A comprehensive patient-specific prediction model for temporomandibular joint osteoarthritis progression

2024年5月21日
Schematic representation for the steps of the TMJ OA prognosis prediction model’s development. (一)临床, 成像, and biological data were collected from the study subjects, 在基线, and utilized to create the OA Prognosis Prediction model. (B)临床 and 成像 data were collected, at follow-up visits, to label the training dataset with the changes of the participants’ health status following 2 to 3 y of conservative management.

Schematic representation for the steps of the TMJ OA prognosis prediction model’s development. (A)临床, 成像, and biological data were collected from the study subjects, 在基线, and utilized to create the OA Prognosis Prediction model. 

Schematic representation for the steps of the TMJ OA prognosis prediction model’s development. (一)临床, 成像, and biological data were collected from the study subjects, 在基线, and utilized to create the OA Prognosis Prediction model. (B)临床 and 成像 data were collected, at follow-up visits, to label the training dataset with the changes of the participants’ health status following 2 to 3 y of conservative management.

(B)临床 and 成像 data were collected, at follow-up visits, to label the training dataset with the changes of the participants’ health status following 2 to 3 y of conservative management.

这是什么??

Temporomandibular joint osteoarthritis (TMJ OA) is a common condition causing jaw pain and difficulty moving the jaw.

What problem does it aim to solve?

The study aimed to improve prediction of how TMJ OA progresses and how patients respond to treatment.

How does it work?

研究ers followed 106 patients, with 74 of them getting checked after 2 to 3 years of non-surgical treatment. This study identified a comprehensive set of clinical, quantitative 成像, and biological biomarkers for precise prediction of TMJ OA disease progression. 研究ers developed an open-source tool based on a robust method called Ensemble via Hierarchical Predictions through Nested cross-validation (EHPN), which surpassed the performance of the 48 models tested. The EHPN model achieved an F1 score of 0.82, indicating strong performance and reliability with new, 看不见的数据, and minimizing false positives and negatives.

What are the real-world implications?

The use of the EHPN model may revolutionize the standards of care, providing clinicians with an accurate tool for anticipating the future status of TMJ OA patients, thereby enhancing their decision-making process.

What are the next steps?

Further refinement of the model.

Source

“A comprehensive patient-specific prediction model for temporomandibular joint osteoarthritis progression”, Proceedings of the National Academy of Sciences USA 2024  Vol. 121  No. 8  

作者

Najla Al Turkestani
Department of Restorative Dentistry, Faculty of Dentistry, King Abdulaziz University, 吉达21589, 沙特阿拉伯

Department of Orthodontics and Pediatric Dentistry, School of Dentistry, University of Michigan, 安阿伯, MI 48109

李腾飞
Department of Psychiatry, The University of North Carolina at 教堂山分校, 教堂山分校, NC 27599

乔纳斯·比安奇
Department of Orthodontics, University of the Pacific, Arthur A. Dugoni School of Dentistry, San Francisco, CA 94103

玛赛拉Gurgel
Department of Orthodontics and Pediatric Dentistry, School of Dentistry, University of Michigan, 安阿伯, MI 48109

胡安-普列托
Department of Psychiatry, The University of North Carolina at 教堂山分校, 教堂山分校, NC 27599

希娜沙
Department of Psychiatry, The University of North Carolina at 教堂山分校, 教堂山分校, NC 27599

Erika Benavides
Department of Periodontics & Oral Medicine, School of Dentistry, University of Michigan, 安阿伯, MI 48109

菲比安娜Soki
Department of Periodontics & Oral Medicine, School of Dentistry, University of Michigan, 安阿伯, MI 48109

Yuji Mishina
Department of Biologic and Materials Sciences & Prosthodontics, School of Dentistry, University of Michigan, 安阿伯, MI 48109

Margherita Fontana
Department of Cariology, Restorative Sciences and Endodontics, School of Dentistry, University of Michigan, 安阿伯, MI 48109

Arvind饶
Department of Radiation Oncology, University of Michigan, 安阿伯, MI 48109
Department of Computational Medicine & Bioinformatics, School of Dentistry, University of Michigan, 安阿伯, MI 48109

性病朱
Department of Radiology and Biomedical 研究 Imaging Center, The University of North Carolina at 教堂山分校, 教堂山分校, NC 27599

露西娅Cevidanes
Department of Orthodontics and Pediatric Dentistry, School of Dentistry, University of Michigan, 安阿伯, MI 48109

Dugoni 研究 in the Spotlight