Data.xlsx

A total of 80 elderly women with knee OA were enrolled in this study. Radiographic severity was assessed with the Kellgren-Lawrence (K/L) scale, we divided the subjects into early (1-2) and late (3-4) according to the K/L stage. HRQoL assessment was conducted using the MOS item Short-Form 36 (SF-36). The association of HRQoL with knee OA severity was estimated using logistic regression. Applied a random forest model to assess the importance and accuracy of relevant variables in the occurrence of OA. The LASSO (Least Absolute Shrinkage and Selection Operator) regression was then used to identify key factors associated with OA, which were incorporated into the development of a risk prediction nomogram model. Furthermore, a receiver operating characteristic (ROC) curve was constructed to evaluate the model's discriminative ability for OA.