Skip to main content
Fig. 16 | Alzheimer's Research & Therapy

Fig. 16

From: Data analysis with Shapley values for automatic subject selection in Alzheimer’s disease data sets using interpretable machine learning

Fig. 16

SHAP summary plot for the XGBoost model. No training subjects were excluded. SHAP summary plots aggregate the explanation of individual predictions of the entire training and test set. Each point visualizes a Shapley value for a subject and a feature. The color of the points depends on the feature values, and the horizontal axis shows the calculated Shapley values. The vertical axis represents both the features, ordered by the mean absolute Shapley values and their distribution. The positive class is pMCI

Back to article page