Designing User-Centric Behavioral Interventions to Prevent Dysglycemia with Novel Counterfactual Explanations
This work addresses the problem of chronic disease prevention for users by offering personalized, actionable feedback, though it is incremental as it builds on existing counterfactual explanation methods.
The paper tackles the problem of predicting and preventing adverse health events like dysglycemia by developing ExAct, a model-agnostic framework for generating counterfactual explanations that provide actionable interventions for users. The result is that ExAct achieves 82.8% average validity in simulation-aided validation, surpassing state-of-the-art techniques by at least 10%, and improves proximity by at least 6.6%.
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.