Reliable Decision Support using Counterfactual Models
This addresses the problem of unreliable decision-making in fields like healthcare by providing a more robust method for predicting outcomes under different actions, though it is incremental as it builds on existing counterfactual and temporal modeling concepts.
The paper tackles the unreliability of supervised learning for decision support by proposing a counterfactual learning objective, introducing the Counterfactual Gaussian Process (CGP) for temporal settings, and demonstrates benefits in risk prediction and treatment planning tasks.
Decision-makers are faced with the challenge of estimating what is likely to happen when they take an action. For instance, if I choose not to treat this patient, are they likely to die? Practitioners commonly use supervised learning algorithms to fit predictive models that help decision-makers reason about likely future outcomes, but we show that this approach is unreliable, and sometimes even dangerous. The key issue is that supervised learning algorithms are highly sensitive to the policy used to choose actions in the training data, which causes the model to capture relationships that do not generalize. We propose using a different learning objective that predicts counterfactuals instead of predicting outcomes under an existing action policy as in supervised learning. To support decision-making in temporal settings, we introduce the Counterfactual Gaussian Process (CGP) to predict the counterfactual future progression of continuous-time trajectories under sequences of future actions. We demonstrate the benefits of the CGP on two important decision-support tasks: risk prediction and "what if?" reasoning for individualized treatment planning.