Search Results

Meets the CDC guidelines for TB exposure control. Has a filter efficiency level of 95% against solid particulate aerosols free of oil (Type N95 respirator). Designed to be fluid resistant to splash and spatter of blood and body fluids.

Respirator consisting of nonwoven inter facing, filter media(s), a fluid barrier film, and an outer facing. It covers the nose and mouth of the wearer, and is held in place with two synthetic clastic headbands, conforming to the curvature of the wearer's nose with a malleable nosepiece.

This document is a 510(k) Premarket Notification for a respirator and surgical mask. It primarily focuses on demonstrating equivalence to a predicate device through performance testing. Therefore, it does not involve the type of study design or criteria typically used for AI-driven medical devices, which the provided questions are geared towards.

Here's an analysis based on the information provided, highlighting why many questions are not directly applicable:

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

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

The document mentions "Subject device samples" for each test but does not specify the exact sample size for any of the performance tests. The provenance of the data (country of origin, retrospective/prospective) is not stated, but given it's a 510(k) submission, it's presumed to be data generated by the manufacturer for the specific device, likely through prospective testing.

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)

This question is not applicable to the provided document. The device is a physical product (respirator/surgical mask), and its performance is evaluated against established physical and material standards (e.g., NIOSH, fluid resistance). There is no "ground truth" derived from expert interpretation of data.

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

This question is not applicable. Adjudication methods like 2+1 are used in clinical studies where multiple experts interpret medical images or clinical data. Here, objective physical tests are performed.

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 question is not applicable. MRMC studies are used for evaluating diagnostic devices, often involving AI, where human readers interpret cases. This document concerns a physical barrier device.

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

This question is not applicable. There is no algorithm or AI component in this device.

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

The "ground truth" for this device's performance is established by objective engineering and material science standards and regulatory requirements (e.g., NIOSH standards for filtration efficiency and airflow resistance, simulated fluid challenge for fluid resistance). There is no "expert consensus," "pathology," or "outcomes data" in the typical medical imaging sense.

8. The sample size for the training set

This question is not applicable. There is no AI model or algorithm that requires a training set for this device.

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

This question is not applicable for the same reason as above; there is no training set.

Ask a specific question about this device