(43 days)
The Microdiagnostics, Inc. Micro-Strip for Cocaine Metabolites is intended to qualitatively detect the metabolites of cocaine in urine at the SAMHSA/NIDA cutoff limit of 300 ng/ml.
Not Found
The provided FDA document (K981388) is a 510(k) clearance letter for the "Micro-Strip for Cocaine Metabolites" device. This document primarily focuses on regulatory approval and does not contain specific details about acceptance criteria, device performance studies, or the methodologies typically associated with evaluating AI/ML-based devices.
The device described is a rapid, qualitative immunoassay for detecting cocaine metabolites in urine, which is a chemical assay, not an AI/ML algorithm. Therefore, many of the requested criteria (e.g., sample size for AI test set, expert qualifications for ground truth, MRMC studies, training set details) are not applicable to this type of device and are not present in the provided text.
However, I can interpret the available information to address the relevant aspects as best as possible for a traditional diagnostic device.
Here's an analysis based on the provided text:
Device Name: Micro-Strip for Cocaine Metabolites
Intended Use: To qualitatively detect the metabolites of cocaine in urine at the SAMHSA/NIDA cutoff limit of 300 ng/ml.
1. Table of Acceptance Criteria and Reported Device Performance
Strictly speaking, the document doesn't explicitly state "acceptance criteria" as a separate section with numerical goals for sensitivity, specificity, etc., nor does it provide a detailed "reported device performance" table as one might expect for a modern clinical study. However, the intended use defines a key performance characteristic. The device must accurately detect cocaine metabolites at a specific cutoff.
| Acceptance Criterion (Inferred) | Reported Device Performance (Inferred/Not explicitly stated with data) |
|---|---|
| Qualitative detection of cocaine metabolites in urine. | The device is intended to perform this function. The FDA's clearance implies that the sponsor demonstrated adequate performance for this intended use, likely through comparison to a reference method, but the specific performance metrics (e.g., sensitivity, specificity, accuracy) are not included in this letter. |
| Detection at the SAMHSA/NIDA cutoff limit of 300 ng/ml. | The device is intended to operate at this specific cutoff. The FDA's clearance implies its capability to do so, though specific data is absent from this document. |
| Substantial equivalence to a predicate device. | The FDA found the device "substantially equivalent" to predicate devices, which means its performance and safety profile are comparable. The specific predicate device and its performance are not detailed here. |
2. Sample size used for the test set and the data provenance
This information is not provided in the FDA clearance letter. For traditional diagnostic assays, performance is typically evaluated using a panel of urine samples (both positive and negative) that have been confirmed by a reference method (e.g., GC/MS). The exact number of samples, their origin, or whether they were retrospective or prospective are not mentioned in this document.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
This is not applicable and not provided. For a chemical assay like this, ground truth is established by a definitive analytical method (e.g., Gas Chromatography-Mass Spectrometry (GC/MS)), not by human expert opinion or interpretation in the way AI models are evaluated.
4. Adjudication method for the test set
This is not applicable and not provided. As ground truth is established by a definitive analytical method, there would be no need for expert 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
This is not applicable. This device is a rapid diagnostic strip, not an AI-assisted diagnostic tool requiring human interpretation and an MRMC study.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
This is not applicable. This device is a standalone chemical assay, not an algorithm. Its performance is inherent to the chemical reactions on the strip.
7. The type of ground truth used
While not explicitly stated in this letter, for qualitative drug screening assays, the ground truth is typically established by a definitive analytical method, most commonly Gas Chromatography-Mass Spectrometry (GC/MS). GC/MS provides quantitative and highly specific confirmation of the presence and concentration of drug metabolites.
8. The sample size for the training set
This is not applicable and not provided. This is a chemical assay, not an AI/ML model, so there is no "training set" in the computational sense. The development of the assay involves optimizing reagents and conditions, but not "training data" in the AI context.
9. How the ground truth for the training set was established
This is not applicable. As there is no training set for an AI/ML algorithm, this question does not apply.
§ 862.3250 Cocaine and cocaine metabolite test system.
(a)
Identification. A cocaine and cocaine metabolite test system is a device intended to measure cocaine and a cocaine metabolite (benzoylecgonine) in serum, plasma, and urine. Measurements obtained by this device are used in the diagnosis and treatment of cocaine use or overdose.(b)
Classification. Class II (special controls). A cocaine and cocaine metabolite test system is not exempt if it is intended for any use other than employment or insurance testing or is intended for Federal drug testing programs. The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 862.9, provided the test system is intended for employment and insurance testing and includes a statement in the labeling that the device is intended solely for use in employment and insurance testing, and does not include devices intended for Federal drug testing programs (e.g., programs run by the Substance Abuse and Mental Health Services Administration (SAMHSA), the Department of Transportation (DOT), and the U.S. military).