Search Results

The Surgical Mask (Model: WK1701-02A, WK1701-03A and WK1701-04A) is intended to be worn to protect both the patient and healthcare personnel from the transfer of microorganisms, body fluids, and particulate material. The Surgical Mask is 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 Model WK1701-02A is Level 1 barrier as ASTM F2100 requirements.

The Model WK1701-03A is Level 2 barrier as ASTM F2100 requirements.

The Model WK1701-04A is Level 3 barrier as ASTM F2100 requirements.

The proposed device(s) includes 3 models, which are WK1701-02A, WK1701-03A and WK1701-04A. Three of them all are Blue color, and Flat Pleated type mask, utilizing Ear Loops' way for wearing, and they all have Nose Piece design for fitting the facemask around the nose.

All three models of proposed device(s) share same materials and structure, they all are manufactured with three layers, the inner and outer layers are made of polypropylene spunbond fabric, and the middle layer is made of polypropylene meltblown fabric.

The proposed device(s) of Level 1, Level 2 and Level 3 have the same material. The proposed device(s) are manufactured with three layers, the inner and outer layers are made of polypropylene spunbond fabric, and the middle layer is made of polypropylene meltblown fabric.

The nose piece contained in the proposed device(s) is in the layers of the facemask to allow the user to fit the facemask around their nose, which is made of polypropylene coated galvanized iron wire.

The proposed device(s) is held in place over the user's mouth and nose by two elastic ear loops welded to the facemask. The elastic ear loops are made with nylon and spandex.

The proposed device(s) are sold non-sterile and are intended to be single-use, disposable devices.

The provided document is a 510(k) Premarket Notification for a Surgical Mask, not a deep learning AI device. Therefore, the questions related to deep learning AI evaluation (such as sample size for training/test sets, data provenance, number of experts for ground truth, adjudication methods, MRMC studies, standalone performance, and ground truth establishment for training data) are not applicable to this submission.

The document describes the acceptance criteria and the study that proves the device meets those criteria for Surgical Masks, based on non-clinical performance and biocompatibility testing.

Here's the information extracted from the document relevant to the acceptance criteria and device performance:

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

The document provides several tables detailing the performance characteristics and comparisons. The most direct representation of acceptance criteria and results for the proposed device is found in the "Non-Clinical Test Conclusion" section (pages 7-8).

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

• Sample Size: Non-clinical tests were conducted using "3 nonconsecutive lots with 32 samples per lot" for verification. This suggests a total of 96 samples (3 lots * 32 samples/lot) were tested for performance characteristics across all models.
• Data Provenance: The manufacturer is Jiangmen Ningrui Medical Supplies Co., Ltd. in China. The tests are non-clinical (laboratory performance and biocompatibility tests), not clinical data from patients. The document does not specify if the testing was performed retrospectively or prospectively, but typically lab verification tests are conducted prospectively during development and manufacturing.

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

N/A. This document pertains to non-clinical performance and biocompatibility testing of a physical medical device (surgical mask), not an AI/deep learning system requiring expert consensus for ground truth on clinical images. The "ground truth" for these tests is established by standardized laboratory methods and measurements (e.g., flow rates, particle counts, chemical reactions, physical observations).

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

N/A. Adjudication methods are relevant for subjective interpretations, common in clinical imaging for AI device evaluation. This is a physical device tested against objective, quantitative standards.

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

N/A. This is not an AI device. No human reader studies or MRMC comparative effectiveness studies were performed. The comparative effectiveness is against the stated ASTM and ISO standards and a predicate device's performance, not human performance with/without AI assistance.

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

N/A. This is not an AI algorithm. The performance tests are "standalone" in the sense that they evaluate the mask itself against specified physical and biological criteria, without human interaction during the test other than operating the testing equipment.

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

The "ground truth" for the performance characteristics of surgical masks is established by the standardized test methods themselves (e.g., ASTM F2100, ASTM F1862, EN 14683, ISO 10993, 16 CFR 1610). These standards define the acceptable range or threshold for a given physical or biological property (e.g., a specific BFE percentage, a maximum differential pressure, absence of cytotoxicity). The results are quantitative measurements against these predefined, objective criteria.

8. The sample size for the training set

N/A. This is not an AI/machine learning device; there is no "training set."

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

N/A. There is no training set for this type of device submission.

Ask a specific question about this device