Fairness-Optimized Synthetic EHR Generation for Arbitrary Downstream Predictive Tasks

TL;DR

This paper introduces a novel pipeline for generating synthetic EHR data that maintains fidelity to real data while reducing fairness concerns in various downstream clinical prediction tasks, enhancing fairness in health AI.

Contribution

The study presents a task- and model-agnostic synthetic EHR generation pipeline that improves fairness in downstream health AI applications, filling a gap in existing methods.

Findings

Effective in reducing fairness concerns across multiple tasks

Applicable to different EHR datasets

Complementary to existing fairness methods

Abstract

Among various aspects of ensuring the responsible design of AI tools for healthcare applications, addressing fairness concerns has been a key focus area. Specifically, given the wide spread of electronic health record (EHR) data and their huge potential to inform a wide range of clinical decision support tasks, improving fairness in this category of health AI tools is of key importance. While such a broad problem (mitigating fairness in EHR-based AI models) has been tackled using various methods, task- and model-agnostic methods are noticeably rare. In this study, we aimed to target this gap by presenting a new pipeline that generates synthetic EHR data, which is not only consistent with (faithful to) the real EHR data but also can reduce the fairness concerns (defined by the end-user) in the downstream tasks, when combined with the real data. We demonstrate the effectiveness of our proposed pipeline across various downstream tasks and two different EHR datasets. Our proposed pipeline can add a widely applicable and complementary tool to the existing toolbox of methods to address fairness in health AI applications, such as those modifying the design of a downstream model. The codebase for our project is available at https://github.com/healthylaife/FairSynth