(57 days)
The noninvasive INVOS 5100C is intended for use as an adjunct trend monitor of regional hemoglobin oxygen saturation of blood in the brain or in other tissue beneath the sensor. It is intended for use in any individual at risk for reduced-flow or no-flow ischemic states. The prospective clinical value of data from the INVOS System has not been demonstrated in disease states. The INVOS System should not be used as the sole basis for diagnosis or therapy.
The INVOS 5100C is a 2 wavelength, diffuse reflectance spectroscopy system employing near infrared light to estimate the percentage of hemoglobin saturated with oxygen in tissue underneath the sensor. This is similar to the noninvasive technology widely used in pulse oximeters to monitor oxygen saturated hemoglobin percentage in arterial blood. An adhesive sensor containing a light source and 2 photodiodes is applied to the skin over the tissue of interest and the returning light is analyzed for hemoglobin and deoxyhemoglobin light absorption. Absorption signals from the photodiode closer to the light source are subtracted from those from the farther photodiode where the returning photons penetrate more deeply in the tissue. This suppresses absorption events originating in the outer layers of tissue that are common to both photodiodes, including the effects of skin pigmentation and subcutaneous tissues. The INVOS 5100C tissue oximeter is a multi-channel monitor with continuous recording and display of readings of regional tissue hemoglobin oxygen saturation from 4 separate sensors simultaneously. The monitor is connected to 2 preamplifiers, each of which in turn supports 2 sensors. It has USB connectivity for dynamic data capture, storage and transfer as well as a digital output port.
The SOMANETICS INVOS 5100C is a cerebral/somatic oximeter system. The provided document is a 510(k) Premarket Notification. Substantial equivalence was claimed for the INVOS 5100C system against the INVOS 5100B, and the FDA determined it was substantially equivalent.
Here's a breakdown of the requested information based on the provided text:
1. A table of acceptance criteria and the reported device performance
The provided document does not explicitly state specific quantitative "acceptance criteria" for the INVOS 5100C or detailed "reported device performance" against those criteria. It states: "Performance data and extensive literature references were submitted demonstrating the substantial equivalence of the device for its stated indication."
The general conclusion drawn from testing regarding performance is: "INVOS System can respond with significant changes during isolated desaturation events in kidney and gut tissues. Monitoring the body with the INVOS System can include organ or intestinal oxygenation as well as skeletal muscle tissue oxygen saturation changes depending on the anatomy." This describes a capability rather than a quantified performance metric against a specific threshold.
Therefore, a table of acceptance criteria and reported performance cannot be generated from the given text. The FDA's decision was based on "substantial equivalence" to a predicate device, which implies the new device performs acceptably similarly to the predicate, but specific performance metrics are not detailed here.
2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)
The document does not specify the sample size used for any test set or the data provenance (country of origin, retrospective/prospective). It generally mentions "Performance data and extensive literature references were submitted."
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience)
The document does not provide information on the number or qualifications of experts used to establish ground truth for any test set.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
The document does not mention any adjudication method used for the test set.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
The INVOS 5100C is an oximeter, a device that measures and displays physiological parameters (regional hemoglobin oxygen saturation). It is not an AI-powered diagnostic tool that human readers would use to interpret images or other complex data. Therefore, an MRMC comparative effectiveness study involving human readers and AI assistance is not applicable to this device type and was not performed.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
The device itself is a standalone monitor: "The noninvasive INVOS 5100C is intended for use as an adjunct trend monitor of regional hemoglobin oxygen saturation...". The description focuses on the device's ability to measure and trend, not on an algorithm operating in isolation without a human connecting the sensor and interpreting the displayed trend. The concept of "standalone (algorithm only)" as typically applied to AI/ML devices is not directly relevant here, as the device's primary function is direct measurement.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The document does not specify the type of ground truth used for performance evaluation, beyond the general statement "Performance data and extensive literature references were submitted." For an oximeter, ground truth would typically refer to a gold standard measurement of tissue oxygen saturation, but no details are provided here.
8. The sample size for the training set
The INVOS 5100C is described as a "2 wavelength, diffuse reflectance spectroscopy system" and mentions "subtracting" absorption signals, indicating a hardware-based measurement and processing method rather than an AI/ML system that would require a "training set" in the conventional sense. Therefore, the concept of a training set sample size is not applicable to this device.
9. How the ground truth for the training set was established
As there is no mention or indication of a "training set" for an AI/ML algorithm, this question is not applicable.
§ 870.2700 Oximeter.
(a)
Identification. An oximeter is a device used to transmit radiation at a known wavelength(s) through blood and to measure the blood oxygen saturation based on the amount of reflected or scattered radiation. It may be used alone or in conjunction with a fiberoptic oximeter catheter.(b)
Classification. Class II (performance standards).