{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T18:53:53Z","timestamp":1773341633890,"version":"3.50.1"},"reference-count":0,"publisher":"MRE Press","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,12]]},"abstract":"<jats:p>Background: Early and accurate diagnosis of adolescent temporomandibular joint (TMJ) osteoarthritis (OA) is critical, as degenerative changes during growth can cause lifelong pain and deformity. This study aimed to identify key clinical and imaging predictors of adolescent TMJ-OA and to evaluate multimodal machine learning models. Methods: The diagnostic utility was evaluated in 79 adolescents (10\u201318 years) with TMJ pain using panoramic radiography (PR) and MRI. TMJ-OA was diagnosed based on the Diagnostic Criteria for Temporomandibular Disorders (DC\/TMD). Three decision tree models were developed: Model 1 (clinical-only), Model 2 (imaging-only), and Model 3 (combined clinical and imaging). Logistic regression was used for the comparisons. Results: To ensure a robust evaluation with a small sample size (n = 79), the models were assessed using nested 5-fold cross-validation. Model 2 (imaging only) had the highest specificity (0.7714 \u00b1 0.2321), accuracy (0.5942 \u00b1 0.0966), and AUROC (0.719\u00b1 0.101), but a low sensitivity (0.4472 \u00b1 0.2065). PR evidence of TMJ-OA (feature importance = 0.70\u037e OR = 3.93) was the strongest predictor and root node in the decision tree. Model 3 (combined clinical and imaging data) showed improved sensitivity (0.6056\u00b1 0.1829), identifying PR_TMJ_OA, MRI_TMJ_ADD (anterior disc displacement), Visual Analog Scale (VAS) score, and age as key nodes (AUROC = 0.6573 \u00b1 0.0338\u037e OR = 2.85 for PR_TMJ_OA). Model 1 (clinical-only) had limited predictive performance (AUROC = 0.4859 \u00b1 0.0894), with symptom duration (importance = 0.64\u037e OR = 1.40), VAS score, and joint locking (importance = 0.20) contributing modestly. A model using PR_TMJ_OA alone achieved perfect specificity (0.9714 \u00b1 0.0571) but low sensitivity (0.3806 \u00b1 0.1458). Conclusions: Although PR is a meaningful screening tool for adolescent TMJ-OA, it remains insufficient as a standalone diagnostic modality. Multimodal integration of clinical and MRI findings improves diagnostic accuracy and provides interpretable, clinically aligned decision-support tools for TMJ-OA.<\/jats:p>","DOI":"10.22514\/jofph.2026.021","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T09:28:57Z","timestamp":1773307737000},"page":"64","source":"Crossref","is-referenced-by-count":0,"title":["Decoding adolescent TMJ osteoarthritis with multimodal machine learning"],"prefix":"10.22514","author":[{"given":"Yeon-Hee","family":"Lee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"26027","published-online":{"date-parts":[[2026,3,12]]},"container-title":["Journal of Oral &amp; Facial Pain and Headache"],"original-title":[],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T09:28:57Z","timestamp":1773307737000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jofph.com\/articles\/10.22514\/jofph.2026.021"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,12]]},"references-count":0,"URL":"https:\/\/doi.org\/10.22514\/jofph.2026.021","relation":{},"ISSN":["2333-0384","2333-0376"],"issn-type":[{"value":"2333-0384","type":"print"},{"value":"2333-0376","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,12]]}}}