Racial Disparities in Pulse Oximetry Cannot Be Fixed With Race-Based Correction

2022/10/10 by Neal Patwari, Di Huang, Patwari, Neal +3
Engineering · Environmental Science · Medicine · #Climate Change and Health Impacts #FOS: Electrical engineering #Non-Invasive Vital Sign Monitoring #Signal Processing (eess.SP) #Ultrasound in Clinical Applications #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2210.04990

openalex publication_date 2022/10/10 · openalex created_date 2022/10/14 · openalex updated_date 2026/07/28

Abstract

Studies have shown pulse oximeter measurements of blood oxygenation have statistical bias that is a function of race, which results in higher rates of occult hypoxemia, i.e., missed detection of dangerously low oxygenation, in patients of color. This paper further characterizes the statistical distribution of pulse ox measurements, showing they also have a higher variance for patients racialized as Black, compared to those racialized as white. We show that no single race-based correction factor will provide equal performance in the detection of hypoxemia. The results have implications for racially equitable pulse oximetry.

Related

• Pulse Oximeter Performance, Racial Inequity, and the Work Ahead
• Path-specific effects for pulse-oximetry guided decisions in critical care
• Accuracy and Bias of Pulse Oximetry in the Intensive Care Unit: A Prospective Observational Study
• Bias in vital signs? Machine learning models can learn patients’ race or ethnicity from the values of vital signs alone
• Evaluating the Impact of Pulse Oximetry Bias in Machine Learning under Counterfactual Thinking