A Counterfactual Fair Model for Longitudinal Electronic Health Records via Deconfounder

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. However, traditional methods often encounter the tradeoff 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)
¹
that aims to achieve both fairness and accuracy in longitudinal Electronic Health Records (EHR) modeling. FLMD employs a two-stage training process. In the first stage, FLMD captures unobserved confounders for each encounter, effectively representing 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 comparing 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. For more details about this work, please refer to the full version of our paper
²
.
¹
https://anonymous.4open.science/r/ICDM_FLMD-C223
²
https://arxiv.org/abs/2308.11819