Related Experiment Video
Updated: Aug 12, 2025
Systematic Assessment of Mammalian Skull Specimens for Dental and Temporomandibular Joint Pathology
Published on: August 22, 2022
Machine-learning-based detection of degenerative temporomandibular joint diseases using lateral cephalograms
Xinyi Fang1, Xin Xiong2, Jiu Lin2
1State Key Laboratory of Oral Diseases, National Clinical Research Center for Oral Diseases, West China Hospital of Stomatology, Sichuan University, Chengdu, Sichuan, China; Department of Orthodontics, Hospital of Stomatology, Key Laboratory of Oral Biomedical Research of Zhejiang Province, School of Stomatology, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China.
This study developed a new tool to help dentists screen for degenerative temporomandibular joint diseases (DJD). The nomogram combines imaging data and patient information for early detection and management of DJD.
Area of Science:
- Dentistry
- Radiology
- Machine Learning
Background:
- Degenerative temporomandibular joint diseases (DJD) are prevalent in dental practice.
- Early detection of DJD is crucial for managing disease progression.
- Current diagnostic methods may lack efficiency in early-stage detection.
Purpose of the Study:
- To develop a cephalogram-based multidimensional nomogram for DJD screening.
- To integrate cephalometric parameters and clinical features for improved diagnostic accuracy.
- To provide a tool for early and effective DJD screening in dental settings.
Main Methods:
- Utilized cephalograms from 502 patients (332 with DJD, 170 normal).
- Extracted 36 cephalometric parameters for a machine-learning algorithm.
- Constructed a nomogram using multivariable logistic regression and validated its performance.
Main Results:
- Identified 22 cephalometric parameters (Ceph score) significantly associated with DJD (P < 0.01).
- The combined model (Ceph score + clinical features) achieved an AUC of 0.893.
- The model demonstrated strong performance in ROC, calibration, and decision curve analyses.
Conclusions:
- A validated multidimensional nomogram integrating Ceph scores and clinical features can aid in DJD screening.
- This tool shows potential for enhancing clinical screening of DJD in dental practice.
- Further research is recommended to confirm the model's reliability.
