Skin tone corrected pulse oximetry models evaluated through reflective pulsatile Monte Carlo simulations

Area of Science:

• Biomedical Engineering
• Medical Physics
• Clinical Diagnostics

Background:

• Pulse oximetry is a vital tool for monitoring arterial blood oxygen saturation (SpO2).
• A known limitation is skin tone bias, leading to inaccurate SpO2 readings in individuals with darker skin tones.
• This disparity can result in suboptimal patient care and inequitable health outcomes.

Purpose of the Study:

• To develop and validate clinically applicable pulse oximetry models that correct for skin tone bias.
• To mitigate the overestimation of SpO2 in individuals with darker skin tones.
• To promote more equitable patient care through accurate SpO2 measurements across diverse populations.

Main Methods:

• Integration of a melanin correction factor into the conventional ratio-of-ratios approach for SpO2 calculation.
• Utilizing pulsatile Monte Carlo simulations to model light-tissue interaction in a six-layered skin model.
• Systematic mapping of the ratio of ratios (R) to SaO2 across varying melanin concentrations and SpO2 levels.

Main Results:

• Quantification of skin tone-induced error in pulse oximetry.
• Demonstration that incorporating a melanin-dependent variable significantly reduces SpO2 bias.
• Development of SpO2 correction models that account for variations in melanin content.

Conclusions:

• Monte Carlo simulations provide a controlled environment to develop robust SpO2 correction models, overcoming limitations of in vivo studies.
• The proposed melanin correction factor effectively mitigates skin tone bias in pulse oximetry.
• These advancements represent a significant step towards achieving equitable pulse oximetry practices and improving patient care for all individuals, regardless of skin tone.