Integrating Social Determinants of Health into Knowledge Graphs: Evaluating Prediction Bias and Fairness in Healthcare

TL;DR

This paper constructs a social determinants of health-enriched knowledge graph, introduces a fairness formulation for graph embeddings, and proposes a reweighting method to reduce biases, aiming for more equitable healthcare predictions.

Contribution

It presents one of the first comprehensive analyses of bias and fairness in biomedical knowledge graphs that include social determinants of health, with a novel bias mitigation technique.

Findings

Bias related to SDoH factors detected in link prediction

Proposed reweighting method reduces SDoH-related biases

Enhanced fairness in healthcare-related graph predictions

Abstract

Social determinants of health (SDoH) play a crucial role in patient health outcomes, yet their integration into biomedical knowledge graphs remains underexplored. This study addresses this gap by constructing an SDoH-enriched knowledge graph using the MIMIC-III dataset and PrimeKG. We introduce a novel fairness formulation for graph embeddings, focusing on invariance with respect to sensitive SDoH information. Via employing a heterogeneous-GCN model for drug-disease link prediction, we detect biases related to various SDoH factors. To mitigate these biases, we propose a post-processing method that strategically reweights edges connected to SDoHs, balancing their influence on graph representations. This approach represents one of the first comprehensive investigations into fairness issues within biomedical knowledge graphs incorporating SDoH. Our work not only highlights the importance of considering SDoH in medical informatics but also provides a concrete method for reducing SDoH-related biases in link prediction tasks, paving the way for more equitable healthcare recommendations. Our code is available at \url{https://github.com/hwq0726/SDoH-KG}.