Algorithmic Bias in Machine Learning Based Delirium Prediction

TL;DR

This paper investigates how sociodemographic biases affect machine learning models for delirium prediction, highlighting the importance of fairness considerations in healthcare AI applications.

Contribution

It provides initial experimental evidence on the impact of social determinants like race and sex on model performance in delirium prediction.

Findings

Sociodemographic features influence model accuracy across subgroups

Biases related to race and sex are evident in prediction performance

Highlights need for fairness in healthcare machine learning models

Abstract

Although prediction models for delirium, a commonly occurring condition during general hospitalization or post-surgery, have not gained huge popularity, their algorithmic bias evaluation is crucial due to the existing association between social determinants of health and delirium risk. In this context, using MIMIC-III and another academic hospital dataset, we present some initial experimental evidence showing how sociodemographic features such as sex and race can impact the model performance across subgroups. With this work, our intent is to initiate a discussion about the intersectionality effects of old age, race and socioeconomic factors on the early-stage detection and prevention of delirium using ML.