AUTHOR=Cui Yuchen , Kang Fujia , Li Xinpeng , Shi Xinning , Zhang Han , Zhu Xianchun 

TITLE=Predicting temporomandibular disorders in adults using interpretable machine learning methods: a model development and validation study

JOURNAL=Frontiers in Bioengineering and Biotechnology

VOLUME=Volume 12 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2024.1459903

DOI=10.3389/fbioe.2024.1459903

ISSN=2296-4185

ABSTRACT=This study aims to apply machine learning (ML) methods to identify risk factors for temporomandibular disorders (TMD) in adults and to develop and validate an interpretable risk prediction model for adult TMD. A total of 949 adults were included in the study. 5 different ML algorithms were used for model development and comparison, and feature selection was performed by feature importance ranking and feature decreasing methods. The performance of the random forest (RF) model was the best among the 5 ML models. An interpretable RF model was developed with 7 predictors (gender, malocclusion, unilateral chewing, chewing hard substances, grinding teeth, clenching teeth, and anxiety). The area under the receiver-operating-characteristic curves (AUC) of the model on the training set, internal validation set, and external test set were 0.892, 0.854, and 0.857, respectively, demonstrating good predictive performance. The calibration curves showed that the predictive probabilities of the model were in high agreement with the actual observations, and the decision curve analysis (DCA) showed that the model had high clinical utility. In addition, the Shapley additive explanations (SHAP) were used to enhance the interpretability of the model. This model provides clinicians with a practical and efficient tool for TMD risk assessment, aiding in more accurate prediction and evaluation of TMD risk in adults.