Actionable Recourse via GANs for Mobile Health

TL;DR

This paper explores the use of GAN-generated counterfactuals to provide actionable recourse in mobile health apps, enabling users and stakeholders to understand and influence predicted health outcomes.

Contribution

It introduces a novel method leveraging GANs to generate plausible counterfactuals for mobile health predictions, enhancing user agency and causal understanding.

Findings

GAN-based recourse is feasible for mobile health predictions

Counterfactuals help identify actionable features to influence outcomes

Method improves interpretability of engagement predictions

Abstract

Mobile health apps provide a unique means of collecting data that can be used to deliver adaptive interventions.The predicted outcomes considerably influence the selection of such interventions. Recourse via counterfactuals provides tangible mechanisms to modify user predictions. By identifying plausible actions that increase the likelihood of a desired prediction, stakeholders are afforded agency over their predictions. Furthermore, recourse mechanisms enable counterfactual reasoning that can help provide insights into candidates for causal interventional features. We demonstrate the feasibility of GAN-generated recourse for mobile health applications on ensemble-survival-analysis-based prediction of medium-term engagement in the Safe Delivery App, a digital training tool for skilled birth attendants.