(88 days)
The INVOS™ Patient Monitor, model PM7100, is a noninvasive cerebral/somatic oximetry system intended for use as an adjunct monitor of regional hemoglobin oxygen saturation of blood in the brain or in other tissue beneath the sensor. It is intended for use on individuals greater than 40 kg at risk for reduced-flow or no-flow ischemic states.
The INVOS™ Adult rSO2 Sensor is indicated for single patient use when cerebral/somatic monitoring of site-specific regional oxygen saturation (rSO2) is required in patients weighing >40 kilograms. This sensor is only intended to be used with INVOS™ Near Infrared Spectroscopy (NIRS) technology including monitoring systems and devices integrated with INVOS™ NIRS technology. For additional information regarding setup and use of the INVOS™ System including indications for use, contraindications, warnings and cautions, consult the Monitoring System Operator's Manual.
The INVOS™ PM7100 Patient Monitor is a cerebral/somatic tissue oximeter that utilizes a near infrared diffuse reflectance spectroscopy system employing near infrared light at four wavelengths. Two wavelengths are used to estimate the percentage of hemoglobin saturated with oxygen in tissue underneath the sensor. Near infrared light at two additional wavelengths are used for the sensor on/off detection algorithm.
The subject device is non-sterile and consists of a multi-channel touch screen display, preamplifier, cables, and a single use sensor.
The device utilizes up to four detachable sensors to collect signals. Up to two preamplifiers receive signals from the sensors, digitize the signals, process the data and then estimate the current rSO2 at each sensor site. The preamplifiers then transmit the measured parameter data to the monitor where the information is displayed.
The provided document describes the K182868 submission for the INVOS™ PM7100 Patient Monitor, which is a cerebral/somatic tissue oximeter. The core of the submission focuses on demonstrating substantial equivalence to a predicate device (INVOS™ Cerebral/Somatic Oximeter System, Model 5100C, K082327), rather than establishing de novo performance criteria against a predefined clinical gold standard. Therefore, the "acceptance criteria" and "reported device performance" are primarily focused on demonstrating equivalence to the predicate, particularly in terms of rSO2 trend and backward compatibility.
Here's a breakdown of the requested information based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
Since this is a substantial equivalence submission, the "acceptance criteria" are implicitly met by demonstrating comparable performance to the predicate device. The document explicitly states: "Performance data demonstrates that the INVOS™ PM7100 Patient Monitor and the INVOS™ Adult rSO₂ Sensor are equivalent to the predicate."
| Acceptance Criteria (Demonstrated Equivalence) | Reported Device Performance |
|---|---|
| rSO2 Trend Equivalence to Predicate Device | An rSO2 trend equivalence clinical study was performed. A secondary analysis of the data for the system comparison of accuracy and precision demonstrated that rSO2 values of the subject and predicate are comparable. The INVOS™ PM7100 maintains the same fundamental rSO2 technology as its predicate (same rSO2 algorithm and optical/electrical signal chain). The study demonstrated that the INVOS™ PM7100 Patient Monitor meets the same trend performance as the predicate device. |
| Sensor Backward Compatibility | A sensor backwards compatibility clinical test demonstrated that the new PMSENS71-A sensor trend accuracy is equivalent to the trend accuracy of the SAFB-SM sensor when used with the INVOS™ 5100C (predicate). A secondary analysis of the system comparison of accuracy and precision demonstrated that rSO2 values of both sensors are comparable. The test supports the use of the PMSENS71-A sensor with the INVOS™ 5100C. |
| Sensor On/Off Detection Functionality | A sensor on/off detection clinical study was conducted. The results prove that the INVOS™ PM7100 Patient Monitor can effectively detect when the sensor is on and when the sensor is off the patient. |
2. Sample Size Used for the Test Set and Data Provenance
The document does not explicitly state the exact sample sizes (number of patients or measurements) for the clinical studies. It mentions "clinical study subjects" for the sensor on/off detection, but no specific numbers.
The data provenance is not specified (e.g., country of origin, retrospective or prospective).
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
This information is not provided. Given that the studies focus on comparing the device to a predicate and its internal consistency (e.g., sensor on/off), it's less likely to involve independent expert ground truth establishment in the way an imaging AI algorithm might. The "ground truth" for rSO2 values is generally a reference method or the predicate device itself in this context.
4. Adjudication Method for the Test Set
This information is not provided. It's unlikely that an adjudication method (like 2+1 or 3+1), typically used for subjective assessments like image interpretation, would be directly applicable to quantitative physiologic measurements like regional oxygen saturation, especially when comparing against a predicate device.
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
No. This is not an MRMC study. The INVOS™ PM7100 Patient Monitor is a physiological monitoring device that provides direct measurements, not an AI diagnostic aid for human readers. Therefore, the concept of "human readers improve with AI vs without AI assistance" does not apply here.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
Yes, in essence. The studies described (rSO2 trend equivalence, sensor backwards compatibility, sensor on/off detection) are evaluating the standalone performance of the INVOS™ PM7100 device and its sensors in providing physiological measurements, compared to a predicate device or expected functionality. The device itself is an "algorithm only" system in that it processes optical signals to provide a regional oxygen saturation value.
7. The Type of Ground Truth Used
The primary "ground truth" for the rSO2 trend equivalence study appears to be the measurements from the predicate device (INVOS™ 5100C). The study aimed to demonstrate that the new device's rSO2 values are "comparable" to the predicate. For the sensor on/off detection, the ground truth would inherently be the physical state of the sensor (on or off) relative to the patient.
8. The Sample Size for the Training Set
The document does not mention a "training set" in the context of device development. This is not an AI/ML device that requires a distinct training set in the typical sense. The rSO2 algorithm itself is described as constant: "The INVOS™ PM7100 maintains the same fundamental rSO2 technology as its predicate i.e., the same rSO2 algorithm."
9. How the Ground Truth for the Training Set Was Established
As no training set is described for an AI/ML algorithm, this question is not applicable based on the provided document. The rSO2 algorithm's development and validation would have been part of the original predicate device (K082327) and its preceding research activities.
§ 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).