Fig. 4From: Identification of parameters and formulation of a statistical and machine learning model to identify Babesia canis infections in dogs using available ADVIA hematology analyzer dataFeature importances of the random forest model determined on the train set in descending order. Each dot is a data point. The SHAP value indicates how much that feature contributes to the prediction of that data point, where large deviations from zero mean a larger contribution and positive values contribute toward a positive prediction of B. canis. Red (blue) colored dots refer to high (low) feature values. For instance, high values (red dots) of the feature %LUC(%) make it more likely a dog is infected with B. canis (positive SHAP value)Back to article page