Skin Pigmentation and Pulse Oximeter Accuracy in the Intensive Care Unit: a Pilot Prospective Study

Abstract

Rationale: Despite multiple reports of pulse oximeter inaccuracy among hospitalized Black individuals, regulatory testing of pulse oximeters is performed on healthy volunteers.

Objective: Evaluate pulse oximeter accuracy among intensive care unit patients with diverse skin pigmentation.

Methods: Skin pigmentation was measured using a chromameter in 12 patients and individual typology angle (ITA), a measure of constitutive pigmentation, calculated. Arterial blood gas (ABG) arterial oxygen saturation (SaO ₂ ) sampling was precisely matched to pulse oximetry (SpO ₂ ) using arterial line waveforms analysis. Error (SpO ₂ -SaO ₂ ), bias, and average root mean square error (A _RMS ) were calculated. Multivariable linear mixed effects models evaluated the association of SpO ₂ -SaO ₂ with skin pigmentation.

Measurements and main results: Sampling time was determined for 350 ABGs. Five participants (N=96 ABGs) were darkly pigmented (forehead ITA<-30°), and 7 lighter pigmented (N=254 ABGs). Darkly pigmented individuals had 1.05% bias and 4.15% A _RMS compared to 0.34% bias and 1.97% A _RMS among lighter pigmented individuals. After adjusting for SaO ₂ , pH, heart rate, and mean arterial pressure, SpO ₂ -SaO ₂ was falsely elevated by 1.00% more among darkly pigmented individuals (95% confidence interval: 0.25-1.76%). SpO ₂ significantly overestimated SaO ₂ for dark, brown, and tan forehead or forearm pigmentation and brown and tan finger pad pigmentation compared to intermediate/light pigmentation.

Conclusions: The pulse oximeter in clinical use at an academic medical center performed worse in darkly pigmented critically ill patients than established criteria for FDA clearance. Pulse oximeter testing in ICU settings is feasible, and could be required by regulators to ensure equivalent device performance by skin pigmentation among patients.