It’s not you, it’s the algorithm

Technology should be neutral. But sometimes, it’s not.

Studies have found devices like pulse oximeters — those devices often clipped to your finger at the hospital to measure oxygen in your blood — may not be accurate across all skin tones. It’s a technical shortcoming that could mean the difference between health care providers catching a critical health issue and missing it altogether.

Accuracy based on a study, not funded by Medtronic, that enrolled 146 healthy subjects in the 92–96% saturation range and examined paired readings from Nellcor™ N-595 and Masimo Radical 7™ pulse oximeters generated simultaneously. This study was not designed for a head-to-head comparison of the respective devices.

A wide array of skin tones missing from clinical studies and data inputs is partly what drives the technology bias. 

Harvard sociology professor Dr. Ellis Monk studies how inequality shows up where we least expect it, from our health to the technology we use.

Dr. Monk points to everyday examples: a sensor-activated faucet that won’t turn on when a person of color puts their hands underneath, or a self-driving car that struggles to detect pedestrians with darker skin.

In both cases, the problem isn’t the person — it’s the algorithm. These systems weren’t tested broadly enough to recognize the full spectrum of human skin tones.

When it comes to health tech, Medtronic is taking that challenge head-on. By investing in research, clinical trials, and inclusive design practices, the company is working for its devices to see every patient, every time.

Acute Care and Monitoring products should not be used as the sole basis for diagnosis or therapy and are intended only as an adjunct in patient assessment. Note: Oxygen saturation accuracy can be affected by certain environmental, equipment, and patient physiologic conditions (as discussed in the operator’s manual for the monitor) that influence readings of SpO₂. Please consult the IFU and operator's manual for full safety information.