本研究针对幼年特发性关节炎 (JIA)患者颞下颌关节 (TMJ)受累临床检测准确性不足的问题，开发了一种基于XGBoost的机器学习模型。该模型通过分析26项临床特征，在独立测试集上达到85.5%的准确率，显著优于常规临床检查。SHAP分析显示髁状突活动度、面部不对称性等为关键预测特征，为JIA相关TMJ疾病的早期诊断提供了可靠工具。

A Global Phenomenon in Addressing TMJ Disorder and Related Health IssuesWilmington, DE, Nov. 06, 2025 (GLOBE NEWSWIRE) -- ...

November 11, 2025) - Dental & TMJ Specialists of Greater DC has formally announced the addition of Dr. Nicole Newberry, DMD, MS, FACP, to its clinical team. The announcement marks a key development ...

Jawad Abbas explains why taking a 'short diagnostic pause' has completely transformed the outcomes of TMJ patients.