A validation method for near-infrared spectroscopy based tissue oximeters for cerebral and somatic tissue oxygen saturation measurements

Abstract

We describe the validation methodology for the NIRS based FORE-SIGHT ELITE^® (CAS Medical Systems, Inc., Branford, CT, USA) tissue oximeter for cerebral and somatic tissue oxygen saturation (StO₂) measurements for adult subjects submitted to the United States Food and Drug Administration (FDA) to obtain clearance for clinical use. This validation methodology evolved from a history of NIRS validations in the literature and FDA recommended use of Deming regression and bootstrapping statistical validation methods. For cerebral validation, forehead cerebral StO₂ measurements were compared to a weighted 70:30 reference (REF CX_B) of co-oximeter internal jugular venous and arterial blood saturation of healthy adult subjects during a controlled hypoxia sequence, with a sensor placed on the forehead. For somatic validation, somatic StO₂ measurements were compared to a weighted 70:30 reference (REF CX_S) of co-oximetry central venous and arterial saturation values following a similar protocol, with sensors place on the flank, quadriceps muscle, and calf muscle. With informed consent, 25 subjects successfully completed the cerebral validation study. The bias and precision (1 SD) of cerebral StO₂ compared to REF CX_B was -0.14 ± 3.07%. With informed consent, 24 subjects successfully completed the somatic validation study. The bias and precision of somatic StO₂ compared to REF CX_S was 0.04 ± 4.22% from the average of flank, quadriceps, and calf StO₂ measurements to best represent the global whole body REF CX_S. The NIRS validation methods presented potentially provide a reliable means to test NIRS monitors and qualify them for clinical use.

Keywords: Cerebral oximetry; FDA; NIRS; Near Infrared Spectroscopy; Saturation; Tissue oximetry; Tissue oxygen.

Fig. 1

Stepped Hypoxia Plateau Sequence Protocol with targeted pulse oximetry SpO₂ values and estimated ETO₂ values previously derived experimentally from SpO₂. For the NIRS cerebral StO₂ validation portion of the protocol, jugular venous and arterial blood samples are drawn for co-oximetry analysis when the cerebral StO₂ value stabilizes for each step. Likewise for NIRS somatic StO₂ validation portion of the protocol, central venous and arterial blood samples are drawn for co-oximetry analysis when the somatic StO₂ values from flank, quadriceps, and calf muscle stabilize for each step

Fig. 2

Scatter plot comparison of cerebral StO₂ measurements to co-oximetry reference (REF CX_B) with data points marked by skin tone (dark, moderate, and light)

Fig. 3

Scatter plot comparison of individual somatic StO₂ measurements (flank, quad, and calf) versus Co-Oximetry Reference (REF CX_S)

Fig. 4

Scatter plot comparison of the average of flank, quad, and calf StO₂ measurements to the global Co-Oximetry Reference (REF CX_S), with data points marked by skin tone (dark, moderate, and light)