Explaining an increase in predicted risk for clinical alerts
This work addresses the need for concise explanations to help clinicians quickly triage alerts when patient risk increases, though it is incremental in applying static attribution techniques to dynamic models.
The paper tackles the problem of explaining increases in predicted risk over time in clinical settings, developing methods to attribute risk rises to past inputs and evaluating their utility through expert assessment.
Much work aims to explain a model's prediction on a static input. We consider explanations in a temporal setting where a stateful dynamical model produces a sequence of risk estimates given an input at each time step. When the estimated risk increases, the goal of the explanation is to attribute the increase to a few relevant inputs from the past. While our formal setup and techniques are general, we carry out an in-depth case study in a clinical setting. The goal here is to alert a clinician when a patient's risk of deterioration rises. The clinician then has to decide whether to intervene and adjust the treatment. Given a potentially long sequence of new events since she last saw the patient, a concise explanation helps her to quickly triage the alert. We develop methods to lift static attribution techniques to the dynamical setting, where we identify and address challenges specific to dynamics. We then experimentally assess the utility of different explanations of clinical alerts through expert evaluation.