Search Results

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

The Nordiwell Medical Face Mask has a flat-folded design consisting of three layers that are comprised of an (polypropylene spunbond) inner and outer cover web and (polypropylene melt blown) filter web. The mask has earloops or tie strings to secure the mask over the users' mouth and face and includes a malleable nosepiece to provide a firm fit over the nose. This is a single use, disposable device, provided non-sterile.

This document is a 510(k) Premarket Notification for a medical face mask. It does not describe an AI/ML powered medical device, but rather a physical product. Therefore, many of the requested criteria regarding AI/ML model evaluation (e.g., training set, ground truth acquisition, MRMC studies, standalone performance with human-in-the-loop, number of experts for ground truth) are not applicable.

However, I can extract the acceptance criteria and performance data for this physical medical device from the provided text.

Here's the information based on the provided document:

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

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

• Sample Size for performance tests: For each performance test (Fluid Resistance, Particulate Filtration, Bacterial Filtration, Differential Pressure, Flammability), the sample size was 32 units. The document also states "Bench test was conducted on 3 nonconsecutive lots of Medical Face Mask". This implies 32 units per lot, or a total of 32 units drawn across 3 nonconsecutive lots. The wording "32 of 32 pass" for each specific test strongly suggests that the sample size for each test was 32.
• Data Provenance: The tests were conducted internally by the manufacturer (Changzhou Combat Protective Equipment Co., Ltd.) in China, as indicated by the contact information and location. The studies are essentially prospective in nature, as they involve testing newly manufactured devices to verify performance.

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

• Not Applicable. This is a physical product, not an AI/ML device that requires human expert annotation for ground truth. The "ground truth" here is the result of standardized physical and biological tests conducted against established ASTM and ISO standards.

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

• Not Applicable. This is a physical product. Test results are objective measurements from laboratory equipment and procedures, not subjective human interpretations requiring 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 not an AI/ML medical device. No human reader studies were conducted as the device is a medical face mask.

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

• Not Applicable. This is not an AI/ML medical device.

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

• The "ground truth" for this medical device's performance is based on established international and national standards (ASTM F1862-17, ASTM F2299-17, ASTM F2101-19, EN 14683:2019, 16 CFR 1610, ISO 10993 series). These standards define the test methodologies and acceptance criteria for medical face masks. The testing is performed in laboratory settings to objectively measure the device's physical and biological properties.

8. The sample size for the training set

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

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

• Not Applicable. This is a physical product, not an AI/ML device.

Ask a specific question about this device