(340 days)
The MICRO2+ is intended for the continuous, non-invasive monitoring of functional oxygen saturation of arterial hemoglobin and pulse rate during both no motion and motion conditions, and for patients who are well or poorly perfused, using a range of compatible sensors. The device will produce visual and aural alarms if these parameters vary beyond preset limits.
The INFINITY MICRO2+ is a small, compact battery operated ambulatory pulse oximeter. The hand-held INFINITY MICRO2+ is a redesign of the MICRO2 (K913489) used for the noninvasive measurement of the functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate with the use of an oxygen transducer (sensor). The SpO2 algorithm is essentially the same as that of the predicate (K980882), but enhanced for greater artifact, motion and low perfusion tolerance. A range of compatible sensors is available for use with the INFINITY MICRO2+. The INFINITY MICRO2+ can be connected to a Siemens INFINITY Telemetry transmitter (K972714) or to a customer's personal computer for the display and printing of SpO2 trend information. The device is intended to provide continuous. non-invasive SpO2 monitoring for neonatal, pediatric and adult patient populations in health care environments where patient care is provided by licensed health care professionals.
The provided document is a 510(k) summary for the INFINITY MICRO2+ Pulse Oximeter. It does not contain specific acceptance criteria, reported device performance data, sample sizes for test sets, details on ground truth establishment, or information about MRMC studies. The document primarily focuses on demonstrating substantial equivalence to predicate devices.
However, based on the information provided, here's what can be inferred and what is missing:
1. A table of acceptance criteria and the reported device performance
This information is not provided in the given text. A 510(k) summary typically includes a summary of performance data in comparison to a predicate device, but specific acceptance criteria (e.g., accuracy +/- X% SpO2) and tables with reported device performance against those criteria are not detailed here. The document mentions "Assessment of non-clinical performance data for equivalence: Section S 7" and "Assessment of clinical performance data for equivalence: Section T 8," suggesting that this information exists in the full 510(k) submission, but it's not present in this summary.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
This information is not provided. The document states "Clinical and bench testing performed demonstrate that the INFINITY MICRO2+ is as safe and effective as [predicate devices]," but no details about the sample size, type of study (retrospective/prospective), or data provenance are given.
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)
This information is not provided. For a pulse oximeter, ground truth for SpO2 is typically established through co-oximetry of arterial blood samples. There would likely be a medical professional (e.g., physician, nurse, or clinical researcher) overseeing the blood draws and potentially confirming the patient's physiological state, but the expert qualifications in the context of "ground truth" for a medical imaging or diagnostic device (like radiologist expertise) are not directly applicable here in the same way.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
This information is not provided. Adjudication methods are typically used when multiple experts are interpreting data and there's a need to resolve disagreements (e.g., in reading medical images). For a pulse oximeter performance study, the ground truth is usually an objective measurement (co-oximetry), so traditional adjudication between multiple human readers or experts is generally not applicable unless there were subjective assessments being made that required resolution.
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
This information is not applicable as the INFINITY MICRO2+ is a pulse oximeter, not an AI-assisted diagnostic tool that would involve human readers interpreting cases. It is a standalone device for measuring physiological parameters.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, the device's performance is inherently standalone in nature. A pulse oximeter algorithm processes raw sensor data to output SpO2 and pulse rate. The "SpO2 algorithm is essentially the same as that of the predicate (K980882), but enhanced for greater artifact, motion and low perfusion tolerance." This indicates that the algorithm's performance, operating without human intervention for the primary measurement, was evaluated.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
While explicitly stated, for pulse oximeters, the ground truth for oxygen saturation (SpO2) measurements in clinical studies is typically arterial blood gas analysis (ABG) measured by a co-oximeter. This provides the true arterial oxygen saturation (SaO2) which is then compared against the SpO2 reading from the device.
8. The sample size for the training set
This information is not provided. The document mentions a redesign and enhancement of the algorithm from a predicate device but does not detail any "training set" in the context of modern machine learning. In 2002, the development process for medical device algorithms like this would likely involve empirical testing and refinement rather than a distinct "training set" as understood in current AI/ML development.
9. How the ground truth for the training set was established
This information is not provided and is likely not applicable in the modern sense of an AI "training set" given the device's approval date (2002). Algorithm development at that time would primarily involve physiological modeling, signal processing, and empirical validation against known physiological states (ground truth likely from co-oximetry, similar to for the test/validation).
§ 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).