Fig. 1.

Example explanation obtained from LIME for a patient who was predicted to have a very high probability of dire outcome by a logistic regression model. The bar plot at the top left shows the predicted probability distribution for dire outcome. The bar plot on the right shows the explanation for the prediction. The explanation is limited to six top-ranked features by magnitude. The magnitude on the horizontal axis represents the weight of a feature in the LIME’s local regression model. Green bars represent the magnitude of predictors that support the predicted outcome, while red bars represent the magnitude of contradictory features. LIME, local interpretable model-agnostic explanations.