontic Access Cavities
Published on: May 24, 2022
Diagnosis of In Vivo Vertical Root Fracture in Endodontically Treated Teeth Using Machine Learning Techniques.
Shujun Ran1, Qiang Wang2, Jia Wang1
1Department of Endodontics and Operative Dentistry, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, College of Stomatology, Shanghai Jiao Tong University, National Center for Stomatology, National Clinical Research Center for Oral Disease, Shanghai Key Laboratory of Stomatology, Shanghai, China.
Machine learning models accurately diagnose vertical root fractures (VRF) in endodontically treated teeth using clinical data and cone beam CT scans. These models aid clinical decisions for better patient outcomes.
Area of Science:
- Dentistry
- Medical Imaging
- Machine Learning
Background:
- Vertical root fracture (VRF) is a common complication in endodontically treated teeth.
- Accurate diagnosis of VRF is crucial for effective treatment planning and prognosis.
Purpose of the Study:
- To develop and evaluate machine learning models for diagnosing VRF.
- To utilize clinical features and cone beam computed tomography (CBCT) bone loss information for VRF detection.
Main Methods:
- A retrospective study included 941 endodontically treated teeth from 887 patients.
- Clinical factors and CBCT-derived bone defects were analyzed.
- Linear (logistic regression) and nonlinear (XGBoost, LightGBM, CatBoost) machine learning models were employed and validated using 5-fold cross-validation.
Main Results:
- 112 cases (11.9%) of VRF were identified.
- XGBoost and LightGBM models demonstrated high performance (AUC ~0.98), with excellent specificity and good sensitivity and precision.
- Key diagnostic features included lingual/buccal bone defect, defect height ratio, defect width, and patient age.
Conclusions:
- Machine learning models integrating patient age, sex, tooth type, root canal filling quality, and bone loss parameters show significant value.
- These models can assist clinicians in making informed decisions for managing endodontically treated teeth with suspected VRF.
