Search Results

To filter possible bacteria and viruses from the patient exhalation, for use with carbon monoxide monitors. For use by healthcare professionals only.

The SafeBreath Filter mouthpiece is a single patient contacting mouthpiece consisting of a 22mm diameter cardboard tube with a filter for the filtration of possible bacteria and viruses from the patient exhaled breath into the breath monitor device to prevent cross contamination.

The SafeBreath mouthpieces connect directly to the carbon monoxide monitors, such as CO Check Pro and CO Screen (K171129).

The provided text is a 510(k) Summary for the SafeBreath Filter Mouthpiece (K190022). It primarily focuses on demonstrating substantial equivalence to a predicate device through performance testing related to biocompatibility and filtration efficiency.

However, the provided text does not describe a study involving an AI/Machine Learning device that utilizes a test set, expert ground truth, multi-reader multi-case studies, or addresses improved human reader performance with AI assistance. The device in question is a physical filter mouthpiece, not a software algorithm.

Therefore, many of the requested criteria related to AI/ML device performance evaluation cannot be answered from the provided document. I will extract the information that is present concerning the device's acceptance criteria and the studies conducted.

Here's an analysis based only on the provided text for the SafeBreath Filter Mouthpiece:

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

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

• Biocompatibility Tests: The exact sample sizes for the in-vitro cytotoxicity study are not specified. For the in-vivo studies:
  • Skin Sensitization (Guinea Pigs): Sample size not explicitly stated, but standard animal study protocols would involve a sufficient group size.
  • Intracutaneous Reactivity (New Zealand White Rabbits): Sample size not explicitly stated, but the test involved "single administration at five sites" in rabbits, implying multiple rabbits.
• Filtration Efficiency Test (Public Health England Report 19/018): The sample size for the filters tested is not explicitly stated, but it refers to "Aged 4 year old SafeBreath mouthpieces."
• Data Provenance: The studies appear to be laboratory-based performance tests, likely conducted in a controlled environment by specific testing organizations (e.g., Public Health England). The data provenance is not described in terms of "country of origin" from a clinical dataset or whether it's retrospective/prospective, as these are material/device performance tests not clinical data studies.

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

• This question is not applicable to the provided document. The "ground truth" for this device is established through objective laboratory testing against established standards (ISO 10993 for biocompatibility) and direct measurement for filtration efficiency, not through expert interpretation of data like in an AI/ML context.

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

• This question is not applicable. As these are objective laboratory tests, there is no need for expert adjudication of results in the way it's done for clinical image interpretation.

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. This device is a physical filter, not an AI-powered diagnostic tool, so no MRMC study or AI assistance evaluation was performed or is relevant here.

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

• This question is not applicable. This is a physical device, not an algorithm.

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

• The "ground truth" for the performance claims are based on:
  • Biocompatibility Standards: Compliance with ISO 10993 series through laboratory tests measuring specific biological responses (cytotoxicity, sensitization, irritation).
  • Direct Measurement: For filtration efficiency, the ground truth is the directly measured percentage of bacterial and viral particles filtered under controlled laboratory conditions.

8. The sample size for the training set

• This question is not applicable. There is no "training set" as this is not a machine learning device.

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

• This question is not applicable. There is no "training set" for this physical device.

Ask a specific question about this device