Algorithmic Bias in Machine Learning Based Delirium Prediction
This work addresses bias in delirium prediction models, which is crucial for equitable healthcare, but it is incremental as it provides initial evidence without major methodological advances.
The study examined algorithmic bias in machine learning models for predicting delirium, finding that sociodemographic features like sex and race impact performance across subgroups, with initial experimental evidence from MIMIC-III and another hospital dataset.
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.