Primary study · included by 1 review

Haghnegahdar 2018

ProbableThe reviews cited this study without a PMID, DOI or NCT, so it is matched by first author and year. Two different studies by the same author in the same year could be merged here.

Included by

Comparing Traditional Versus AI-Assisted TMJ Disorder Management Approaches: A Systematic Review and Meta-Analysis.

Non-Cochrane · DTA · 2026 · cited as Haghnegahdar 2018 · Fig. 4 forest plot; Table 1

Outcome this study informs	Pooled effect	Evidence	Certainty
Pooled specificity AI-based diagnostic algorithms (machine learning, deep learning, radiomics) applied to CBCT, OPG, MRI or clinical data vs Traditional diagnostic reference standard (clinical examination per RDC/TMD or DC/TMD, expert radiologist or clinician consensus)	Specificity 0.766 [0.711, 0.814]	5 studies · 866 participants	GRADE not reported
Pooled sensitivity AI-based diagnostic algorithms (machine learning, deep learning, radiomics) applied to CBCT, OPG, MRI or clinical data vs Traditional diagnostic reference standard (clinical examination per RDC/TMD or DC/TMD, expert radiologist or clinician consensus)	Sensitivity 0.751 [0.703, 0.794]	5 studies · 866 participants	GRADE not reported
Pooled sensitivity AI-based diagnostic algorithms (machine learning, deep learning, radiomics) applied to CBCT, OPG, MRI or clinical data vs Traditional diagnostic reference standard (clinical examination per RDC/TMD or DC/TMD, expert radiologist or clinician consensus)	Change in pooled sensitivity (leave-one-out delta) -0.014	4 studies	GRADE not reported
Pooled specificity AI-based diagnostic algorithms (machine learning, deep learning, radiomics) applied to CBCT, OPG, MRI or clinical data vs Traditional diagnostic reference standard (clinical examination per RDC/TMD or DC/TMD, expert radiologist or clinician consensus)	Change in pooled specificity (leave-one-out delta) 0.036	4 studies	GRADE not reported

1 including review in total.