K Number
K014192
Date Cleared
2002-05-23

(153 days)

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

Immunoassay for the qualitative detection of methamphetamine at the cut-off of 1000 ng/mL in urine to assist in screening of drugs of abuse samples at home and work place. For In vitro Diagnostic Use

Immunoassay for the qualitative detection of methamphetamine at the cut-off of 1000 ng/mL in urine to assist in screening of drugs of abuse samples. For In vitro Diagnostic Use

Device Description

Life Sign® Home Drug Test (MET) is simple one step immunochromatographic test for the rapid, qualitative detection of methamphetamine.

Status Stik™ MET is simple one step immunochromatographic test for the rapid, qualitative detection of methamphetamine.

AI/ML Overview

Here's an analysis of the acceptance criteria and study information based on the provided text:

Acceptance Criteria and Reported Device Performance

The provided documents describe two variations of the device:

  1. Life Sign® Home Drug Test (MET): Intended for home or workplace use (Over-The-Counter).
  2. Status Stik™ MET, AccuSign®Stik MET, AccuStik™ MET, AccuSign® MET, Status DSTM MET, AccuStrip™ MET (collectively referred to as "Professional Use Devices"): Intended for professional/prescription use.

Both devices are for the qualitative detection of methamphetamine in urine at a cutoff of 1000 ng/mL.

Acceptance CriteriaReported Device PerformanceComments
Qualitative Detection of Methamphetamine in Urine at 1000 ng/mL CutoffThe devices demonstrate 100% correlation with the predicate device (K990786; Status DS™ DOA 10) in detecting methamphetamine qualitatively at the 1000 ng/mL cutoff.This is the primary functional acceptance criterion. The 100% correlation is a strong indicator of meeting this.
Substantial Equivalence to Predicate Device (K990786; Status DS™ DOA 10)The devices "are substantially equivalent to the K990786; Status DS™ DOA 10. Both products use the same assay principle and immunochromatographic assay to detect methamphetamine qualitatively. The detection cutoff level is the same."This is the overarching regulatory acceptance criterion for 510(k) clearance. The provided text claims and concludes substantial equivalence.
Overall Accuracy (for Consumer Study / OTC version)LifeSign® Home Drug Test (MET) showed over 96% overall accuracy in a consumer study.This criterion is specific to the Life Sign® Home Drug Test (MET), indicating its performance in the hands of intended users (consumers).

Study Information

  1. Sample Size Used for the Test Set and Data Provenance:

    • Test Set Size: 94 specimens (50 negative and 44 positive) were used for comparison between the new device and the predicate device.
    • Data Provenance: Not explicitly stated (e.g., country of origin). The study appears to be a retrospective comparison as it evaluates the new device against already available specimens.
  2. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:

    • This information is not provided in the given text. The "ground truth" seems to be established by comparison to a legally marketed predicate device (Status DS™ DOA 10) rather than by independent expert assessment of each sample.
  3. Adjudication Method for the Test Set:

    • This information is not provided. The method mentioned is a direct comparison to the predicate device's results.
  4. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

    • No, an MRMC comparative effectiveness study was not explicitly mentioned or described. The study focused on a 100% correlation between the new device and a predicate device.
    • The "consumer study" for the LifeSign® Home Drug Test (MET) that showed "over 96% overall accuracy" might involve multiple lay users, but it's not described as a formal MRMC comparative effectiveness study demonstrating improvement with AI vs. without AI. The device described is a rapid immunoassay, not an AI-powered diagnostic system.
  5. Standalone Performance (Algorithm Only Without Human-in-the-Loop Performance):

    • Yes, a standalone performance was done. The 100% correlation study between the new device and the predicate device is a standalone performance evaluation of the device itself.
    • For the professional use versions, the device is intended for clinical laboratory or professional settings, implying human interpretation of the result, but the 100% correlation study is about the device's inherent detection capability.
    • For the home use version, the "consumer study" also evaluates the standalone performance, likely including the human-in-the-loop (the consumer performing and interpreting the test). However, it's not an AI algorithm.
  6. Type of Ground Truth Used:

    • The primary ground truth for the comparison study was the results obtained from a legally marketed predicate device (K990786; Status DS™ DOA 10).
    • For the 94 specimens, the predicate device results likely served as the reference standard to determine if the 50 negative and 44 positive classifications were truly negative and positive, respectively. This implies the predicate device's performance was accepted as truth.
  7. Sample Size for the Training Set:

    • This information is not provided. The description focuses on a comparison study/test set, not the development or training of the immunoassay itself. As this is a rapid immunoassay (not an AI/machine learning model), the concept of a "training set" in the context of machine learning does not apply directly. The development would involve analytical validation rather than machine learning training.
  8. How the Ground Truth for the Training Set Was Established:

    • Not applicable as no training set (in the machine learning sense) is described. The "ground truth" reference during the immunoassay development would typically involve analytical methods (e.g., GC/MS, HPLC) to confirm the presence and concentration of the target analyte in spiked or characterized samples.

N/A