Making pulse oximeters fairer for people with darker skin
Overcoming inequities in Pulse oximetry Through clinical InformatiCs (OPTIC)
Using hospital records and smart computer tools to spot patients whose pulse oximeters might miss low oxygen levels, especially people with darker skin.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Duke University NIH-funded |
| Lab location | 1 site (Durham, United States) |
| Project ID | NIH-11264759 on NIH RePORTER |
What this research studies
This project uses routinely collected hospital records and arterial blood gas tests to find when pulse oximeters overestimate oxygen, a problem that happens more often in people with darker skin. Researchers will train a machine learning model on vital signs, lab results, and oxygen measurements from nine hospitals to predict who is at high risk for hidden low oxygen. When the model flags a patient, clinicians could be prompted to check arterial blood gases or adjust monitoring. The goal is to reduce missed low-oxygen events and the unequal harm they cause.
Who could benefit from this research
Good fit: Hospitalized patients who are being monitored with pulse oximetry—particularly people with darker skin tones—would be the main candidates for the model's alerts and related checks.
Not a fit: People not receiving care in the participating hospitals, those without pulse oximeter monitoring, or those already having frequent arterial blood gas testing may not benefit directly from this work.
Why it matters
Potential benefit: If successful, the work could detect hidden low oxygen earlier and reduce racial disparities in oxygen monitoring, helping prevent organ damage from untreated hypoxemia.
How similar studies have performed: Prior studies have documented pulse oximeter bias by skin tone, but deploying multi-hospital machine learning to predict hidden hypoxemia is a relatively new approach.
Where this research is happening
Durham, United States
- Duke University — Durham, United States (Active)
Researchers
- Principal investigator: Wong, an-Kwok I — Duke University
- Study coordinator: Wong, an-Kwok I
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.