Search Results

VITEK®2 Gram Negative Piperacillin/Tazobactam is designed for antimicrobial susceptibility testing of Acinetobacter baumanii. Escherichia coli. Klebsiella pneumoniae. Pseudomonas aeruginosa, Citrobacter koseri, Morganella morganii, Proteus mirabilis, Proteus vulgaris, Providencia rettgeri, Providencia stuartii, and Salmonella enterica. It is intended for use with the VITEK® 2 and VITEK® 2 COMPACT Systems as a laboratory aid in the determination of in vitro susceptibility to antimicrobial agents.

The VITEK 2 AST Cards are essentially miniaturized versions of the doubling dilution technique for determining the minimum inhibitory concentration (MIC) microdilution methodology. The bacterial isolate to be tested is diluted to a standardized concentration in 0.45% saline before being used to rehydrate the antimicrobial medium within the card. The VITEK 2 System automatically fills, seals and places the card into the incubator/reader. The VITEK 2 COMPACT has a manual filling and sealing operation. The VITEK 2 monitors the growth of each well in the card over a defined period of time (up to 18 hours). At the completion of the incubation cvcle, a report is generated that contains the MIC value along with the interpretive category result for each antibiotic contained on the card.

This document describes the regulatory submission for the VITEK® 2 Gram Negative Piperacillin/Tazobactam system, specifically a Special 510(k) for a device modification related to updated breakpoints for Pseudomonas aeruginosa. The provided text details the device's intended use and performance without explicitly laying out acceptance criteria in a table format common for AI/ML device clearances. However, by analyzing the "Special 510(k) Summary" section, we can infer the acceptance criteria and performance as presented for this specific modification.

Here's a breakdown of the requested information based on the provided text:

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

Based on the information provided, the primary performance metric reported for this modification is Category Agreement.

Note: The document specifies that the performance is evaluated against the CLSI broth microdilution reference method, as defined in the FDA Class II Special Controls Guidance Document: Antimicrobial Susceptibility Test (AST) Systems; Guidance for Industry and FDA, Issued Feb. 5, 2003. This guidance outlines the specific criteria for Category Agreement (CA), Essential Agreement (EA), and overall acceptable performance for AST systems.

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

The document does not explicitly state the sample size (number of isolates) used for the test set. It mentions that "The data are representative of performance on both the VITEK 2 and VITEK 2 COMPACT instrument platforms." No specific information about the country of origin or whether the data was retrospective or prospective is provided. The focus of this specific submission is on the re-evaluation of performance due to a breakpoint change for a single organism (Pseudomonas aeruginosa).

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

The ground truth is established by the CLSI broth microdilution reference method. This is a standardized laboratory method for determining antimicrobial susceptibility, not typically requiring expert human interpretation beyond standard laboratory procedures and quality control. Therefore, the concept of "experts" in the context of ground truth establishment, as it applies to AI/ML devices requiring human labeling, is not relevant here.

4. Adjudication method for the test set

Not applicable. The ground truth is a laboratory reference method (CLSI broth microdilution), not a subjective human interpretation requiring adjudication.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done

Not applicable. This is an antimicrobial susceptibility test system, not an imaging device requiring human reader interpretation or AI-assistance for diagnosis. The device generates MIC values and interpretive categories (Susceptible, Intermediate, Resistant).

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

The VITEK 2 system automatically performs the test and generates results. The reported performance (92.3% Category Agreement) is the standalone performance of the device against the reference method. There isn't a "human-in-the-loop" component in the direct interpretation of the raw data from the device to produce the MIC and categorical result.

7. The type of ground truth used

The ground truth used is the CLSI broth microdilution reference method. This is a gold-standard laboratory method for determining minimum inhibitory concentrations (MICs) of antimicrobials, which then dictate the interpretive category (susceptible, intermediate, resistant).

8. The sample size for the training set

The document does not provide details on a distinct "training set" or its sample size. The VITEK 2 system operates based on established principles of growth detection and comparison to provide MICs. The original development and "training" (calibration) would have been part of the predicate device's clearance (K113200). This submission is a modification to update the interpretation when a new breakpoint for a specific organism is applied, not a new AI model requiring a separate training phase.

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

As in point 8, the concept of a "training set" for an AI/ML model is not directly applicable in the same way for this type of device. The original calibration and validation of the VITEK 2 system, which would serve a similar purpose to "training," would have established its internal algorithms and growth detection parameters. This would have involved extensive testing against the CLSI broth microdilution reference method with a large collection of isolates. The current modification focuses on applying a new interpretive breakpoint, not retraining the core measurement algorithm.

Ask a specific question about this device