Fig. 5

SHAP summary graph of the XGboost model. A This diagram describes the dot estimation on the model output of the XGBoost model. Each dot represents an individual patient from the dataset. The colors represent the feature value, red represents the higher SHAP value of specific features, and blue represents the lower SHAP value of specific features. B Average absolute impact of variables on the output value of the XGBoost model (ranked in descending order of feature importance). Abbreviations: XGBoost, Extreme Gradient Boosting; SHAP, Shapley Additive Explanations; RBC, red blood cell count; NEU%, percentage of neutrophils; PLT, platelet count