Counterfactual Reasoning for Fair Clinical Risk Prediction
This addresses fairness issues in healthcare AI for underrepresented groups, but it is incremental as it builds on existing fairness criteria and methods.
The paper tackles fairness in clinical risk prediction by developing an augmented counterfactual fairness criteria to extend group fairness to an individual level, using a variational autoencoder for counterfactual inference on electronic health records data for prolonged inpatient length of stay and mortality, though it notes a trade-off between fairness and predictive performance.
The use of machine learning systems to support decision making in healthcare raises questions as to what extent these systems may introduce or exacerbate disparities in care for historically underrepresented and mistreated groups, due to biases implicitly embedded in observational data in electronic health records. To address this problem in the context of clinical risk prediction models, we develop an augmented counterfactual fairness criteria to extend the group fairness criteria of equalized odds to an individual level. We do so by requiring that the same prediction be made for a patient, and a counterfactual patient resulting from changing a sensitive attribute, if the factual and counterfactual outcomes do not differ. We investigate the extent to which the augmented counterfactual fairness criteria may be applied to develop fair models for prolonged inpatient length of stay and mortality with observational electronic health records data. As the fairness criteria is ill-defined without knowledge of the data generating process, we use a variational autoencoder to perform counterfactual inference in the context of an assumed causal graph. While our technique provides a means to trade off maintenance of fairness with reduction in predictive performance in the context of a learned generative model, further work is needed to assess the generality of this approach.