Search Results

The Surgical Mask is intended to be worn to protect both the patient and healthcare personnel from transfer of microorganisms, body fluids and particulate material. These face masks are intended for use in infection control practices to reduce the potential exposure to blood and body fluids. This is a single use, disposable device(s), provided non-sterile.

The Surgical Mask is a single use, Flat Pleated mask with ear loops and nose piece. The Surgical Mask is consisting of three layers, the inner and outer layers are made of spunbonded polypropylene, and the middle layer is made of melt blown polypropylene filter. The Surgical Mask uses different colors to distinguish the inner and outer layers, the inner layer is white and the outer layer is blue. The ear loops are held in place over the users' mouth and nose by two elastic ear loops welded to the facemask. The nose piece in the layers of facemask is to allow the user to fit the facemask around their nose, which is made of polypropylene and metal wire. The Surgical Mask is sold non-sterile and is intended to be single use, disposable devices.

This document describes the premarket notification (510(k)) for a Surgical Mask (K201852) and its substantial equivalence to a predicate device (K182515). The information provided focuses on non-clinical performance testing to demonstrate this equivalence. Since this is a submission for a Surgical Mask, the "device" in the context of your request refers to the surgical mask itself, not an AI or software-based medical device.

Therefore, many of the questions you've asked, which are typically relevant for AI/ML-based medical devices, are not applicable to this submission. This document does not describe an AI/ML device that requires a test set, ground truth established by experts, MRMC studies, or training sets.

Here's an analysis based on the provided document:

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

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

• Sample sizes for test set:
  • Fluid Resistance: 32 samples (implied by "32 out of 32 passes").
  • Other tests (Particulate Filtration, Bacterial Filtration, Differential Pressure, Flammability, Biocompatibility): The exact sample size for each test is not explicitly stated, but tests were conducted. These are material/product performance tests, not "data provenance" in the AI/ML sense.
• Data Provenance: Not applicable in the context of a surgical mask. The tests are non-clinical laboratory tests performed on the physical device. The manufacturing country is China.

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)

• Not Applicable. This is a physical device (surgical mask) and its performance is evaluated through standardized non-clinical laboratory tests, not by expert review of data for ground truth establishment, as would be the case for an AI/ML device.

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

• Not Applicable. See point 3.

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 a surgical mask, not an AI-assisted diagnostic tool. No human reader studies were performed or are relevant.

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

• Not Applicable. This is a physical device, not an algorithm.

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

• Not Applicable. The "ground truth" for a surgical mask's performance is defined by the standardized test methods (e.g., ASTM F1862 for fluid resistance) and the associated physical measurements. There isn't a "ground truth" in the diagnostic or AI sense.

8. The sample size for the training set

• Not Applicable. This is a physical device, not an AI/ML model that requires a training set.

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

• Not Applicable. See point 8.

Ask a specific question about this device