Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K133958
    Date Cleared
    2014-03-20

    (86 days)

    Product Code
    Regulation Number
    868.5160
    Reference & Predicate Devices
    Predicate For
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The indication for FLOW-i Anesthesia System is administering inhalation Anesthesia while controlling the entire ventilation of patients with no ability to breathe, as well as in supporting patients with a limited ability to breathe. The system is intended for use on neonatal to adult patient populations. The system is intended for use in hospital environments, except MRI environment, by healthcare professionals trained in inhalation Anesthesia administration.

    Device Description

    The modified FLOW-i Anesthesia System version 3.0 is an Anesthesia System designed to meet the many ventilatory challenges within Anesthesia, as well as to provide inhalation Anesthesia. It is intended to serve a wide range of patients from neonatal to adult. FLOW-i Anesthesia System is a software-controlled semi-closed system for inhalation Anesthesia (Sevoffurane, Desflurane, Isofturane and/or nitrous oxide). The most important performance features of the FLOW-i Anesthesia System are: - a ventilator whose functionality is based on ICU-ventilator technology, o - the volume reflector technology, o - the electronically controlled injector vaporizers and o - the ergonomic design. o

    AI/ML Overview

    The provided 510(k) summary describes modifications to an Anesthesia System and claims substantial equivalence to a predicate device. It specifically states that no clinical investigation was needed or performed to validate the changes. Therefore, the device does not have a study with acceptance criteria in the traditional sense, as it relies on non-clinical testing and substantial equivalence.

    However, the document does list technical specifications for various parameters, which can be interpreted as the performance criteria that the device (and its modifications) must continue to meet. The "study" that proves the device meets these criteria is the non-clinical testing and performance activities.

    Here's an attempt to structure the information based on the request, interpreting the provided text accordingly:


    1. Table of Acceptance Criteria and Reported Device Performance

    Since no specific "acceptance criteria" for a study are explicitly stated, the technical specifications from the "Specifications from FLOW-i User's Manual, section 14 Technical Specifications" are used as the inherent performance criteria the device is expected to meet. The document states that "Design verification and validation has demonstrated that the FLOW-i Anesthesia System performs within its specifications."

    ParameterAcceptance Criteria (Predicate Device Specification)Reported Device Performance (Subject Device Specification)
    Fresh gas oxygen conc21 - 100 % (O2/Air); 28- 100 % (O2/N2O) Accuracy: 21-59%: ±3 % v/v; 60-100%: ±5 % v/vSame
    Isoflurane conc0-5% Accuracy: ±15% of set value or ±5% of maximum possible setting (whichever is greater)Same
    Sevoflurane conc0-8% Accuracy: ±15% of set value or ±5% of maximum possible setting (whichever is greater)Same
    Desflurane conc0-10% (FG flow < 20 l/min); 0-18% (FG flow < 10 l/min) Accuracy: ±15% of set value or ±5% of maximum possible setting (whichever is greater)Same
    Fresh gas flow0.3-20 l/min Accuracy: ± 10 % or ± 50 ml/min (whichever is greater)Same
    Tidal volumeSettings: 100-2000 ml (adult); 20-350 ml (infant) Accuracy: ±10% or 10 ml, whichever is greaterSettings: Same
    Minute volume0.5-60 l/min (adult); 0.3-20 l/min (infant) Accuracy: ±10% or 0.3 l/min (whichever is greater)Same
    PEEP0-50 cmH2O Accuracy: ±2 cmH2O or ±10% (whichever is greater)Same
    Pressure level above PEEP0 to 120 cmH2O - PEEP (adult); 0 to 80 cmH2O-PEEP (infant) Accuracy: ±15% or ±2 cmH2O (whichever is greater)Same
    Breathing frequency4 - 100 breaths per minute Accuracy: ±5 % or ± 1 bpm (whichever is greater)Same
    I:E ratio1:10-4:1 in automatic modesSame
    Pressure (Monitoring)-30 cmH2O - 140 cmH2O Accuracy: ±5% or ±2 cm H2O (whichever is greater)Same
    Oxygen conc (Monitoring)0 to 100% Accuracy: ±1 vol% @ (0-25%); ±2 vol% @(25-80%); ±3 vol% @(80-100%)Same
    Tidal volume (Monitoring)Exp. Tidal volume: Measurement range: 20-2000 ml Accuracy: ±10% or 10 ml, whichever is greaterExp. Tidal volume: Measurement range: 5-2000 ml Accuracy: ±4ml (5-20 ml); ±10% or 10 ml, whichever is greater (20-2000ml)
    Carbon dioxide conc (Monitoring)0 to 10% Accuracy: ± 0.1 vol%@ (0-1%); ± 0.2 vol%@ (1-5%); ± 0.3 vol%@ (5-7%); ± 0.5 vol%@ (7-10%)Same
    Isoflurane conc (Monitoring)0 to 5% Accuracy: ± 0.15 vol%@ (0-1%); ± 0.2 vol%@ (1-5%)Same
    Sevoflurane conc (Monitoring)0 to 8% Accuracy: ± 0.15 vol%@ (0-1%); ± 0.2 vol%@ (1-5%); ± 0.4 vol%@ (5-8%)Same
    Desflurane conc (Monitoring)0 to 18% Accuracy: ± 0.15 vol%@ (0-1%); ± 0.2 vol%@ (1-5%); ± 0.4 vol%@ (5-10%); ± 0.6 vol%@ (10-15%); ± 1.0 vol%@ (15-18%)Same

    Note: The primary change affecting a numerical range/accuracy related to these specifications is the extension of the "Measured Tidal Volume lower range in Pressure Control" from 20ml to 5ml, and the corresponding adjustment in accuracy for the 5-20ml range.


    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 explicitly states: "The functionality added in the proposed FLOW-i Anesthesia System version 3.0 (K133958) does not add any new functions that need to be validated by clinical investigation."

    Therefore, there is no identified "test set" in the context of clinical data. The validation was based on non-clinical engineering and software testing.


    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)

    Not applicable, as no clinical investigation or expert-driven test set was used for independent ground truth establishment. Design validation involved assuring "the product meets its intended use and user needs, including usability," implying internal expert review by the manufacturer, but specific details on expert numbers or qualifications for ground truth are not provided for a test set.


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

    Not applicable, as no clinical investigation or expert-driven test set requiring adjudication was performed.


    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

    Not applicable. This device is an Anesthesia System and does not involve "human readers" or "AI assistance" in the context of image interpretation or similar diagnostic tasks for which MRMC studies are typically conducted.


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

    This refers to the performance of the device itself (the Anesthesia System) without human intervention in its automated functions. The non-clinical testing included "Design verification and validation has demonstrated that the FLOW-i Anesthesia System performs within its specifications and within the limits of the applied performance standards." This primarily covers the standalone performance of the system's various components and software features under controlled conditions.


    7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

    For the non-clinical testing, the "ground truth" would be established by:

    • Engineering specifications and standards: The device performance was verified against existing technical specifications ("within its specifications and within the limits of the applied performance standards") such as IEC 60601-1, IEC 60601-2-13, ISO 5356-1, ISO 5360, ASTM F1101-90, and CGA V-5.
    • Reference measurements and simulation: Testing would involve using calibrated equipment and simulated patient environments to verify accuracy and functionality.
    • User needs and intended use: Design validation was performed to assure the product meets "its intended use and user needs, including usability."

    8. The sample size for the training set

    Not applicable in the context of a general machine learning "training set". The device's software is developed and verified through standard software engineering practices (code review, static code analysis, regression testing, Free User Testing). If internal machine learning components exist (not explicitly stated for this Anesthesia System), their training set details are not provided.


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

    Not applicable, as no specific machine learning "training set" is described for this device in the provided text.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1