K Number
K172904
Date Cleared
2017-12-26

(95 days)

Product Code
Regulation Number
868.1400
Panel
AN
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

Indications for Use statement for the Capnography Extension 867040:

The measurement extension adds physiological measurements (Mainstream / Sidestream CO2 and optionally temperature, invasive blood pressure, cardiac output) to a dedicated host device. It is intended for use by trained healthcare professionals for adult, pediatric, and neonatal patients in a hospital environment and for transport inside hospitals. The measurement extension can only function when it is connected to a dedicated host device.

Indications for Use statement for the Microstream Extension 867041:

The measurement extension adds physiological measurements (Microstream CO2 and optionally temperature and invasive blood pressure) to a dedicated host device. It is intended for use by trained healthcare professionals for adult, pediatric, and neonatal patients in a hospital environment and for transport inside hospitals.

The measurement extension can only function when it is connected to a dedicated host device.

The Integrated Pulmonary Index (IPI) is intended for use with adult and pediatric (1 to 12 years) patients only. The IPI is an adjunct to and not intended to replace vital sign monitoring.

Device Description

The new IntelliVue Capnography Extension 867040 and Microstream Extension 867041 are modifications of the legally marketed Philips Capnography Extension M3014A and Microstream Extension M3015B, respectively.

IntelliVue Capnography Extension 867040 and Microstream Extension 867041 are compact measuring devices without display and control elements that, in combination with dedicated host devices, add the following measurement parameters:

867040: Capnography (Mainstream / Sidestream CO2) and optionally temperature, invasive blood pressure, and cardiac output (C.O.)

867041: Microstream CO2 and optionally temperature and invasive blood pressure. IntelliVue Capnography Extension 867040 and Microstream Extension 867041 use settings and power of the connected host device. Trend data and measurement settings from the measurements in the extensions are stored in the connected host device. The measurement extensions send processed waves, numerics and basic alerts to the host device.

AI/ML Overview

The provided document describes the Philips IntelliVue Capnography Extension 867040 and Microstream Extension 867041 devices. It states that these devices are modifications of legally marketed predicate devices (Philips Capnography Extension M3014A and Microstream Extension M3015B, respectively) and that their fundamental scientific technology is the same. The document focuses on regulatory compliance, verification, and validation activities.

Based on the provided text, here's a breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not provide a specific table or detailed quantitative acceptance criteria for device performance. Instead, it states that:

  • "All specified pass/fail criteria have been met."
  • "The new devices perform according to the specified criteria that are the same as those for the predicate devices."
  • "All specified test requirements have been met. The test results demonstrate that modified and previously available device functions work correctly according to the specifications and labeling claims."
  • "Pass/Fail criteria were based on the specifications cleared for the predicate devices and test results showed substantial equivalence."
  • "The results demonstrate that the new devices meet all defined reliability requirements and performance claims."

This indicates that the acceptance criteria are generally "working according to specifications" and achieving "substantial equivalence" to the predicate devices, as demonstrated through various tests.

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

The document does not specify a separate "test set" in terms of patient data or clinical samples. The testing described appears to be primarily bench testing, environmental testing, and functional system-level testing of the devices themselves, rather than testing on a distinct dataset of patient information.
Therefore, information on data provenance (country of origin, retrospective/prospective) is not applicable or provided for a "test set" in this context.

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

This information is not provided in the document. The testing described focuses on the device's adherence to engineering specifications and performance standards, rather than establishing a ground truth for clinical diagnoses or measurements that would typically require expert consensus.

4. Adjudication Method for the Test Set

This information is not provided and is not applicable given the nature of the testing described (bench and system-level performance, not clinical adjudication of patient data).

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 MRMC comparative effectiveness study is mentioned in the document. The devices are extensions for physiological measurements, not AI-driven diagnostic tools that would typically involve human reader performance studies.

6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) Was Done

The document describes performance bench testing and functional system-level tests for the devices (extensions), which operate in a standalone-like manner in terms of producing measurements that are then sent to a host device. The verification and validation activities inherently assess the algorithm and hardware performance without direct human intervention in the measurement process itself, although the device is intended for use by trained healthcare professionals. The specific term "standalone algorithm performance" is not used, but the performance tests cover the device's output.

7. The Type of Ground Truth Used

The "ground truth" for the device's performance is established by the specifications and claims of the predicate devices and relevant recognized consensus standards (e.g., IEC 60601-1-2 regarding electromagnetic compatibility, ISO 80601-2-55 for respiratory gas monitors).
The testing confirms that the new devices perform according to these established criteria. This is a type of engineering and regulatory "ground truth" rather than a clinical ground truth like pathology or outcomes data.

8. The Sample Size for the Training Set

This information is not provided. The devices described are not explicitly stated to be using machine learning or AI that would require a "training set" in the conventional sense. They are measurement extensions based on established physiological measurement technologies.

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

Since no training set is mentioned, this information is not applicable.

§ 868.1400 Carbon dioxide gas analyzer.

(a)
Identification. A carbon dioxide gas analyzer is a device intended to measure the concentration of carbon dioxide in a gas mixture to aid in determining the patient's ventilatory, circulatory, and metabolic status. The device may use techniques such as chemical titration, absorption of infrared radiation, gas chromatography, or mass spectrometry.(b)
Classification. Class II (performance standards).