Mitigating melanin-induced bias in pulse oximetry: Optical, algorithmic, engineering, hardware and modeling tools

Abstract

Melanin, the primary determinant of skin pigmentation, absorbs light at wavelengths that can have significant impact on the accuracy of pulse oximetry and other optical biosensing methods. This narrative review examines key factors influencing melanin-dependent pulse oximetry inaccuracies, including optical interference in transmission and reflectance modes. These inaccuracies further highlight the need for use of standardized skin tone metrics in device testing and design such as the Monk Skin Tone scale and Individual Typology Angle for performance stratification. There are several approaches in development that hope to address the errors in pulse oximetry measurements on melanin-rich skin. These include algorithmic and engineering approaches such as multi-wavelength sensing, regression-based correction, and machine learning models demonstrating significant reductions in melanin-induced error. Advances in pulse oximeter hardware and testing are also considered, including tissue-mimicking phantoms, optimized light sources, sensor design, and wearable innovations. Modeling tools, particularly Monte Carlo simulations, are also reviewed for their role in sensor design, spectral optimization, and algorithm training. Finally, evolving regulatory and equity frameworks are discussed, highlighting the January 2025 US FDA guidance on skin tone subgroup reporting. These findings underscore the need for skin-aware calibration and integrated modeling to ensure equitable pulse oximetry performance across diverse populations.