Predicting joint space changes in knee osteoarthritis over 6 years: a combined model of TransUNet and XGBoost.

Abstract

Background: The progression of knee osteoarthritis is mainly characterized by the reduction in joint space width (JSW). The goal of this study was to build a knee joint space segmentation model through deep learning (DL) methods and develop a model for automatically measuring JSW. Furthermore, we predicted JSW changes in the sixth year based on regression models.

Methods: The data for this study was sourced from the Osteoarthritis Initiative database. We filtered knee X-ray images from 1,947 participants and tested six neural networks for segmentation to build an automatic JSW measurement model. Subsequently, we combined the clinical data with the JSW measurement results to predict the sixth-year knee JSW using six different regression models.

Results: The segmentation results showed that TransUNet performed the best, with an overall Dice coefficient of 0.889. The intraclass correlation coefficient (ICC) between manually measured and TransUNet's automatically measured JSW reached 0.927 (P<0.01). Among the regression models, eXtreme Gradient Boosting (XGBoost) demonstrated the best predictive performance, with a mean absolute error (MAE) of 0.48 and an ICC of 0.887 (P<0.01). To better align with clinical practice, we reduced the prediction model to utilize only 2 years of JSW images. The results showed that using the 0- and 12-month X-ray images still achieved high accuracy, with an MAE of 0.585 (P<0.05) and an ICC of 0.805 (P<0.01).

Conclusions: We developed a novel JSW measurement model that significantly improves accuracy compared to previous methods and identified the best prediction model by combining TransUNet and XGBoost. Additionally, in our built model, predicting the 72-month JSW using only 2 years of knee X-ray images and several clinical features achieved high accuracy.