Auditing ICU Readmission Rates in an Clinical Database: An Analysis of Risk Factors and Clinical Outcomes

TL;DR

This paper develops a machine learning pipeline for ICU readmission prediction and conducts a fairness audit revealing disparities across demographic groups, emphasizing the need for bias mitigation in clinical AI systems.

Contribution

It introduces a comprehensive ML pipeline for ICU readmission prediction and performs a fairness audit highlighting existing disparities based on sensitive attributes.

Findings

Disparities in model performance across gender, ethnicity, language, and insurance groups.

Identifies gaps in fairness criteria such as equal opportunity and predictive parity.

Highlights the necessity for bias mitigation strategies in clinical AI applications.

Abstract

This study presents a machine learning (ML) pipeline for clinical data classification in the context of a 30-day readmission problem, along with a fairness audit on subgroups based on sensitive attributes. A range of ML models are used for classification and the fairness audit is conducted on the model predictions. The fairness audit uncovers disparities in equal opportunity, predictive parity, false positive rate parity, and false negative rate parity criteria on the MIMIC III dataset based on attributes such as gender, ethnicity, language, and insurance group. The results identify disparities in the model's performance across different groups and highlights the need for better fairness and bias mitigation strategies. The study suggests the need for collaborative efforts among researchers, policymakers, and practitioners to address bias and fairness in artificial intelligence (AI) systems.