FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

The MicroScan® MICroSTREP plus™ Panel is used to determine quantitative and/or qualitative antimicrobial agent susceptibility of colonies grown on solid media of aerobic streptococci, including Streptococcus pneumoniae. After inoculation, panels are incubated for 20 - 24 hours at 35°C +/- 1°C in a non-CO2 incubator, and read visually according to the Package Insert. The antimicrobial susceptibility tests are miniaturizations of the broth dilution susceptibility test. Various antimicrobial agents are diluted in water, buffer or minute concentrations of broth to concentrations bridging the range of clinical interest. Panels are rehydrated with 115 ul Mueller-Hinton broth supplemented with 2-5% lysed horse blood (LHB) and buffered with 50 mM HEPES, after inoculation of the broth with a standardized suspension of the organism in saline. After incubation in a non-CO2 incubator for 20-24 hours, the minimum inhibitory concentration (MIC) for the test organism is manually read by observing the lowest antimicrobial concentration showing inhibition of growth.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study details for the MicroScan® MICroSTREP plus™ Panel with Clindamycin, based on the provided text:

Acceptance Criteria and Device Performance

Acceptance Criteria	Reported Device Performance
Overall Essential Agreement (compared to NCCLS frozen Reference Panel)	96.2% for Clindamycin
Reproducibility	Acceptable reproducibility and precision for Clindamycin
Quality Control	Acceptable results for Clindamycin

Note: The document states that the performance was reviewed against the "FDA DRAFT document "Guidance on Review Criteria for Assessment of Antimicrobial Susceptibility Devices", dated March 8, 2000." This implies that the 96.2% Essential Agreement met the acceptance threshold defined in that guidance document. Specific numeric thresholds for reproducibility and quality control are not explicitly stated but are implied to have been met with "acceptable" results.

Study Details

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

Test Set Sample Size: Not explicitly stated as a single number. The external evaluation was conducted with "fresh and stock Efficacy isolates and stock Challenge strains." The text doesn't specify the total number of isolates used in these categories combined for the Clindamycin evaluation.
Data Provenance: Not explicitly stated (e.g., country of origin). The study involved "external evaluation," suggesting the data was collected from multiple sites beyond the manufacturer's internal labs. It was a prospective study in the sense that the new device's performance was compared to a reference method, but the isolates themselves could be either retrospectively collected "stock" or prospectively collected "fresh."

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

Not applicable. This device determines antimicrobial susceptibility, where the "ground truth" is established by a reference laboratory method (NCCLS frozen Reference Panel), not by human expert interpretation of images or clinical data.

4. Adjudication method for the test set

Not applicable. As the ground truth is established by a reference laboratory method, there is 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

Not applicable. This is an in vitro diagnostic device for determining microbial susceptibility. It does not involve human readers interpreting cases or AI assistance in that context. The "reading" is manual observation of an MIC for the test organism in the panel.

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

The device is described as being "read visually according to the Package Insert" to observe the "lowest antimicrobial concentration showing inhibition of growth." This indicates a human-in-the-loop process for reading the results. The "device" itself (the panel) is a diagnostic assay, and its performance is assessed based on the accuracy of the manual reading compared to the reference. There is no "algorithm only" performance reported in this context.

7. The type of ground truth used

The ground truth was an NCCLS frozen Reference Panel. This is a recognized standard laboratory method for determining antimicrobial susceptibility.

8. The sample size for the training set

Not applicable. This is a microbiology susceptibility test panel, not an AI/machine learning algorithm that requires a "training set" in the conventional sense. The "development" of the panel involves formulating the dilutions and components, not training a model.

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

Not applicable, as there is no "training set" or AI algorithm involved.

Summary

Regulation Number and Section

§ 866.1640 Antimicrobial susceptibility test powder.

(a)
Identification. An antimicrobial susceptibility test powder is a device that consists of an antimicrobial drug powder packaged in vials in specified amounts and intended for use in clinical laboratories for determining in vitro susceptibility of bacterial pathogens to these therapeutic agents. Test results are used to determine the antimicrobial agent of choice in the treatment of bacterial diseases.(b)
Classification. Class II (performance standards).