Artificial intelligence and machine learning in diagnosing and managing temporomandibular disorders: A systematic review and meta-analysis
Bibliographic record
Abstract
Background Artificial intelligence (AI) and machine learning (ML) models have recently emerged as promising tools for enhancing diagnostic accuracy. Objective To evaluate the diagnostic accuracy of AI/ML models in detecting TMDs through a systematic review and meta-analysis of existing literature. Methods A comprehensive search of electronic databases was conducted to identify studies assessing the diagnostic performance of AI/ML models in TMD diagnosis (PROSPERO-CRD420251035080). Data extraction and quality assessment were conducted independently by two reviewers using the AXIS tool for cross-sectional and Newcastle–Ottawa Scale for cohort studies. Meta-analysis of diagnostic accuracy was performed using pooled sensitivity, specificity, diagnostic odds ratio, and area under the curve. Statistical heterogeneity was assessed with the I 2 statistic. Results The systematic search identified 368 articles, of which 12 studies met inclusion criteria after screening. Risk of bias assessment showed most observational studies had low to unclear bias, while cross-sectional studies varied from moderate to high quality. Five studies were eligible for meta-analysis and they revealed that AI and machine learning models achieved a pooled sensitivity of 87.1 %(95 %CI:84.9 %–89.2 %) and specificity of 87.0 %(95 %CI:84.8 %–89.2 %) for TMD diagnosis. The diagnostic odds ratio was 45.1(95 %CI:30.5–66.8), with an area under the ROC curve of 0.96, indicating excellent diagnostic accuracy. Moderate heterogeneity I 2 = 38.7 %. Conclusion AI/ML models demonstrate excellent accuracy in differentiating patients with and without TMDs, reinforcing their potential as reliable diagnostic aids in clinical and screening settings. However, variability in input features and lack of standardized model development protocols highlight the need for future research focusing on validation across diverse populations and harmonization of diagnostic criteria.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.009 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".