Fig. 1

Workflow for clinical data analysis and AI-driven applications in OA: the process begins with data acquisition from various clinical sources, including basic demographic data, clinical visit records, laboratory test results, and electronic medical records (a). These data are analyzed using machine learning (e.g., Random Forest, SVM, XGBoost, K-NN) and deep learning methods (e.g., deep neural networks, convolutional neural networks, U-Net) to identify latent pathological features and risk factors associated with OA (b). The resulting insights are applied to a range of clinical tasks, such as OA risk prediction, surgery prediction, recovery prediction, and other applications, facilitating early screening, personalized treatment strategies, and improved patient outcomes (c)