Figure 4
From: Machine learning analysis of serum cholesterol's impact on knee osteoarthritis progression
SHAP interpretation model. (a) Attributes of features in SHAP. Each line represents a feature and the horizontal coordinate is the SHAP value. Red dots indicate higher feature values and blue dots indicate lower feature values. SHAP values represent the predictive features of individual patients and the contribution of each patient to the predictive progress. The length of the arrows helps to visualize how much the prediction is affected. The longer the arrow, the greater the effect. (b) Dot plot of the correlation between the "risk factor TC" and the distribution of the scatterplot, which shows that the risk of KOA progression increases after a TC greater than 200 mg/dl.
