A Counterfactual Fair Model for Longitudinal Electronic Health Records via Deconfounder

TL;DR

This paper introduces FLMD, a novel model for longitudinal EHR data that balances fairness and accuracy by capturing unobserved confounders using a deconfounder-inspired approach.

Contribution

The paper proposes a two-stage training method for FLMD that captures unobserved confounders and applies counterfactual fairness criteria to improve health disparity mitigation.

Findings

FLMD outperforms baseline methods in fairness and accuracy.

Effective in imbalanced and synthetic datasets.

Captures unobserved confounders for better modeling.

Abstract

The fairness issue of clinical data modeling, especially on Electronic Health Records (EHRs), is of utmost importance due to EHR's complex latent structure and potential selection bias. It is frequently necessary to mitigate health disparity while keeping the model's overall accuracy in practice. However, traditional methods often encounter the trade-off between accuracy and fairness, as they fail to capture the underlying factors beyond observed data. To tackle this challenge, we propose a novel model called Fair Longitudinal Medical Deconfounder (FLMD) that aims to achieve both fairness and accuracy in longitudinal Electronic Health Records (EHR) modeling. Drawing inspiration from the deconfounder theory, FLMD employs a two-stage training process. In the first stage, FLMD captures unobserved confounders for each encounter, which effectively represents underlying medical factors beyond observed EHR, such as patient genotypes and lifestyle habits. This unobserved confounder is crucial for addressing the accuracy/fairness dilemma. In the second stage, FLMD combines the learned latent representation with other relevant features to make predictions. By incorporating appropriate fairness criteria, such as counterfactual fairness, FLMD ensures that it maintains high prediction accuracy while simultaneously minimizing health disparities. We conducted comprehensive experiments on two real-world EHR datasets to demonstrate the effectiveness of FLMD. Apart from the comparison of baseline methods and FLMD variants in terms of fairness and accuracy, we assessed the performance of all models on disturbed/imbalanced and synthetic datasets to showcase the superiority of FLMD across different settings and provide valuable insights into its capabilities.