Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K150214
    Manufacturer
    Date Cleared
    2015-07-31

    (182 days)

    Product Code
    Regulation Number
    862.1345
    Reference & Predicate Devices
    Predicate For
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The OneTouch Verio Flex™ Blood Glucose Monitoring System is intended to be used for the quantitative measurement of glucose (sugar) in fresh capillary whole blood samples drawn from the fingertip. The OneTouch Verio Flex™ Blood Glucose Monitoring System is intended to be used by a single patient and should not be be shared.

    OneTouch Verio Flex™ Blood Glucose Monitoring System is intended for self testing outside the body (in vitro diagnostic use) by people with diabetes at home as an aid to monitor the effectiveness of diabetes control. The OneTouch Verio Flex™ Blood Glucose Monitoring System is not to be used for the diagnosis of or screening of diabetes, or for neonatal use.

    The OneTouch® Verio Test Strips are for use with the OneTouch Verio Flex™ Blood Glucose Meter to quantitatively measure glucose drawn from the fingertips.

    Device Description

    The OneTouch Verio Flex Blood Glucose Monitoring System consists of the OneTouch Verio Flex Blood Glucose Meter, OneTouch® Verio® Test Strips, OneTouch® Verio® Level 3 and Level 4 Control Solutions, Lancing Device and Sterile Lancets. The OneTouch Verio Flex Blood Glucose Monitoring System measures the glucose content of a blood sample by means of an electrical current produced in the test strip and sent to the meter for measurement.

    AI/ML Overview

    OneTouch Verio Flex™ Blood Glucose Monitoring System Acceptance Criteria and Study Details

    1. Acceptance Criteria and Reported Device Performance

    The OneTouch Verio Flex™ Blood Glucose Monitoring System was designed and tested in accordance with ISO 15197:2013(E) guidelines for system accuracy. The key acceptance criteria and reported performance from the device's system accuracy study are summarized below.

    Acceptance Criteria per ISO 15197:2013(E) Clause 6.3 - System Accuracy (Healthcare Professional Use):

    Glucose Concentration RangeAcceptance Criterion (Percentage of samples within range)
    < 100 mg/dL≥ 95% of results within ±15 mg/dL
    ≥ 100 mg/dL≥ 95% of results within ±15%
    Overall (Combined)≥ 95% of results within ±15 mg/dL or ±15%

    Reported Device Performance (Healthcare Professional Use):

    Glucose Concentration RangeReported Performance (Percentage of samples within range)
    < 100 mg/dL100% of results within ±15 mg/dL (Pooled Lots A-C)
    ≥ 100 mg/dL99.3% of results within ±15% (Pooled Lots A-C)
    Overall (Combined)99.5% of results within ±15 mg/dL or ±15% (Pooled Lots A-C)

    Acceptance Criteria per ISO 15197:2013(E) Clause 8 - User Performance Evaluation (Lay User):

    Glucose Concentration RangeAcceptance Criterion (Percentage of samples within range)
    < 100 mg/dL≥ 95% of results within ±15 mg/dL
    ≥ 100 mg/dL≥ 95% of results within ±15%
    Overall (Combined)≥ 95% of results within ±15 mg/dL or ±15%

    Reported Device Performance (Lay User Performance Evaluation):

    Glucose Concentration RangeReported Performance (Percentage of samples within range)
    < 100 mg/dL93.1% of results within ±15 mg/dL (Note: This is below the ISO 95% criterion)
    ≥ 100 mg/dL98.6% of results within ±15%
    Overall (Combined)97.6% of results within ±15 mg/dL or ±15%

    Note on Lay User Performance: While the overall and ≥100 mg/dL results met the ISO 15197:2013(E) Clause 8 criteria, the performance for glucose concentrations <100 mg/dL was 93.1%, which is below the 95% acceptance criterion mentioned in the ISO standard for this range. However, the summary statement on page 15 still concludes that the system meets "all design input specifications" and ISO 15197:2013 requirements, suggesting that possibly the specific internal acceptance criteria for this portion might have been different or considered acceptable within the context of the overall system accuracy. Without further information, this discrepancy for the <100 mg/dL range in lay user performance is noted.


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

    Method Comparison Performance (Healthcare Professional Use):

    • Sample Size: 115 subjects
    • Data Provenance: Not explicitly stated, but implies prospective collection as it involved "fingersick samples from diabetic subjects" and testing against a reference method. The location is not specified.

    System Accuracy in compliance with ISO 15197:2013(E) Clause 6.3 (Healthcare Professional Use):

    • Sample Size: 100 subjects
    • Data Provenance: Not explicitly stated, but implies prospective collection as it involved "fingertip capillary blood samples obtained by healthcare professionals". The location is not specified.

    Lay User Performance Evaluation (Clause 8, first study summary):

    • Sample Size: 172 lay persons
    • Data Provenance: Not explicitly stated, but implies prospective collection as it involved "fingertip capillary blood samples obtained by lay persons". The location is not specified.

    User Performance Evaluation in compliance with ISO 15197:2013(E) Clause 8 (second study summary):

    • Sample Size: 167 lay persons
    • Data Provenance: Not explicitly stated, but implies prospective collection as it involved "fingertip capillary blood samples obtained by lay persons". The location is not specified.

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

    The document does not specify the number or qualifications of experts used to establish the ground truth. Instead, the ground truth was established using a recognized laboratory reference method: the Yellow Springs Instrument (YSI) 2300 (or YSI 2300 STAT PLUS) glucose analyzer. This instrument itself is considered the "expert" for generating accurate glucose measurements.


    4. Adjudication method for the test set

    Not applicable. The ground truth was established by a laboratory reference instrument (YSI analyzer), not by human experts 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

    Not applicable. This device is a blood glucose monitoring system, not an AI-powered diagnostic imaging or interpretation tool that involves "human readers." Therefore, an MRMC comparative effectiveness study with AI assistance is not relevant to this product.


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

    Yes, a standalone performance evaluation was done. The "Method Comparison Performance" study and the "System Accuracy in compliance with ISO 15197:2013(E) Clause 6.3" study assessed the device's accuracy when operated by healthcare professionals, comparing its readings directly to the laboratory reference method (YSI). This represents the algorithm's performance with trained users, effectively functioning as a standalone assessment of the device's accuracy in a controlled environment. The "Lay User Performance Evaluation" also assessed the device's accuracy when operated by intended users, albeit with human interaction in using the device.


    7. The type of ground truth used

    The ground truth used was laboratory reference measurements obtained from a Yellow Springs Instrument (YSI) 2300 (or YSI 2300 STAT PLUS) glucose analyzer. This is considered a highly accurate and recognized method for determining glucose concentrations.


    8. The sample size for the training set

    The document does not provide a sample size specifically for a "training set." Blood glucose monitoring systems like the OneTouch Verio Flex™ typically do not use machine learning models that require a separate training set in the same way AI algorithms do. The development process would involve calibration and optimization based on chemical and electrical principles rather than iterative training on a dataset. The studies described are validation studies.


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

    As noted above, the concept of a "training set" in the context of machine learning does not directly apply to this device. For the development and calibration of the glucose monitoring system, the ground truth would have been established through highly accurate laboratory reference methods (like those provided by a YSI analyzer) during the chemical and electrical engineering phases, prior to the validation studies described in the document. The document doesn't detail these initial development and calibration phases.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1