Mediation Analysis in the Presence of Sample Selection Bias with an Application to Disparities in Liver Transplantation Listing

2025-09-02

AI Summary

Health inequities in liver transplant listing decisions are systematically misestimated due to selection bias—arising from modeling only the subset of patients who complete evaluation—leading to biased causal estimates of social determinants (e.g., socioeconomic status) on listing, including direct, indirect, and path-specific effects. Method: We propose a causal inference framework integrating referral-population data: (1) a directed acyclic graph (DAG) formalizes the selection mechanism and confounding structure; (2) an extended reweighting-based mediation formula corrects for non-random missingness under selection bias; and (3) identification and estimation of direct, indirect, and path-specific effects are enabled in nonexperimental observational data. Contribution/Results: This work is the first to extend mediation analysis to clinical decision-making settings with selection bias. Applied to a real-world liver transplant cohort, it yields unbiased quantification of mechanisms driving health inequities, substantially improving external validity and policy relevance of causal interpretations.

Technology Category

• Reasoning under Uncertainty: Causality
• Machine Learning: Causal Learning
• Philosophy and Ethics of AI: Bias, Fairness & Equity

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Social Networks and Social Media: Fairness and bias in social network and social media analysis
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

The study of disparities in the liver transplantation process may focus on quantifying causal effects, particularly the average, direct, or indirect effects of various social determinants of health on being listed as a candidate for transplant. Selection bias arises when the data sample does not represent the target population, defined here as all individuals referred to the transplant clinic. Listing decisions are made for the subset of patients who complete the evaluation process, who may differ systematically from the referred population. There is evidence that selection is associated with patient characteristics that also impact outcomes. Using data only from the selected population may yield biased causal effect estimates. However, incorporating data from the referred population allows for analytic correction. This correction leverages hypothesized causal relationships among selection, the outcome (getting listed), exposures, and mediators. Using directed acyclic graphs (DAGs), we establish graphical conditions under which a reweighted mediation formula identifies effect of interest - direct, indirect, and path-specific effects - in the presence of sample selection. In a clinical case study, we investigate mediated and direct effects of a patient's socioeconomic position on being listed for transplant, allowing selection to depend on race, gender, age, and other social determinants.

Problem

• Addressing sample selection bias in mediation analysis
• Correcting biased causal effect estimates in liver transplantation
• Investigating socioeconomic disparities in transplant listing decisions

Innovation

• DAGs establish conditions for identification
• Reweighted mediation formula corrects selection bias
• Analytic correction leverages causal relationships