Search Results

Indicated for use whenever there is a need for monitoring, transport monitoring, recording, and alarming of the physiological parameters arterial oxygen saturation (SpO2) and pulse rate of adult, pediatric and neonatal patients in a hospital environment by health care professionals.

X2 (M3002A) Multi-Measurement Module is indicated for transport monitoring outside hospitals.

The SpO2 measurement is based on the absorption of light, which is emitted through human tissue (i.e. index finger). Two light sources transmit red and infrared light through the human tissue. The ratio of the different absorption of the red and infrared light is calculated. The saturation value is defined by the percentage ratio of the oxygenated hemoglobin [HbO₂] to the total amount of hemoglobin [Hb] (SpO2 = [HbOz]/({Hb]+[HbO2]). Out of calibration curves, which are based on controlled hypoxia studies with healthy non-smoking adult volunteers over a specified saturation range (SaO2 from 70%-100%), the ratio determines the SpO2 value. The measurement accuracy of SpO2 in the range of 70% to 100% is between 2% and 4% RMS dependent on the Philips sensor type. The measurement accuracy of pulse rate in the range of 30 bpm to 300 bpm is 2% or 1 bpm (whichever is greater).

The modification is a hardware and firmware improvement and reduces the manufacturing costs.

Here's an analysis of the acceptance criteria and study details for the picoSAT IIP408 SpO2 pulse oximetry module, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size Used for the Test Set and Data Provenance

• Sample Size: 10 volunteers
• Data Provenance: Controlled hypoxia studies with healthy non-smoking adult volunteers. Since the submitter is Philips Medizin Systeme Böblingen GmbH (Germany), it's highly likely the study was conducted in Germany or a similar Western country, but the specific country of origin is not explicitly stated. The study was prospective in nature due to it being a "controlled desaturation study."

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

• Number of Experts: Not applicable in this context.
• Qualifications of Experts: The ground truth was established by a CO-Oximeter as a reference, not human experts. CO-Oximeters are laboratory-grade instruments used for highly accurate blood gas analysis, including oxygen saturation.

4. Adjudication Method (e.g., 2+1, 3+1, none) for the Test Set

• Adjudication Method: Not applicable. The ground truth was established by instrumental reference (CO-Oximeter) rather than human expert interpretation requiring adjudication.

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

• MRMC Study Done: No. This device is a pulse oximeter, not an AI-assisted diagnostic tool that would involve human readers interpreting cases.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done

• Standalone Study Done: Yes, essentially. The accuracy of the SpO2 measurement is a direct output of the device's hardware and firmware, compared against a reference standard. There is no human "in-the-loop" for the direct SpO2 measurement process itself.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

• Type of Ground Truth: Instrumental reference – a CO-Oximeter was used to provide SaO2 (arterial oxygen saturation) reference values.

8. The Sample Size for the Training Set

• Sample Size: Not explicitly stated as a distinct "training set" in the context of machine learning model development. For traditional medical device calibration (as described here), "calibration curves" are developed. While the text mentions "Out of calibration curves, which are based on controlled hypoxia studies with healthy non-smoking adult volunteers over a specified saturation range (SaO2 from 70%-100%), the ratio determines the SpO2 value," it does not specify a separate sample size for developing these curves, implying some overlap or that the 10 volunteers may have contributed to this process. It explicitly states "at least 20 data samples per volunteer" for the validation study.

9. How the Ground Truth for the Training Set was Established

• Ground Truth Establishment: The "calibration curves" (analogous to a training process for establishing the device's core functionality) were "based on controlled hypoxia studies with healthy non-smoking adult volunteers over a specified saturation range (SaO2 from 70%-100%)." This implies that during these hypoxia studies, a reference method (likely a CO-Oximeter, similar to the validation) was used to establish the true SaO2 values against which the device's internal light absorption ratios were mapped to create the SpO2 output.

Ask a specific question about this device

Indicated for use by health care professionals whenever there is a need for monitoring the physiological parameters of patients. Intended for monitoring and recording of and to generate alarms for multiple physiological parameters of adults, pediatrics and neonates in hospital environments. The MP5 is also intended for use in transport situations within hospital environments.

The names of the device is the Philips MP5 IntelliVue Patient Monitor

The Philips MP5 IntelliVue Patient Monitor is a patient monitoring device. The provided text outlines the declaration of substantial equivalence for this device to previously cleared devices. It does not contain detailed information about specific acceptance criteria for performance metrics (like accuracy for heart rate, blood pressure, etc.) or a study that specifically proves the device meets those criteria with granular data and methodology.

However, based on the document, we can infer the approach taken:

1. A table of acceptance criteria and the reported device performance:

The document states: "Pass/Fail criteria were based on the specifications cleared for the predicate device and test results showed substantial equivalence." This indicates that the acceptance criteria for the MP5 IntelliVue Patient Monitor were inherently tied to, and met, the established performance specifications of its predicate devices (Philips MP30 IntelliVue Patient Monitor and its modules).

Since specific numerical acceptance criteria and reported performance values for parameters like arrhythmia detection sensitivity/specificity, blood pressure accuracy, or oxygen saturation accuracy are not provided in this summary, a detailed table cannot be created from the given text. The general statement of "substantial equivalence" is the reported overall performance.

2. Sample size used for the test set and the data provenance:

• Sample Size for Test Set: Not specified. The document mentions "system level tests, performance tests, and safety testing," but does not detail the number of patients, test cases, or data points used in these tests.
• Data Provenance: Not specified. There is no mention of the country of origin of the data or whether it was retrospective or prospective.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• Number of Experts: Not applicable/Not specified. This device is a physiological monitor, and its "ground truth" for parameters like heart rate, blood pressure, or oxygen saturation would typically be established by validated reference methods or other highly accurate medical equipment, not by human experts adjudicating diagnoses. The testing would compare the device's readings against these reference standards. If "safety testing from hazard analysis" involved expert review, it is not detailed.
• Qualifications of Experts: Not applicable/Not specified.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

• Adjudication Method: Not applicable/Not specified. As mentioned above, "ground truth" for physiological parameters is typically established by reference instruments, not through expert adjudication in the same way as, for example, image interpretation.

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:

• MRMC Study: No. This device is a patient monitor, not an AI-assisted diagnostic tool that aids human readers. Therefore, an MRMC comparative effectiveness study comparing human readers with and without AI assistance is not relevant to this type of device and was not performed.
• Effect Size: Not applicable.

6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done:

• Standalone Performance: The testing described ("system level tests, performance tests, and safety testing") would inherently evaluate the standalone performance of the device's algorithms and hardware in measuring and reporting physiological parameters. While human interaction is involved in setting up and monitoring, the core performance metrics (e.g., accuracy of readings, alarm thresholds) are assessed based on the device's output. However, the document does not break down the results into explicit "standalone algorithm performance" versus "human-in-the-loop performance."

7. The type of ground truth used:

• Type of Ground Truth: Inferred to be reference standard measurements. For physiological parameters measured by a patient monitor (e.g., ECG, blood pressure, SpO2, temperature, gas analysis), the "ground truth" would generally be established using highly accurate and calibrated reference devices or methodologies. For example, a "true" heart rate might be determined by a known ECG simulator, or blood pressure by an invasive catheter with a calibrated transducer.

8. The sample size for the training set:

• Sample Size for Training Set: Not applicable/Not specified. This document describes a traditional medical device (patient monitor) and its declaration of substantial equivalence, not a machine learning or AI-based device that typically undergoes a distinct "training" phase with a specific dataset.

9. How the ground truth for the training set was established:

• Ground Truth Establishment for Training Set: Not applicable/Not specified. As above, a "training set" and its associated ground truth are primarily concepts in machine learning/AI development, which is not the focus of this 510(k) summary.

In summary, the 510(k) pertains to a traditional patient monitor. The testing performed focused on verifying that the modified device met the established specifications of its predicate devices, thereby demonstrating "substantial equivalence." The details typically requested for AI/ML-based devices (like MRMC studies, expert adjudication, training set specifics) are not applicable or provided for this type of submission.

Ask a specific question about this device