Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K210346
    Date Cleared
    2022-11-08

    (638 days)

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

    Sysmex XW-100 Automated Hematology Analyzer

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

    The XW-100 Automated Hematology Analyzer (XW-100) is a quantitative automated hematology analyzer intended for in vitro diagnostic use to classify and enumerate the following parameters for venous whole blood anticoagulated with K2/K3 EDTA: WBC, RBC, HGB, HCT, MCV, PLT, LYM%, Other WBC%, NEUT%, LYM#, Other WBC#, and NEUT#. It is not for use in diagnosing or monitoring patients with primary or secondary chronic hematologic diseases/ disorders, oncology patients, critically ill patients, or children under the age of 2.

    Device Description

    The XW-100 Automated Hematology Analyzer for CLIA Waived Use is an electrical resistance type blood cell counter. This technology may be variously referred to as direct current (DC) or impedance. The analyzer uses a human whole blood specimen and produces results for 12 hematology parameters, including the basic complete blood count (CBC), 3 part white blood cell (WBC) differential, and MCV.

    AI/ML Overview

    The provided text is a 510(k) premarket notification letter from the FDA to Sysmex America, Inc. regarding their XW-100 Automated Hematology Analyzer. It primarily details the device's intended use, technological principles, and a comparison to a predicate device, focusing on a software update.

    Crucially, this document does not contain the detailed study information typically requested for acceptance criteria and device performance proofs. It explicitly states that the device is "as safe and effective as the predicate device" and that "The results of the design control activities demonstrate that the device is substantially equivalent to the predicate device." This suggests that the detailed performance studies were likely conducted for the original predicate device (K172604/CW170012), and for this new submission (K210346), the focus was on demonstrating that the software update did not negatively impact the previously established safety and effectiveness.

    Therefore, many of the requested fields cannot be directly answered from the provided text. However, I can infer some information based on the context of a 510(k) submission for a software update.

    Here's an attempt to answer the questions based on the provided text and general 510(k) submission understanding for software updates:


    Acceptance Criteria and Device Performance Study Information:

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

    The document does not provide a table of acceptance criteria or specific reported device performance metrics for the XW-100 with software version 1.14. It relies on the principle of "substantial equivalence" to the predicate device (XW-100 with software version 1.03). The acceptance criterion for this submission is that "the device is as safe and effective as the predicate device" and that the "proposed software update was implemented in accordance to design controls and risk management."

    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 does not specify the sample size used for any test set or the data provenance. For a software update submission, testing would typically involve verifying that the new software performs identically or acceptably compared to the previous version across a range of samples. This would likely be internal validation data.

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

    Not applicable/Not mentioned. The device is an automated hematology analyzer, and its "ground truth" for parameters like WBC, RBC, etc., is typically established by reference methods or validated calibrated instruments, not subjective expert interpretations as would be the case for imaging diagnostics. The context here is a software update for an already cleared device.

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

    Not applicable/Not mentioned. No human expert adjudication method would be used for an automated hematology analyzer's numerical output for the specified parameters.

    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 automated hematology analyzer, not an AI-assisted diagnostic tool that human readers would use to improve their interpretation of images or data. It produces direct numerical measurements.

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

    Yes, the device (the XW-100 Automated Hematology Analyzer) inherently operates in a "standalone" fashion, as it is an automated instrument performing quantitative measurements. The evaluation for this 510(k) was focused on the software update (version 1.03 to 1.14) and ensuring it maintained the performance of the predicate device.

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

    For an automated hematology analyzer, the "ground truth" for its measurements (WBC, RBC, HGB, HCT, MCV, PLT, LYM%, Other WBC%, NEUT%, LYM#, Other WBC#, and NEUT#) is established through:

    • Reference methods: Highly accurate and precise laboratory methods.
    • Validated reference materials/calibrators: Materials with known and traceable values.
    • Comparison to predicate devices: As stated, the updated device is compared to the original XW-100 with version 1.03.

    8. The sample size for the training set

    Not applicable/Not mentioned. This document pertains to a 510(k) software update for an automated instrument, not a de novo AI/ML algorithm that requires a distinct "training set" in the context of machine learning model development. The software update is likely to be code changes rather than a re-trained model.

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

    Not applicable/Not mentioned, as there is no mention of a typical "training set" for an AI/ML model for this software update.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1