Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K110381
    Date Cleared
    2011-12-22

    (315 days)

    Product Code
    Regulation Number
    864.5220
    Reference & Predicate Devices
    Why did this record match?
    Device Name :

    CELL-DYN EMERALD 22 SYSTEM

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The CELL-DYN Emerald 22 System is a quantitative multi-parameter automated hematology analyzer designed for in-vitro-diagnostic use in clinical laboratories for enumeration of the following parameters: WBC, LYM%, LYM # , MON%, MON # , NEU%, NEU #, EOS%, EOS # , BAS%, BAS #, RBC, HCT, MCV, RDW, HGB, MCH, MCHC, PLT, MPV in K2EDTA anti-coagulated whole blood.

    The CELL-DYN Emerald 22 is indicated for use to identify patients with hematologic parameters within and outside of established reference ranges.

    Device Description

    The CELL-DYN Emerald 22 System is a bench-top analyzer consisting of the main analyzer with data module, display station, and printer. The main analyzer, data module, and display station are housed in a single chassis. The printer is a stand-alone module.

    The CELL-DYN Emerald 22 open sampler is equipped to aspirate blood from a collection tube that has been opened and is held under the open sample aspiration probe.

    AI/ML Overview

    Here's a breakdown of the acceptance criteria and study information for the CELL-DYN Emerald 22 System, based on the provided text:

    1. Table of Acceptance Criteria and Reported Device Performance

    The provided 510(k) summary does not explicitly state numerical acceptance criteria for each parameter. Instead, it describes a "substantial equivalence" study where the CELL-DYN Emerald 22 System was compared to the predicate device, the CELL-DYN 3700 System. The study's conclusion is that the device is substantially equivalent.

    Therefore, the "acceptance criteria" were implicitly met if the performance of the Emerald 22 was deemed comparable to the legally marketed 3700. The text states:

    "The system evaluation included data for background, correlation, precision, linearity and carryover."

    Lack of specific criteria is common in 510(k) summaries when demonstrating substantial equivalency to a predicate device. The performance is deemed acceptable if it aligns with the established predicate's performance.

    ParameterAcceptance Criteria (Implicit: Comparable to CELL-DYN 3700)Reported Device Performance
    BackgroundPerformance comparable to CELL-DYN 3700Data supports substantial equivalence
    CorrelationPerformance comparable to CELL-DYN 3700Data supports substantial equivalence
    PrecisionPerformance comparable to CELL-DYN 3700Data supports substantial equivalence
    LinearityPerformance comparable to CELL-DYN 3700Data supports substantial equivalence
    CarryoverPerformance comparable to CELL-DYN 3700Data supports substantial equivalence
    OverallSubstantially Equivalent to CELL-DYN 3700"The CELL-DYN Emerald 22 System is substantially equivalent to the CELL-DYN 3700 (predicate device)."

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

    The document mentions "a clinical trial" where the device was compared to the predicate, but it does not specify the sample size used for this test set.

    The data provenance is not explicitly stated regarding country of origin. The submission is to the FDA in the USA, implying US regulatory context. It's likely a prospective study, as it's a "clinical trial" for a new device comparison, but this is not definitively stated.

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

    This information is not provided in the document. The study framework is a comparison of the new device's measurements against a predicate device's measurements, not against an expert-established "ground truth" for individual parameters.

    4. Adjudication Method for the Test Set

    This information is not provided in the document. Given the nature of a comparison study between two automated hematology analyzers, an adjudication method for individual parameter values is typically not applicable in the same way it would be for, say, image analysis interpreted by humans. The comparison would involve statistical methods to assess agreement or correlation between the two devices.

    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

    There was no MRMC comparative effectiveness study done. The CELL-DYN Emerald 22 System is an automated hematology analyzer, not an AI-assisted diagnostic tool that human readers would interact with. The study compares the new automated device to an existing automated device.

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

    Yes, this was a standalone performance study. The CELL-DYN Emerald 22 System is an "automated hematology analyzer" performing quantitative measurements. The study evaluated its performance (background, correlation, precision, linearity, carryover) in comparison to another automated device, without direct human intervention in the primary measurement process itself.

    7. The Type of Ground Truth Used

    The "ground truth" in this context is the measurements obtained from the predicate device, the CELL-DYN 3700 System. The study aims to demonstrate that the new device's measurements are substantially equivalent to those of the predicate, which is already a legally marketed and presumably validated device.

    8. The Sample Size for the Training Set

    This information is not applicable/not provided. Automated hematology analyzers like the CELL-DYN Emerald 22 are typically built on established physical and chemical principles (e.g., electrical impedance, optical analysis for cell counting, hemoglobin analysis). They do not usually involve "training sets" in the machine learning sense to develop their core algorithms for parameter enumeration. Their algorithms are based on physics and chemistry, not learned from large datasets in the way an AI diagnostic model would be.

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

    This information is not applicable/not provided for the reasons stated above.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1