K Number
K152493
Date Cleared
2016-04-25

(237 days)

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

The POGO Automatic 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 fingertips. The POGO Automatic Blood Glucose Monitoring System is intended to be used by a single person and should not be shared.

The POGO Automatic 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 POGO Automatic Blood Glucose Monitoring System should not be used for the diagnosis of or screening of diabetes or for neonatal use. The POGO Automatic Blood Glucose Monitoring System is indicated for use in adults and adolescents (13 and up).

POGO Automatic Test Cartridges are for use with the POGO Automatic Meter to quantitatively measure glucose (sugar) in fresh capillary whole blood samples drawn from the fingertips.

POGO Control Solutions are used with the POGO Automatic Meter to indicate appropriate user technique and to indicate that the POGO Automatic Test Cartridge and POGO Automatic Meter are functioning properly.

Device Description

The POGO Automatic Blood Glucose Monitoring System (POGO BGMS) is a quantitative assay for the detection of glucose in capillary whole blood sampled from the fingertip. The system includes multiple glucose-oxidase-based dry-reagent test strips housed in a cartridge and a photometer to read the glucose-dependent color change from the in-use strip. The meter uses calibration information from a barcode on the disposable cartridge to convert the reflectance information into a plasma-equivalent glucose value.

The POGO BGMS automates finger lancing, blood sample collection and placement onto the test strip, and calculation of the blood glucose result, and so requires significantly fewer steps than existing BGMSs to obtain a glucose result. The POGO BGMS accomplishes this via a 10-test cartridge where each foil-sealed test includes a hollow lancet, spring, and test strip. The user does not need a separate lancing device since the lancing mechanism is built into individual test cells of the cartridge. Additionally, used tests are retained within the cartridge for added user convenience. Control solutions are available to confirm correct system performance.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study information for the Pogo Automatic Blood Glucose Monitoring System, based on the provided text:

Acceptance Criteria and Device Performance

Acceptance Criteria CategoryAcceptance Criteria (from "The protocol acceptance criteria were met")Reported Device Performance (as described in the text)
RepeatabilityMet the protocol acceptance criteria.%CVs ranged from 2.3% to 3.4% across five whole blood samples (41.8 mg/dL to 306.7 mg/dL) tested in replicates of 10 with 10 meters.
Intermediate PrecisionMet the protocol acceptance criteria.%CVs were 6.5% (2.1 SD), 3.1%, and 3.2% for three levels of commercial controls (approx. 30, 100, and 300 mg/dL) tested in duplicate with 10 meters over 10 days.
LinearityMet the protocol acceptance criteria.Linear throughout the claimed dynamic range, based on testing a whole blood sample spiked with nine glucose levels (17 mg/dL to 529 mg/dL) in replicates of 10.
Hematocrit ToleranceMet the protocol acceptance criteria.Accurate throughout the claimed 20-60% hematocrit range, based on studies with four glucose levels (60, 120, 250, and 400 mg/dL) and seven different hematocrits.
Altitude ToleranceMet the protocol acceptance criteria.Provides accurate results at altitudes up to the claimed 10,000 feet, based on studies at sea level, 5,000 feet, and 10,000 feet with blood at nominal glucose levels of 60, 120, and 300 mg/dL.
Temperature ToleranceMet the protocol acceptance criteria.Provides accurate results across the tested 4°C to 40°C range and the claimed temperature range of 10°C to 40°C, based on testing at five temperatures with nominal glucose levels of 60, 120, and 300 mg/dL.
Humidity ToleranceMet the protocol acceptance criteria.Provides accurate results when tested across the claimed humidity range of 10% to 90% RH, based on testing at 10%, 50%, and 90% relative humidity with nominal glucose levels of 60, 120, and 300 mg/dL.
Temperature and Humidity CombinationsMet the protocol acceptance criteria.Provides accurate results at extreme combinations of temperature and humidity (25°C/45% RH, and 10℃/40℃ crossed with 10%/90% RH) with three nominal glucose levels of 60, 120, and 300 mg/dL.
Sample Volume ToleranceMet the protocol acceptance criteria.Accurate when tested with a sample volume between 250 and 1000 nL. At 80% felt it was more convenient. Majority (51%) agreed they'd better adhere to testing, and >81% would recommend it.

Study Details

  1. Sample size used for the test set and the data provenance:

    • Test Set Sample Size (Clinical): 287 subjects with diabetes.
    • Data Provenance: Subjects were enrolled across US clinical sites. The study was prospective as subjects performed tests, were observed, and completed questionnaires.
  2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

    • Number of Experts: Not explicitly stated as a specific number. The text mentions "health care professionals (HCPs)" observed subjects and "HCPs also performed assisted fingerstick tests." It doesn't specify how many or their exact qualifications beyond "health care professionals."
    • Qualifications: "Health care professionals (HCPs)." No specific details like years of experience or specialization (e.g., endocrinologist, nurse) are provided.
  3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

    • The text does not describe an adjudication method for the test set results. The accuracy of the POGO BGMS results was compared directly against a reference instrument (YSI).
  4. 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, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. This is a blood glucose monitoring system, not an imaging AI device. The study focused on the performance of the device itself and user experience.
  5. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:

    • Yes, a standalone performance was done for the analytical studies (Repeatability, Intermediate Precision, Linearity, Hematocrit Tolerance, etc.). These tests evaluate the device's inherent analytic capabilities under controlled conditions.
    • The clinical accuracy study also includes a "user self-testing" arm, which represents the device's performance when used by the intended lay user (human-in-the-loop).
  6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

    • Clinical Accuracy Ground Truth: YSI reference instrument. For blood glucose monitoring systems, a YSI (Yellow Springs Instrument) glucose analyzer is considered a highly accurate laboratory reference method.
  7. The sample size for the training set:

    • The provided document describes a 510(k) summary for a medical device (blood glucose monitor). For such devices, "training sets" in the context of machine learning (AI) are not typically applicable. The device relies on chemical reactions and optical measurement, calibrated during manufacturing and design verification. The "training" for the device's performance is embedded in its design, chemical formulation, and manufacturing process.
    • Therefore, a specific "training set sample size" as one would discuss for an AI algorithm is not applicable here.
  8. How the ground truth for the training set was established:

    • As noted above, a "training set" in the AI sense is not applicable. The device's internal calibration and performance parameters would have been established during its development and manufacturing using high-precision reference methods (like YSI) and extensive analytical studies to ensure accuracy and precision across its operational range. These internal calibration processes are part of the device's engineering and quality control, not a "training set" for an algorithm.

§ 862.1345 Glucose test system.

(a)
Identification. A glucose test system is a device intended to measure glucose quantitatively in blood and other body fluids. Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus, neonatal hypoglycemia, and idiopathic hypoglycemia, and of pancreatic islet cell carcinoma.(b)
Classification. Class II (special controls). The device, when it is solely intended for use as a drink to test glucose tolerance, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 862.9.