Quantifying Racial Bias in SpO 2 Measurements Using a Machine Learning Approach

Hakan Burak Karli, Eli Hilborn, Bige Deniz Unluturk

2025

Abstract

This paper investigates the racial biases in pulse oximetry, focusing on the importance of noninvasive peripheral oxygen saturation (SpO2) measurements in classifying patient race and ethnicity. Using the publicly available BOLD dataset, our study applies various machine learning models to quantify the extent of bias in SpO2 readings. Initial analysis revealed significant inaccuracies for individuals with darker skin tones, highlighting broader health disparities. Further exploration with machine learning models assessed SpO2 as a predictive marker for race, uncovering that conventional oximetry may underestimate hypoxemia in non-White patients. Notably, the XGBoost model demonstrated superior performance, achieving baseline accuracy of 58.08% across the dataset with all races and 72.60% for only black and white patients included, while consis-tently identifying SpO2 as a significant factor in these disparities. Our findings demonstrate the necessity for recalibrating medical devices to enhance their reliability and inclusivity, ensuring equitable health outcomes.

Paper Citation

in Harvard Style

Karli H., Hilborn E. and Unluturk B. (2025). Quantifying Racial Bias in SpO 2 Measurements Using a Machine Learning Approach. In Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOSIGNALS; ISBN 978-989-758-731-3, SciTePress, pages 853-859. DOI: 10.5220/0013117000003911

in Bibtex Style

@conference{biosignals25,
author={Hakan Karli and Eli Hilborn and Bige Unluturk},
title={Quantifying Racial Bias in SpO 2 Measurements Using a Machine Learning Approach},
booktitle={Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOSIGNALS},
year={2025},
pages={853-859},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013117000003911},
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 1: BIOSIGNALS
TI - Quantifying Racial Bias in SpO 2 Measurements Using a Machine Learning Approach
SN - 978-989-758-731-3
AU - Karli H.
AU - Hilborn E.
AU - Unluturk B.
PY - 2025
SP - 853
EP - 859
DO - 10.5220/0013117000003911
PB - SciTePress