Non-Cochrane · DTA · PM42587704
Artificial Intelligence for Diagnosis of Temporomandibular and Cranio-Cervico-Mandibular Musculoskeletal Disorders: A Systematic Review and Exploratory Diagnostic Test Accuracy Meta-Analysis.
Arbeláez Ramírez Arturo, Botero Rosas Daniel · Diagnostics (Basel, Switzerland) · 2026 · PubMed · doi:10.3390/diagnostics16152468
Findings
Population Adults with suspected or confirmed TMJ osteoarthritis (analytical unit: image or condyle)
6 findings
| AI-based image classification (deep learning) for TMJ osteoarthritis | Reference standard (CBCT or CT-supported expert radiological diagnosis) | Diagnostic accuracy: sensitivity Broad seven-study exploratory analysis including image-level cross-validation data (Supplementary Figure S1; later withdrawn in text) | Sensitivity 0.900 GRADE not reported 7 studies |
| AI-based image classification (deep learning) for TMJ osteoarthritis | Reference standard (CBCT or CT-supported expert radiological diagnosis) | Diagnostic accuracy: sensitivity Domain-specific expanded exploratory analysis: three TMJ osteoarthritis studies | Sensitivity 0.791 [0.700, 0.861] GRADE not reported 3 studies |
| AI-based image classification (deep learning) for TMJ osteoarthritis | Reference standard (CBCT or CT-supported expert radiological diagnosis) | Diagnostic accuracy: specificity Domain-specific expanded exploratory analysis: three TMJ osteoarthritis studies | Specificity 0.869 [0.811, 0.911] GRADE not reported 3 studies |
| AI-based image classification (deep learning) for TMJ osteoarthritis | Reference standard (CBCT or CT-supported expert radiological diagnosis) | Diagnostic accuracy: specificity Strict analysis: two studies with explicit 2x2 data | Specificity 0.864 [0.767, 0.925] GRADE not reported 2 studies |
| AI-based image classification (deep learning) for TMJ osteoarthritis | Reference standard (CBCT or CT-supported expert radiological diagnosis) | Diagnostic accuracy: specificity Broad seven-study exploratory analysis including image-level cross-validation data (Supplementary Figure S1; later withdrawn in text) | Specificity 0.914 [0.850, 0.952] GRADE not reported 7 studies |
| AI-based image classification (deep learning) for TMJ osteoarthritis | Reference standard (CBCT or CT-supported expert radiological diagnosis) | Diagnostic accuracy: sensitivity Strict analysis: two studies with explicit 2x2 data | Sensitivity 0.748 [0.688, 0.801] GRADE not reported 2 studies |
Included primary studies 7
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 | PM42587704-P2-O1 | not extracted yet |
| Nozawa 2025 Can temporomandibular joint osteoarthritis be diagnosed on MRI proton density-weighted images with diagnostic support from the latest deep… PMID:39067043 | 2025 | 1 other review | Diagnostic accuracy: sensitivity | not extracted yet |
| Choi 2021 Artificial intelligence in detecting temporomandibular joint osteoarthritis on orthopantomogram. PMID:33986459 | 2021 | this review only | Diagnostic accuracy: sensitivity | not extracted yet |
| Fang 2023 Machine-learning-based detection of degenerative temporomandibular joint diseases using lateral cephalograms. PMID:36710061 | 2023 | this review only | PM42587704-P2-O1 | not extracted yet |
| Lee 2020 Automated Detection of TMJ Osteoarthritis Based on Artificial Intelligence. PMID:32609562 | 2020 | this review only | Diagnostic accuracy: sensitivity | not extracted yet |
| Lin 2022 Automatic detection of anteriorly displaced temporomandibular joint discs on magnetic resonance images using a deep learning algorithm. PMID:34788124 | 2022 | this review only | not stated | not extracted yet |
| Yu 2024 Deep learning-based automated diagnosis of temporomandibular joint anterior disc displacement and its clinical application. PMID:39735724 | 2024 | 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 question
| Element | Planned (methods) | Found (results) |
|---|---|---|
| Population | Human adults aged 18 years or older with suspected or confirmed TMD, TMJ pathology, condylar abnormality, disc displacement, degenerative joint disease, masticatory muscle disorder or CCM musculoskeletal condition | Adults with TMJ osteoarthritis in 3 pooled studies |
| Intervention | AI-based diagnostic methods (machine learning, deep learning, CNN, radiomics, vision transformers, multimodal models) | AI classification of TMJ osteoarthritis on CBCT, orthopantomogram and MRI (n=3) |
| Comparison | Reference standards: MRI, CBCT or CT, DC/TMD or expert clinical diagnosis, expert radiological interpretation, ultrasonography, electromyography, jaw tracking | CBCT-based expert classification, CBCT reference, CT-supported radiological diagnosis (n=3) |
| Outcomes | Sensitivity, specificity, accuracy, AUC, likelihood ratios, diagnostic odds ratio, predictive values, 2x2 data | Pooled sensitivity and specificity (n=3); strict 2-study analysis also reported |
| Study designs | Published studies in English or Spanish; diagnostic accuracy and AI studies | Diagnostic accuracy studies (n=3 pooled; 21 potential DTA candidates) |
| Timing | Not specified | Not specified |