Non-Cochrane · DTA · PM42046845
Comparing Traditional Versus AI-Assisted TMJ Disorder Management Approaches: A Systematic Review and Meta-Analysis.
Mehta Vini, Vathani Annie, Kamma Praveen Kumar Gonuguntla, et al. · Clinical and experimental dental research · 2026 · PubMed · doi:10.1002/cre2.70370
Findings
9 findings
| Population | ||||
|---|---|---|---|---|
| Patients with temporomandibular joint disorders (mostly TMJ osteoarthritis) | AI-based diagnostic models (machine learning or deep learning on imaging or clinical data) | Traditional diagnosis (clinical examination, DC/TMD, expert radiologist reading) | Accuracy Diagnostic accuracy of AI models for TMD · Leave-one-out sensitivity: omitting Study 3 | Change in pooled estimate when study omitted (delta) 0.019 GRADE not reported 4 studies |
| Patients with temporomandibular disorders (mostly TMJ osteoarthritis) | AI-based diagnostic algorithms (machine learning, deep learning, radiomics) applied to CBCT, OPG, MRI or clinical data | Traditional diagnostic reference standard (clinical examination per RDC/TMD or DC/TMD, expert radiologist or clinician consensus) | Pooled specificity Diagnostic accuracy of AI models for TMD/TMJ osteoarthritis on imaging | Specificity 0.766 [0.711, 0.814] GRADE not reported 5 studies · 866 participants |
| Patients with temporomandibular disorders (mostly TMJ osteoarthritis) | AI-based diagnostic algorithms (machine learning, deep learning, radiomics) applied to CBCT, OPG, MRI or clinical data | Traditional diagnostic reference standard (clinical examination per RDC/TMD or DC/TMD, expert radiologist or clinician consensus) | Normalized partial AUC (pAUC) Diagnostic accuracy of AI models for TMD/TMJ osteoarthritis on imaging | Normalized pAUC 0.729 GRADE not reported 5 studies · 866 participants |
| Patients with temporomandibular joint disorders (mostly TMJ osteoarthritis) | AI-based diagnostic models (machine learning or deep learning on imaging or clinical data) | Traditional diagnosis (clinical examination, DC/TMD, expert radiologist reading) | Accuracy Diagnostic accuracy of AI models for TMD · Leave-one-out sensitivity: omitting Study 1 | Change in pooled estimate when study omitted (delta) -0.012 GRADE not reported 4 studies |
| Patients with temporomandibular disorders (mostly TMJ osteoarthritis) | AI-based diagnostic algorithms (machine learning, deep learning, radiomics) applied to CBCT, OPG, MRI or clinical data | Traditional diagnostic reference standard (clinical examination per RDC/TMD or DC/TMD, expert radiologist or clinician consensus) | Area under the summary ROC curve (AUC) Diagnostic accuracy of AI models for TMD/TMJ osteoarthritis on imaging | AUC 0.813 GRADE not reported 5 studies · 866 participants |
| Patients with temporomandibular disorders (mostly TMJ osteoarthritis) | AI-based diagnostic algorithms (machine learning, deep learning, radiomics) applied to CBCT, OPG, MRI or clinical data | Traditional diagnostic reference standard (clinical examination per RDC/TMD or DC/TMD, expert radiologist or clinician consensus) | Pooled sensitivity Diagnostic accuracy of AI models for TMD/TMJ osteoarthritis on imaging | Sensitivity 0.751 [0.703, 0.794] GRADE not reported 5 studies · 866 participants |
| Patients with temporomandibular joint disorders (mostly TMJ osteoarthritis) | AI-based diagnostic models (machine learning or deep learning on imaging or clinical data) | Traditional diagnosis (clinical examination, DC/TMD, expert radiologist reading) | F1 score Diagnostic accuracy of AI models for TMD · Leave-one-out sensitivity: omitting Study 1 | Change in pooled estimate when study omitted (delta) -0.013 GRADE not reported 4 studies |
| Patients with temporomandibular disorders (mostly TMJ osteoarthritis) | AI-based diagnostic algorithms (machine learning, deep learning, radiomics) applied to CBCT, OPG, MRI or clinical data | Traditional diagnostic reference standard (clinical examination per RDC/TMD or DC/TMD, expert radiologist or clinician consensus) | Pooled sensitivity Diagnostic accuracy of AI models for TMD/TMJ osteoarthritis on imaging · Sensitivity analysis: leave-one-out omitting Study 1 | Change in pooled sensitivity (leave-one-out delta) -0.014 GRADE not reported 4 studies |
| Patients with temporomandibular disorders (mostly TMJ osteoarthritis) | AI-based diagnostic algorithms (machine learning, deep learning, radiomics) applied to CBCT, OPG, MRI or clinical data | Traditional diagnostic reference standard (clinical examination per RDC/TMD or DC/TMD, expert radiologist or clinician consensus) | Pooled specificity Diagnostic accuracy of AI models for TMD/TMJ osteoarthritis on imaging · Sensitivity analysis: leave-one-out omitting Study 3 | Change in pooled specificity (leave-one-out delta) 0.036 GRADE not reported 4 studies |
Included primary studies 15
Open in Studies| Study | Year | Also included by | Outcomes it informs here | Trial data |
|---|---|---|---|---|
| Haghnegahdar 2018 Diagnosis of Tempromandibular Disorders Using Local Binary Patterns. PMID:29732343 | 2018 | 1 other review | Pooled sensitivity | not extracted yet |
| Al Turkestani 2023 Osteoarthritis Diagnosis Integrating Whole Joint Radiomics and Clinical Features for Robust Learning Models Using Biological Privileged… DOI:10.1007/978-3-031-47425-5_18 | 2023 | this review only | not stated | not extracted yet |
| Bianchi 2020 Osteoarthritis of the Temporomandibular Joint can be diagnosed earlier using biomarkers and machine learning DOI:10.1038/s41598-020-64942-0 | 2020 | this review only | Pooled sensitivity; Pooled specificity | not extracted yet |
| Choi 2021 Artificial intelligence in detecting temporomandibular joint osteoarthritis on orthopantomogram DOI:10.1038/s41598-021-89742-y | 2021 | this review only | Pooled sensitivity; Pooled specificity | not extracted yet |
| de Dumast 2018 A web-based system for neural network based classification in temporomandibular joint osteoarthritis DOI:10.1016/j.compmedimag.2018.04.009 | 2018 | this review only | not stated | not extracted yet |
| Diniz de Lima 2022 Artificial intelligence and infrared thermography as auxiliary tools in the diagnosis of temporomandibular disorder DOI:10.1259/dmfr.20210318 | 2022 | this review only | not stated | not extracted yet |
| Haghnegahdar 2018 matched by author and year (probable) | NR | this review only | Pooled sensitivity; Pooled specificity | not extracted yet |
| Ito 2022 Automated segmentation of articular disc of the temporomandibular joint on magnetic resonance images using deep learning DOI:10.1038/s41598-021-04354-w | 2022 | this review only | not stated | not extracted yet |
| Kim 2020 Expert System for Mandibular Condyle Detection and Osteoarthritis Classification in Panoramic Imaging Using R-CNN and CNN DOI:10.3390/app10217464 | 2020 | this review only | not stated | not extracted yet |
| Lee 2022 Accuracy of deep learning-based integrated tooth models by merging intraoral scans and CBCT scans for 3D evaluation of root position… DOI:10.1186/s40510-022-00410-x | 2022 | this review only | Pooled sensitivity | not extracted yet |
| Mackie 2022 Quantitative bone imaging biomarkers and joint space analysis of the articular fossa in temporomandibular joint osteoarthritis using… DOI:10.3389/fdmed.2022.1007011 | 2022 | this review only | Pooled sensitivity; Pooled specificity | not extracted yet |
| Orhan 2021 Development and Validation of a Magnetic Resonance Imaging‐Based Machine Learning Model for TMJ Pathologies DOI:10.1155/2021/6656773 | 2021 | this review only | not stated | not extracted yet |
| Ribera 2019 Shape variation analyzer: a classifier for temporomandibular joint damaged by osteoarthritis DOI:10.1117/12.2506018 | 2019 | this review only | not stated | not extracted yet |
| Shoukri 2019 Minimally Invasive Approach for Diagnosing TMJ Osteoarthritis DOI:10.1177/0022034519865187 | 2019 | this review only | not stated | not extracted yet |
| Talaat 2023 An artificial intelligence model for the radiographic diagnosis of osteoarthritis of the temporomandibular joint DOI:10.1038/s41598-023-43277-6 | 2023 | this review only | not stated | not extracted yet |
Overlap with other reviews
Reviews that include the same primary studies are not independent evidence. Shared counts match studies by PMID, DOI or NCT, and otherwise by author and year (a probable match). Only the non-Cochrane dental reviews have study lists, so overlap with Cochrane reviews is not counted yet.
| Review | Shared studies | Jaccard |
|---|---|---|
| Artificial Intelligence for Diagnosis of Temporomandibular and Cranio-Cervico-Mandibular Musculoskeletal Disorders: A Systematic Review… (2026) | 1 | 0.05 |
Review question
| Element | Planned (methods) | Found (results) |
|---|---|---|
| Population | Patients diagnosed with temporomandibular disorders | Patients with TMJ disorders, mostly TMJ osteoarthritis, adults (n=14 studies; sample sizes 20 to 3514) |
| Intervention | AI-assisted (ML, DL, CAD) diagnosis or management approaches | AI models: ML classifiers and DL (CNN, ResNet, SSD, U-Net) on CBCT, MRI, OPG or clinical data (n=14) |
| Comparison | Traditional approaches (clinical examination, DC/TMD or RDC/TMD, conventional imaging, standard therapy) | Expert or radiologist reading and DC/TMD or RDC/TMD reference standards (n=14) |
| Outcomes | Diagnostic accuracy (sensitivity, specificity, accuracy), treatment outcomes, efficiency, safety | Sensitivity, specificity, accuracy, AUC; pooled in 5 studies |
| Study designs | Comparative studies, diagnostic accuracy studies, observational studies | Diagnostic accuracy and comparative studies (n=14) |
| Timing | Not specified | Not specified |