Search Results

The emOx device is intended to generate oxygen of greater than 99.7% purity for emergency first aid administration.

emOx Portable Oxygen Generator

The provided document is a 510(k) clearance letter from the FDA for a device called "emOx Portable Oxygen Generator" (K984081). It confirms that the device is substantially equivalent to legally marketed predicate devices. However, this document does not contain the detailed information requested regarding acceptance criteria, study data, sample sizes, expert qualifications, or ground truth establishment.

A 510(k) clearance letter typically references that such information was provided by the manufacturer in their submission, but it does not reproduce the full study report or acceptance criteria within the letter itself. The letter focuses on the FDA's determination of substantial equivalence based on the submitted data.

Therefore, I cannot fulfill your request with the provided text. The requested information about acceptance criteria, study details, sample sizes, and ground truth would be found in the original 510(k) submission documentation, which is not included in this letter.

Ask a specific question about this device

The emOx™ device by MedTrak is intended to generate 99% pure oxygen for emergency first aid administration.

The emOx™ device is a lightweight, portable device that produces oxygen of greater than 99% purity by a chemical reaction. The evolved oxygen bubbles pass through a water-filled chamber to humidify the gas on its way to the patient via flexible, ribbed tubing and an open adult or pediatric face mask.

The device, other than the face mask, does not come into contact with the patient. The mask is a currently legally marketed adult or pediatric mask. The oxygen container is constructed of polypropylene. Therefore, the biocompatibility of the materials used is without significance.

This request pertains to the acceptance criteria and supporting studies for a medical device described in a 510(k) premarket notification, not an AI/ML powered device that relies on algorithms and ground truth data. Therefore, many of the questions regarding AI/ML specific details (e.g., sample sizes for training/test sets, expert adjudication, MRMC studies, ground truth establishment for training) are not applicable to this document.

However, I can extract the relevant information from the provided text regarding the device's acceptance criteria and the tests performed.

Acceptance Criteria and Reported Device Performance for MedTrak International Inc: emOx™

Study Details:

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

   • The document does not specify a "test set" in the context of data for an algorithm. Instead, it refers to non-clinical tests performed by independent laboratories on the device itself. Therefore, sample sizes for these tests are not provided, nor is the provenance of "data" in the sense of clinical data. It describes physical testing of the device.

2. 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 device is not an AI/ML algorithm that requires expert-established ground truth from a dataset. The "ground truth" here is the physical measurement of the device's output (e.g., purity, flow rate) by independent testing laboratories.

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

   • Not applicable for a physical device test. The tests were performed by "independent test laboratories," implying standard scientific measurement and reporting, not expert adjudication of cases.

4. 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-powered device. No clinical tests were performed as explicitly stated in the document.

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

   • Not applicable. This is not an AI/ML algorithm.

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

   • The "ground truth" for this device's performance is based on direct physical and chemical analytical measurements performed by independent test laboratories (e.g., gas chromatography for purity, flow meters for flow rate, analytical chemistry for contaminants).

7. The sample size for the training set:

   • Not applicable. This is not an AI/ML algorithm that requires a training set.

8. How the ground truth for the training set was established:

   • Not applicable. This is not an AI/ML algorithm that requires a training set.

Ask a specific question about this device