ARTIFICIAL INTELLIGENCE IN EARLY DETECTION OF TEMPOROMANDIBULAR JOINT DISORDERS-A SYSTEMATIC REVIEW
Bibliographic record
Abstract
Background: Temporomandibular joint disorders (TMDs) affect a significant portion of the population and are a leading cause of chronic orofacial pain and functional limitation. Early diagnosis is crucial for effective intervention, yet conventional diagnostic methods often fall short in accuracy and accessibility. Recent advancements in artificial intelligence (AI) offer a novel approach to early detection through enhanced image analysis, but existing evidence is scattered and lacks systematic synthesis. Objective: This systematic review aims to evaluate the effectiveness and diagnostic performance of AI-based tools in the early identification of temporomandibular joint disorders. Methods: A systematic review was conducted following PRISMA guidelines. Databases searched included PubMed, Scopus, Web of Science, and the Cochrane Library, covering studies published between January 2018 and April 2024. Inclusion criteria encompassed human studies utilizing AI for TMD diagnosis through imaging modalities such as MRI, CBCT, or panoramic radiographs. Exclusion criteria included non-English articles, animal studies, and reviews. Data extraction focused on study design, population, AI model used, imaging type, and diagnostic outcomes. Risk of bias was assessed using the Newcastle-Ottawa Scale and Cochrane tools. Results: Eight studies involving 2,138 participants were included. AI models—primarily convolutional neural networks and deep learning systems—achieved high diagnostic performance with accuracy ranging from 85.7% to 92.3%, sensitivity between 88.0% and 94.1%, and AUC values up to 0.96. Most tools matched or exceeded the diagnostic capabilities of human experts. Risk of bias was low to moderate, though some concerns regarding model validation and blinding were noted. Conclusion: AI-based diagnostic systems demonstrate strong potential for early and accurate detection of TMDs, offering a valuable adjunct to clinical decision-making. However, larger, externally validated studies are needed to support widespread clinical implementation and ensure reproducibility.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.010 | 0.043 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.008 | 0.009 |
| Bibliometrics | 0.008 | 0.007 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".