Related Experiment Video
Updated: Jun 23, 2025
07:32
Author Spotlight: 3D Movement Assessment of Maxillary Posterior Teeth in Clear Aligner Treatment
Published on: February 23, 2024
1.1K
Comparison of Machine Learning Algorithms Fed with Mobility-Related and Baropodometric Measurements to Identify
Juri Taborri1, Luca Molinaro1, Luca Russo2
1Department of Economics, Engineering, Society and Business Organization (DEIM), University of Tuscia, 01100 Viterbo, Italy.
Sensors (Basel, Switzerland)
|June 19, 2024
Summary
This study explored using machine learning with portable sensors to diagnose temporomandibular disorders (TMDs). The k-nearest neighbours algorithm showed high accuracy in identifying TMD, suggesting a potential for objective clinical assessment.
Area of Science:
- Biomedical Engineering
- Computational Medicine
- Orthodontics
Background:
- Temporomandibular disorders (TMDs) are common conditions affecting jaw joint function and causing pain.
- Current TMD diagnosis relies on clinical assessment, questionnaires, and imaging, which can be subjective.
- Objective and accessible diagnostic tools for TMDs are needed.
Purpose of the Study:
- To investigate the feasibility of using machine learning algorithms with data from low-cost, portable instruments for TMD identification.
- To develop an objective method for measuring TMD presence in adult subjects.
Main Methods:
- Fifty participants (25 TMD, 25 healthy controls) were enrolled.
- Data collected included baropodometric analysis using a pressure matrix and cervical mobility evaluation via inertial sensors.
- Nine machine learning algorithms (SVM, k-NN, Decision Tree) were compared.
Main Results:
- The k-nearest neighbours algorithm, utilizing cosine distance, demonstrated superior performance.
- Achieved accuracy of 0.94, F1-score of 0.94, and G-index of 0.08.
- This algorithm effectively distinguished between TMD and healthy subjects.
Conclusions:
- Machine learning algorithms, particularly k-NN, show promise for objective TMD diagnosis.
- Low-cost, portable instruments combined with AI can support clinical TMD assessment.
- This approach could enhance diagnostic accuracy and accessibility in clinical settings.
