Table 1.
Demographic characteristics of the patients.
Table 2.
Comparison of demographic and clinical characteristic, WOMAC, TUG SF-36, SAS and SDS of OA patients between early group (K/L 1-2) and late group (K/L 3-4) radiological stages.
Table 3.
Correlation between early group (K/L 1-2) and late group (K/L 3-4) radiological stages with age, course of disease, BMI, WOMAC, TUG, SF-36, SAS and SDS.
Table 4.
Results of logistic regressions of K/L score with Age, BMI, WOMAC, physical function and quality of life.
Fig 1.
(A) The importance of the 10 variables associated with the occurrence of OA risk. (B) The accuracy of the 10 variables associated with the occurrence of OA risk.
Fig 2.
The LASSO regression analysis used to identify factors associated with OA.
(A) The coefficient shrinkage process for all relevant variables, with changes in coefficients represented by lines of different colors, indicating the variations of each feature at different levels of shrinkage. (B) Ten-fold cross-validation of the LASSO regression model. LASSO: Least Absolute Shrinkage and Selection Operator.
Fig 3.
The establishment and validation of the OA risk prediction model.
(A) A nomogram model representing the eight factors associated with OA risk. (B) The ROC curve used to assess the nomogram model’s predictive ability for OA risk. *P < 0.05, **P < 0.01.