EUVIMEDEUVIMED entdecken
Open Access

Decoding adolescent TMJ osteoarthritis with multimodal machine learning

Yeon-Hee Lee, Do-Hoon Kim, Akhilanand Chaurasia, Tae-Seok Kim, Fernando P S Guastaldi, Yung-Kyun Noh

Journal of Oral & Facial Pain and Headache · 12.03.2026 · 64

DOI: 10.22514/jofph.2026.021 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Oral & Facial Pain and Headache, online erschienen am 12.03.2026. Verfasst von Yeon-Hee Lee und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Orofacial Pain and Oral Medicine, College of Dentistry, Kyung Hee University Dental Hospital, Kyung Hee University, 02447 Seoul, Republ…. Hauptthemen laut MEDLINE: Machine Learning, Temporomandibular Joint Disorders, Osteoarthritis. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Ministry of Science and ICT (MSIT), Institute of Information & Communications Technology Planning & Evaluation (IITP), Kyung Hee University in 2025.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 (10–18 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 ± 0.2321), accuracy (0.5942 ± 0.0966), and AUROC (0.719± 0.101), but a low sensitivity (0.4472 ± 0.2065). PR evidence of TMJ-OA (feature importance = 0.70; 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± 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 ± 0.0338; OR = 2.85 for PR_TMJ_OA). Model 1 (clinical-only) had limited predictive performance (AUROC = 0.4859 ± 0.0894), with symptom duration (importance = 0.64; 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 ± 0.0571) but low sensitivity (0.3806 ± 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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningTemporomandibular Joint DisordersOsteoarthritisHumansAdolescentChildMagnetic Resonance ImagingFemaleMaleRadiography, PanoramicDecision TreesSensitivity and SpecificityPredictive Learning Models

Stichwörter der Autor:innen

AdolescentsDecision treesMachine learningMagnetic resonance imagingOsteoarthritisPanoramic radiographyTemporomandibular disorders

Autor:innen und Institutionen

  • Department of Orofacial Pain and Oral Medicine, College of Dentistry, Kyung Hee University Dental Hospital, Kyung Hee University, 02447 Seoul, Republic of Korea.
  • Center for Systems Biology, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA.
  • Department of Computer Science, Hanyang University, 04763 Seoul, Republic of Korea.
  • Department of Oral Medicine and Radiology, King George's Medical University, 226003 Lucknow, India.
  • Division of Oral and Maxillofacial Surgery, Department of Surgery, Massachusetts General Hospital, Harvard School of Dental Medicine, Boston, MA 02114, USA.
  • School of Computational Sciences, Korea Institute for Advanced Study (KIAS), 02455 Seoul, Republic of Korea.

Förderung

  • Ministry of Science and ICT (MSIT)
  • Institute of Information & Communications Technology Planning & Evaluation (IITP)
  • Kyung Hee University in 2025

Zitieren

APA

Lee, Y. H., Kim, D. H., Chaurasia, A., Kim, T. S., Guastaldi, F. P. S., & Noh, Y. K. (2026). Decoding adolescent TMJ osteoarthritis with multimodal machine learning. Journal of Oral & Facial Pain and Headache, 64. https://doi.org/10.22514/jofph.2026.021

Vancouver

Lee YH, Kim DH, Chaurasia A, Kim TS, Guastaldi FPS, Noh YK. Decoding adolescent TMJ osteoarthritis with multimodal machine learning. Journal of Oral & Facial Pain and Headache. 2026:64. doi:10.22514/jofph.2026.021

BibTeX
@article{Lee2026,
  author = {Lee, Yeon-Hee and Kim, Do-Hoon and Chaurasia, Akhilanand and Kim, Tae-Seok and Guastaldi, Fernando P S and Noh, Yung-Kyun},
  title = {Decoding adolescent TMJ osteoarthritis with multimodal machine learning},
  journal = {Journal of Oral & Facial Pain and Headache},
  year = {2026},
  pages = {64},
  doi = {10.22514/jofph.2026.021}
}
Kostenlos starten →