Monitoring fairness in machine learning models that predict patient mortality in the ICU

Tempest A. van Schaik; Xinggang Liu; Louis Atallah; Omar Badawi

Monitoring fairness in machine learning models that predict patient mortality in the ICU

Machine Learning 2024-11-08 v2 Artificial Intelligence

Authors: Tempest A. van Schaik , Xinggang Liu , Louis Atallah , Omar Badawi

Abstract

This work proposes a fairness monitoring approach for machine learning models that predict patient mortality in the ICU. We investigate how well models perform for patient groups with different race, sex and medical diagnoses. We investigate Documentation bias in clinical measurement, showing how fairness analysis provides a more detailed and insightful comparison of model performance than traditional accuracy metrics alone.

Keywords

fairness in machine learning clinical prediction clinical decision support

Cite

@article{arxiv.2411.00190,
  title  = {Monitoring fairness in machine learning models that predict patient mortality in the ICU},
  author = {Tempest A. van Schaik and Xinggang Liu and Louis Atallah and Omar Badawi},
  journal= {arXiv preprint arXiv:2411.00190},
  year   = {2024}
}

Comments

8 pages

Related papers

View all related →