This is a model for predicting recurrence of breast cancer based on patient and tumor attributes. InterpretML explains the predictions (Guideline 11) by providing information about how a particular feature impacts it (Pattern 11B). In this example, we see how the tumor size impacts the score (in blue bars) for recurrent events (above zero). For example, tumor sizes lower than 19 are associated with negative scores, meaning no recurrent events. Image captured July 2020.
