Using Under-Represented Subgroup Fine Tuning to Improve Fairness for Disease Prediction

Yanchen Wang, Rex Bone, Will Fleisher, Carole Gresenz, Jean Mitchell, Wilbert van der Klaauw, Crystal Wang, Lisa Singh

2025

Abstract

The role of artificial intelligence is growing in healthcare and disease prediction. Because of its potential impact and demographic disparities that have been identified in machine learning models for disease prediction, there are growing concerns about transparency, accountability and fairness of these predictive models. However, very little research has investigated methods for improving model fairness in disease prediction, particularly when the sensitive attribute is multivariate and when the distribution of sensitive attribute groups is highly skewed. In this work, we explore algorithmic fairness when predicting heart disease and Alzheimer’s Disease and Related Dementias (ADRD). We propose a fine tuning approach to improve model fairness that takes advantage of observations from the majority groups to build a pre-trained model and uses observations from each underrepresented subgroup to fine tune the pre-trained model, thereby incorporating additional specific knowledge about each subgroup. We find that our fine tuning approach performs better than other algorithmic fairness fixing methods across all subgroups even if the subgroup distribution is very imbalanced and some subgroups are very small. This is an important step toward understanding approaches for improving fairness for healthcare and disease prediction.

Paper Citation

in Harvard Style

Wang Y., Bone R., Fleisher W., Gresenz C., Mitchell J., van der Klaauw W., Wang C. and Singh L. (2025). Using Under-Represented Subgroup Fine Tuning to Improve Fairness for Disease Prediction. In Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF; ISBN 978-989-758-731-3, SciTePress, pages 240-253. DOI: 10.5220/0013318600003911

in Bibtex Style

@conference{healthinf25,
author={Yanchen Wang and Rex Bone and Will Fleisher and Carole Gresenz and Jean Mitchell and Wilbert van der Klaauw and Crystal Wang and Lisa Singh},
title={Using Under-Represented Subgroup Fine Tuning to Improve Fairness for Disease Prediction},
booktitle={Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF},
year={2025},
pages={240-253},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013318600003911},
isbn={978-989-758-731-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF
TI - Using Under-Represented Subgroup Fine Tuning to Improve Fairness for Disease Prediction
SN - 978-989-758-731-3
AU - Wang Y.
AU - Bone R.
AU - Fleisher W.
AU - Gresenz C.
AU - Mitchell J.
AU - van der Klaauw W.
AU - Wang C.
AU - Singh L.
PY - 2025
SP - 240
EP - 253
DO - 10.5220/0013318600003911
PB - SciTePress