Related Experiment Video
Updated: Jun 8, 2025
05:56
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
Published on: April 14, 2023
2.4K
Using machine learning to classify temporomandibular disorders: a proof of concept.
Fernanda Pretto Zatt1, João Victor Cunha Cordeiro1, Lauren Bohner1
1Universidade Federal de Santa Catarina (UFSC), Departamento de Odontologia, Florianópolis, Brasil.
Journal of Applied Oral Science : Revista FOB
|November 6, 2024
Summary
Artificial intelligence, specifically machine learning, shows promise in diagnosing temporomandibular disorders (TMD). Decision tree models accurately classify joint and muscular pain, aiding general practitioners in diagnosis.
Area of Science:
- Dentistry
- Artificial Intelligence
- Machine Learning
Background:
- Temporomandibular disorders (TMD) present diagnostic challenges for non-specialists.
- Integrating AI can reduce diagnostic disparities in TMD.
- Accurate TMD diagnosis is crucial for effective patient management.
Purpose of the Study:
- Evaluate a machine-learning model for classifying TMD.
- Utilize the International Classification of Orofacial Pain (ICOP-1) for diagnosis.
- Assess AI's potential in aiding dental practitioners.
Main Methods:
- Developed a decision tree-based machine learning model.
- Used patient data from the Multidisciplinary Orofacial Pain Center (CEMDOR).
- Classified TMD into muscular or articular conditions based on ICOP-1.
Main Results:
- The model achieved 84% accuracy and 0.85 F1-score for joint pain classification.
- Myofascial pain classification reached 78% accuracy and 0.76 F1-score.
- Both models effectively used 2-5 clinical variables.
Conclusions:
- Decision tree-based machine learning supports TMD classification.
- AI tools can assist general practitioners in diagnosing TMD.
- This approach has significant potential for improving TMD diagnosis accuracy.
