Unmasking Societal Biases in Respiratory Support for ICU Patients through Social Determinants of Health

2024-08-01

International Joint Conference on Artificial Intelligence

AI Summary

This study investigates health inequities in ICU respiratory support interventions—specifically, long-term mechanical ventilation and successful weaning—across key social determinants of health (SDOH), including race, gender, age, and socioeconomic status. Methodologically, it introduces the first SDOH-augmented, temporally structured ICU clinical dataset, systematically integrating multidimensional SDOH variables into longitudinal clinical time-series data and validated by clinical domain experts; it further proposes a reproducible evaluation framework combining fairness auditing, temporal predictive modeling, and bias detection. Results reveal significant performance disparities across SDOH subgroups, with notably degraded weaning prediction accuracy among low-income and racial/ethnic minority patients. This work establishes the first SDOH-enhanced, clinically grounded evaluation paradigm and open infrastructure for fairness assessment of AI in ICU respiratory interventions.

Technology Category

• Philosophy and Ethics of AI: Bias, Fairness & Equity
• Machine Learning: Ethics, Bias, and Fairness
• Humans and AI: Planning and Decision Support for Human-Machine Teams

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
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

In critical care settings, where precise and timely interventions are crucial for health outcomes, evaluating disparities in patient outcomes is important. Current approaches often fall short in comprehensively understanding and evaluating the impact of respiratory support interventions on individuals affected by social determinants of health. Attributes such as gender, race, and age are commonly assessed and essential, but provide only a partial view of the complexities faced by diverse populations. In this study, we focus on two clinically motivated tasks: prolonged mechanical ventilation and successful weaning. We also perform fairness audits on the models' predictions across demographic groups and social determinants of health to better understand the health inequities in respiratory interventions in the intensive care unit. We also release a temporal benchmark dataset, verified by clinical experts, to enable benchmarking of clinical respiratory intervention tasks.

Problem

• Uncover disparities in ICU respiratory support
• Assess impact of social determinants on health outcomes
• Conduct fairness audits across demographic groups

Innovation

• Social determinants analysis
• Fairness audits models
• Temporal benchmark dataset