Path-specific effects for pulse-oximetry guided decisions in critical care

TL;DR

This paper uses causal inference to analyze how racial biases in pulse oximetry measurements influence clinical decisions like ventilation in ICUs, revealing nuanced effects on treatment duration.

Contribution

It introduces a causal framework with path-specific effects and novel estimators to assess biases in healthcare decision-making, validated on real-world datasets.

Findings

Minimal impact of racial measurement bias on ventilation rates

Disparities more evident in ventilation duration

Methodology applicable to other healthcare fairness studies

Abstract

Identifying and measuring biases associated with sensitive attributes is a crucial consideration in healthcare to prevent treatment disparities. One prominent issue is inaccurate pulse oximeter readings, which tend to overestimate oxygen saturation for dark-skinned patients and misrepresent supplemental oxygen needs. Most existing research has revealed statistical disparities linking device measurement errors to patient outcomes in intensive care units (ICUs) without causal formalization. This study causally investigates how racial discrepancies in oximetry measurements affect invasive ventilation in ICU settings. We employ a causal inference-based approach using path-specific effects to isolate the impact of bias by race on clinical decision-making. To estimate these effects, we leverage a doubly robust estimator, propose its self-normalized variant for improved sample efficiency, and provide novel finite-sample guarantees. Our methodology is validated on semi-synthetic data and applied to two large real-world health datasets: MIMIC-IV and eICU. Contrary to prior work, our analysis reveals minimal impact of racial discrepancies on invasive ventilation rates. However, path-specific effects mediated by oxygen saturation disparity are more pronounced on ventilation duration, and the severity differs across datasets. Our work provides a novel pipeline for investigating potential disparities in clinical decision-making and, more importantly, highlights the necessity of causal methods to robustly assess fairness in healthcare.