Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Transformers with Off-Nominal Turns Ratios01:25

Transformers with Off-Nominal Turns Ratios

In scenarios involving parallel transformers with disparate ratings, developing per-unit models requires accommodating off-nominal turns ratios. This situation arises when the selected base voltages are not proportional to the transformer’s voltage ratings. Consider a transformer where the rated voltages are related by the term a. If the chosen voltage bases satisfy a relationship involving term b, term c is defined as the ratio of these bases. This ratio is then substituted into the rated...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Clinical and MRI markers for acute vs chronic temporomandibular disorders using a machine learning and deep neural networks.

Communications medicine·2025
Same author

Oral Candidiasis Associated with Aging and Salivary Hypofunction in Stomatitis Patients.

Journal of fungi (Basel, Switzerland)·2025
Same author

AI in Learning Anatomy and Restoring Central Incisors: A Comparative Study.

Journal of dental research·2025
Same author

Oral Microbial Changes in Oral Squamous Cell Carcinoma: Focus on <i>Treponema denticola</i>, <i>Lactobacillus casei</i>, and <i>Candida albicans</i>.

Medicina (Kaunas, Lithuania)·2024
Same author

Publicly Available Dental Image Datasets for Artificial Intelligence.

Journal of dental research·2024
Same author

A Deep Learning System to Predict Epithelial Dysplasia in Oral Leukoplakia.

Journal of dental research·2024

Related Experiment Video

Updated: Jun 23, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.3K

TMD Diagnosis Using a Masked Self-Supervised Tabular Transformer.

Y-H Lee1,2, J H Lee3, Q-S Auh1

  • 1Department of Orofacial Pain and Oral Medicine, Kyung Hee University, Kyung Hee University Dental Hospital, Seoul, Korea.

Journal of Dental Research
|October 24, 2025
PubMed
Summary

A novel deep learning model, Gated Attention Tabular Transformer (GATT), accurately classifies temporomandibular disorders (TMDs) subgroups using structured clinical data. This AI tool aids in standardized TMD diagnosis and management without requiring imaging.

Keywords:
algorithmsartificial intelligencedecision makingdeep learningdiagnosistemporomandibular disorder (TMD)

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

732

Related Experiment Videos

Last Updated: Jun 23, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.3K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

732

Area of Science:

  • Artificial Intelligence in Medicine
  • Machine Learning for Healthcare
  • Computational Biology and Bioinformatics

Background:

  • Temporomandibular disorders (TMDs) are complex musculoskeletal conditions affecting the temporomandibular joint (TMJ) and associated structures.
  • Diagnosis of TMDs is challenging due to symptom overlap, multifactorial causes, and clinical variability.
  • Existing diagnostic criteria for TMDs (DC/TMD) require structured data for accurate classification.

Purpose of the Study:

  • To develop and evaluate a novel deep-learning model, the Gated Attention Tabular Transformer (GATT), for classifying TMD subgroups.
  • To assess GATT's performance against conventional and advanced machine-learning methods using structured clinical data.
  • To identify key clinical features contributing to TMD diagnoses through explainable AI methods.

Main Methods:

  • Development of the Gated Attention Tabular Transformer (GATT), a deep-learning model employing masked self-supervised learning and gated attention.
  • Analysis of 4,644 structured clinical records from a university registry, covering 12 core TMD subgroups.
  • Performance evaluation using receiver operating characteristic (ROC) curves, sensitivity, specificity, and comparison with logistic regression, random forest, SVM, XGBoost, TabNet, TabTransformer, AutoGluon, and FT-Transformer.

Main Results:

  • GATT demonstrated robust diagnostic performance across TMD subgroups, with ROC AUC values from 0.815 to 1.000.
  • The model significantly outperformed all compared conventional and advanced machine-learning methods.
  • Shapley Additive Explanations (SHAP) identified 'pain-free opening' and 'current TMJ noise' as key features for mechanical TMDs.

Conclusions:

  • Deep learning, specifically the GATT model, can effectively classify heterogeneous TMD subgroups using only structured clinical data, eliminating the need for imaging.
  • GATT provides an accurate, explainable, and scalable tool to support clinician-assisted TMD diagnosis and reduce management variability.
  • Integration of AI tools like GATT into clinical workflows can standardize and enhance the efficiency of patient-specific TMD diagnosis and care.