LogoFDA 510(k) Search
Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K222305
    Device Name
    MissLan™ Digital Pregnancy Rapid Test
    Manufacturer
    Guangzhou Decheng Biotechnology Co. Ltd.
    Date Cleared
    2022-11-30

    (121 days)

    Product Code
    LCX
    Regulation Number
    862.1155
    Type
    Traditional
    Panel
    Clinical Chemistry
    Reference & Predicate Devices
    K173229
    Predicate For
    K241978
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    MissLan™ Digital Pregnancy Rapid Test is intended for the qualitative detection of human chorionic gonadotropin (hCG) in urine, as an aid in early detection of pregnancy. It is intended for use by people who would like to find out whether they are pregnant in a home environment.

    Only for use outside the body. For over the counter use.

    Device Description

    MissLan™ Digital Pregnancy Rapid Test is used for in vitro qualitative detection of Human Chorionic Gonadotropin (HCG) in human urine, and is designed to be tested in dip or midstream mode. The test device consists of a single test strip assembled in a plastic housing, with an absorbent tip. The device is in a ready-to-use format.

    AI/ML Overview

    The provided document details the performance characteristics of the MissLan™ Digital Pregnancy Rapid Test, which is a qualitative test for human chorionic gonadotropin (hCG) in urine.

    Here's an analysis of the acceptance criteria and the study that proves the device meets them:

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

    The document doesn't explicitly list "acceptance criteria" for each performance metric with quantitative targets. Instead, it presents the results of various analytical and clinical studies, implying that the observed performance meets the requirements for demonstrating substantial equivalence to the predicate device.

    However, we can infer the key performance metrics and the achieved results from the "Performance Characteristics" section. For qualitative pregnancy tests, crucial performance indicators include sensitivity (detection limit), specificity (absence of false positives), reproducibility, absence of hook effect, and agreement with predicate devices/professional results.

    Inferred Acceptance Criteria and Reported Device Performance:

    Performance CharacteristicAcceptance Criteria (Inferred)Reported Device Performance
    Analytical SensitivityAchieve 100% positive detection at the claimed sensitivity (25 mIU/mL hCG) and 100% negative detection at concentrations below the critical cutoff. Ensure consistent detection across multiple operators and lots.- 25 mIU/mL hCG: 100% positive for both midstream and dip testing across all 3 operators and 3 lots (total 150 positive results for each method, 300 total).- 0 mIU/mL hCG: 100% negative for both midstream and dip testing across all 3 operators and 3 lots (total 150 negative for each method, 300 total).- 12.5 mIU/mL hCG: 100% negative for both midstream and dip testing across all 3 operators and 3 lots (total 150 negative for each method, 300 total).- Overall Sensitivity (for both methods combined): Demonstrated to be 25 mIU/mL.- Reproducibility: Exhibited reproducible results across operators and lots.
    SpecificityNo false positive results should be observed from healthy non-pregnant individuals across various age groups. No significant cross-reactivity with structurally similar hormones (e.g., hLH, hFSH, hTSH) or hCG ß-core fragment.- Non-pregnant healthy females: 300 urine samples from healthy, non-pregnant females across pre-menopausal, peri-menopausal, and post-menopausal groups (100 per group) showed no false positive results for both dip and midstream testing.- Cross-reactivity: No cross-reactivity was observed with 500 mIU/mL hLH, 1000 mIU/mL hFSH, or 1000 uIU/mL hTSH.- hCG ß-core fragment: Performance not affected by hCG ß-core fragment concentrations up to 500,000 pmol/L.
    Hook EffectNo false negative results at very high concentrations of hCG.No hook effect observed at hCG concentrations up to 500,000 mIU/mL (all tested concentrations from 6,250 mIU/mL to 500,000 mIU/mL gave a positive result).
    InterferencePerformance should not be affected by common interfering substances, urine pH, or urine density.- Interfering substances: No interference effect observed for 25 listed substances (e.g., Glucose, Albumin, Hemoglobin, Acetaminophen, Aspirin, Ibuprofen, Ethanol, etc.) at specified concentrations.- Urine pH: Performance not affected by urine pH values between 4 and 9.- Urine Density: Performance not affected by urine density values between 1.000 and 1.035.
    Method ComparisonHigh conformity (ideally 100%) with a legally marketed predicate device.- Midstream Method: 100% concordance (55 positive, 45 negative) with the predicate device (n=100).- Dip Method: 100% concordance (47 positive, 53 negative) with the predicate device (n=100).- Overall Conformity: 100% between MissLan™ and the predicate device.
    Lay Person StudyHigh agreement between lay user results and professional results. Easy to use and interpret.- First Study (Self-Testing): 100% conformity (midstream: 55 positive, 45 negative; dip: 47 positive, 53 negative) between layperson results and professional results (for 200 women).- Second Study (Spiked Samples): 100% correct results for 5 mIU/mL (100 negative) and 25 mIU/mL (100 positive) hCG samples tested by laypersons.- Questionnaire: Consumers found the test easy to use and had no trouble understanding labeling and interpreting results.

    2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

    • Analytical Performance (Sensitivity/Reproducibility):

      • Sample Size: For each hCG concentration (0, 12.5, 15, 18.75, 22.5, 25, 50, 100, 200 mIU/mL):
        • 10 replicates per day for 5 days = 50 replicates per operator per lot.
        • 3 operators for each sample concentration.
        • 3 device lots.
        • Total tests per hCG concentration: 50 (replicates) * 3 (operators) * 3 (lots) = 450 tests.
        • Total tests for all concentrations: 450 * 9 = 4050 tests across all concentrations, operators, and lots.
      • Data Provenance: The document does not specify the country of origin of the data or whether it was retrospective or prospective. It implies a controlled laboratory setting (analytical performance).

    • Specificity (Non-pregnant females):

      • Sample Size: 300 urine samples (100 from pre-menopausal, 100 peri-menopausal, 100 post-menopausal).
      • Data Provenance: Not specified regarding country or retrospective/prospective.

    • Method Comparison Study:

      • Sample Size: 200 urine samples from women presenting to test for pregnancy (approximately half suspected pregnant, most in early stage < 5 weeks).
      • Data Provenance: Conducted at "three POC sites." Not specified regarding country or retrospective/prospective. The description "samples were collected from... women presenting to test for pregnancy" suggests prospective collection for the study.

    • Lay Person Study (First Study):

      • Sample Size: 200 women.
      • Data Provenance: Individuals with varying educational and occupational backgrounds from "three sites." Not specified regarding country or retrospective/prospective. This was a self-testing study.

    • Lay Person Study (Second Study):

      • Sample Size: 200 laypersons (100 tested 5 mIU/mL hCG aliquots, 100 tested 25 mIU/mL hCG aliquots).
      • Data Provenance: Not specified regarding country or retrospective/prospective. Samples were laboratory-prepared spiked pools, blind labeled.

    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)

    • Analytical Performance: The ground truth for spiked samples was established by the known concentrations of hCG added to negative urine. There were no "experts" establishing ground truth in the traditional sense for these tests.
    • Specificity (Non-pregnant females): Ground truth was established by the fact that the individuals were "healthy, non-pregnant female." No expert adjudication mentioned.
    • Method Comparative Study: The comparator device (predicate device) and "professional" testing served as a form of ground truth for comparison. "Three POC sites (3 different professionals using the candidate device and 1 professional using the predicate device at each site)" were involved. The qualifications of these professionals are not specified beyond being "professionals."
    • Lay Person Study (First Study): "Professional testing" served as the ground truth. Qualifications of professionals are not specified.
    • Lay Person Study (Second Study): The ground truth was the known concentration of hCG in the laboratory-prepared spiked samples (0 mIU/mL, 5 mIU/mL, 25 mIU/mL hCG). "Professionals" also tested these samples for comparison, but the inherent ground truth was the known spike concentration.

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

    • Analytical Performance & Specificity: None, as ground truth was established by known concentrations or clinical status.
    • Method Comparison Study: "Professional" testing results and predicate device results were used for comparison. The document does not describe an adjudication method for discrepancies between these, but rather implies they served as the reference for the candidate device's performance.
    • Lay Person Studies: "Professional results" served as the reference for the self-tested samples. No specific adjudication method (like 2+1 or 3+1) is described. In the second lay person study, the known spike concentration was the definitive ground truth.

    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

    • This is a study for a digital pregnancy rapid test, not an AI-assisted diagnostic imaging system for human readers. Therefore, an MRMC comparative effectiveness study involving AI assistance for human readers is not applicable and was not reported. The device uses "light reflection for the detection" and displays results on an LCD screen, not requiring human interpretation of complex images.

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

    • The device is a rapid diagnostic test that provides a digital readout. Its performance, as described in the Analytical Performance section, is essentially "standalone" in that it produces a result based on its internal mechanism. While a direct "algorithm only" performance study in the context of complex software algorithms isn't explicitly named, the core functional performance data (sensitivity, specificity, interference, hook effect) represents the device's inherent capability to detect hCG. The "human-in-the-loop" aspect is the user collecting and applying the urine sample, then reading the digital display, not interpreting a complex output.

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

    • Known Spiked Concentrations: For analytical sensitivity, hook effect, cross-reactivity, and interfering substance studies, the ground truth was established by precisely preparing urine samples with known concentrations of hCG or other substances. This is a highly controlled laboratory method.
    • Clinical Status/Predetermined Criteria: For specificity studies, the ground truth was the enrollment of "healthy, non-pregnant female" volunteers.
    • Professional Reference/Predicate Device: For method comparison and lay person studies, the results obtained by "professionals" or the legally marketed "predicate device" served as the comparative ground truth.

    8. The sample size for the training set

    • This document describes a 510(k) submission for a rapid diagnostic test kit, not a machine learning model that requires a "training set" in the computational sense. The device is based on a lateral flow immunoassay with an optical detection system. Therefore, the concept of a "training set" for an AI algorithm is not applicable to this type of device.

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

    • As explained in point 8, the product is a rapid diagnostic test kit, not a machine learning model. Thus, there is no training set and consequently, no method for establishing ground truth for a training set in this context.
    Ask a Question

    Ask a specific question about this device

    Page 1 of 1