Designing User-Centric Behavioral Interventions to Prevent Dysglycemia with Novel Counterfactual Explanations

TL;DR

This paper introduces ExAct, a novel model-agnostic framework that generates actionable counterfactual explanations to help prevent adverse health events like blood glucose spikes, leveraging adversarial learning and user preferences.

Contribution

ExAct is a new framework that combines adversarial learning and user preferences to generate effective, actionable counterfactual explanations for chronic disease prevention.

Findings

Achieves 82.8% validity in simulations

Outperforms state-of-the-art by at least 10% in counterfactual quality

Improves proximity of explanations by at least 6.6%

Abstract

Monitoring unexpected health events and taking actionable measures to avert them beforehand is central to maintaining health and preventing disease. Therefore, a tool capable of predicting adverse health events and offering users actionable feedback about how to make changes in their diet, exercise, and medication to prevent abnormal health events could have significant societal impacts. Counterfactual explanations can provide insights into why a model made a particular prediction by generating hypothetical instances that are similar to the original input but lead to a different prediction outcome. Therefore, counterfactuals can be viewed as a means to design AI-driven health interventions to not only predict but also prevent adverse health outcomes such as blood glucose spikes, diabetes, and heart disease. In this paper, we design \textit{\textbf{ExAct}}, a novel model-agnostic framework for generating counterfactual explanations for chronic disease prevention and management. Leveraging insights from adversarial learning, ExAct characterizes the decision boundary for high-dimensional data and performs a grid search to generate actionable interventions. ExAct is unique in integrating prior knowledge about user preferences of feasible explanations into the process of counterfactual generation. ExAct is evaluated extensively using four real-world datasets and external simulators. With $82.8\%$ average validity in the simulation-aided validation, ExAct surpasses the state-of-the-art techniques for generating counterfactual explanations by at least $10\%$. Besides, counterfactuals from ExAct exhibit at least $6.6\%$ improved proximity compared to previous research.