Fig. 5

Feature importance analysis and interpretation of the ensemble model predictions. (a) SHAP summary plot showing the impact and distribution of each feature on model output. Red indicates higher feature values, while blue represents lower values. The x-axis represents the SHAP value impact on model predictions. (b) Boruta feature importance rankings displaying the relative importance of selected features in the final model. (c) SHAP force plot demonstrating the prediction process for a correctly identified treatment failure case. Features in red pushed the prediction toward treatment failure, while blue features opposed this prediction. (d) SHAP force plot illustrating the prediction process for a correctly predicted treatment success case. Features in red suggested treatment failure, while blue features supported treatment success