Search Results

The Surgical Face Masks are 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 sterile.

The Surgical Face Masks are Flat Pleated type mask, utilizing Ear straps way for wearing, and they all have Nose clip design for fitting the face mask around the nose. The Surgical Face Masks are manufactured with three layers. The outer layer is made of polypropylene spun-bond non-woven fabric. The middle layer with filtration function is made of polypropylene melt-blown non-woven fabric. The inner layer contact with face is made of polypropylene spun-bond non-woven fabric. The nose clip is made of polyethylene strip with iron wire inside. The ear straps are made of spandex polyester fiber. The Surgical Masks are single use, disposable device, provided sterile.

The provided text is a 510(k) Premarket Notification for a Surgical Face Mask. It details the device's characteristics, comparison to a predicate device, and non-clinical testing results. However, it does not contain information about an AI/ML-based device or a comparative effectiveness study involving human readers.

Therefore, I cannot fulfill your request for information regarding:

• A table of acceptance criteria and reported device performance for an AI/ML device.
• Sample size used for the test set and data provenance for an AI/ML device.
• Number of experts and qualifications to establish ground truth for an AI/ML device.
• Adjudication method for an AI/ML device.
• Multi-reader multi-case (MRMC) comparative effectiveness study or effect size for an AI/ML device.
• Standalone performance for an AI/ML algorithm.
• Type of ground truth used for an AI/ML algorithm.
• Sample size for the training set for an AI/ML algorithm.
• How ground truth for the training set was established for an AI/ML algorithm.

The document focuses on the physical and performance characteristics of a surgical face mask, such as fluid resistance, particulate filtration, bacterial filtration, differential pressure, flammability, and biocompatibility.

Here's the information that is available in the document regarding the physical device (surgical face mask):

1. Table of Acceptance Criteria and Reported Device Performance (for a Surgical Face Mask):

2. Sample Size Used for the Test Set and Data Provenance:

• For Fluid Resistance: 32 samples (implied from "29 out of 32 pass").
• Other tests' specific sample sizes are not explicitly stated, but often these are conducted on a statistically significant number of samples as per the respective standards.
• Data Provenance: The document does not specify the country of origin for the non-clinical test data (e.g., where the lab testing was performed), nor does it describe the "data" as retrospective or prospective in a clinical study sense, as these are lab-based performance tests for a physical product.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
Not applicable, as this document refers to a physical device and laboratory performance testing, not AI/ML model evaluation requiring human expert ground truth.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:
Not applicable for laboratory performance testing of a physical device.

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:
No MRMC study was done, as this is a physical medical device (surgical face mask), not an AI/ML diagnostic or assistive device. The document explicitly states: "No clinical study is included in this submission."

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
Not applicable, as this is a physical surgical face mask, not an AI/ML algorithm.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
For the physical device, the "ground truth" for compliance is defined by the technical specifications and methodologies outlined in the listed ISO/ASTM/EN standards. This is laboratory-derived data, not clinical ground truth.

8. The sample size for the training set:
Not applicable, as this is a manufactured physical product, not an AI/ML model that requires a training set.

9. How the ground truth for the training set was established:
Not applicable, for the reason mentioned in point 8.

Ask a specific question about this device