Explaining an increase in predicted risk for clinical alerts
Michaela Hardt, Alvin Rajkomar, Gerardo Flores, Andrew M. Dai, Michael D. Howell, Greg S. Corrado, Claire Murong Cui, Moritz Hardt · 2020
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.