Skip to main content
Fig. 6 | BMC Cardiovascular Disorders

Fig. 6

From: A machine learning-based prediction model for postoperative delirium in cardiac valve surgery using electronic health records

Fig. 6

The SHAP summary plots of Random Forest Classifier under full feature set (A) and selected feature set (B). The higher the SHAP value of the feature, the higher the probability of delirium after surgery. A point is created for each attribution value of each feature of the model for each patient. Therefore, a point is assigned to each row of features for a patient. The points are colored based on the corresponding patient’s feature value and vertically accumulated to depict density. Red represents higher feature values, and blue represents lower feature values

Back to article page