(104 days)
The Omni-5 Total O2 Delivery System is intended to supply low-pressure supplemental oxygen for the treatment of Respiratory Diseases in children through adults in the home, health care facility or hospital and to supply pressurized oxygen to fill oxygen cylinders for patient's ambulatory use.
The Omni 5 Total O2 Delivery System is comprised of conventional pressure adsorption technology which supplies low pressure oxygen to a nasal cannula and/or an intensifier which compresses a small portion of the gas to pressures up to 2015 psig in an oxygen gas cylinder for ambulatory use. The Omni 5 Total O2 Delivery System has a unique cylinder fill mechanism, which allows it to be easily and safely connected to the patient's Total O2 oxygen cylinder. The unique cylinder fill mechanism ensures that Total O₂ oxygen cylinders can only be filled through the unique fill port with the Total O₂ Delivery System. The original Total O2 Delivery System allowed for continuous oxygen flows and settings from 0 - 3 liters per minute, the modified Total O2 Delivery System (Omni 5 Total O2 Delivery System) allows for continuous oxygen flows and settings from 0 - 5 liters per minute. Additionally, the Omni 5 Total O2 Delivery System incorporates an automatic cylinder filling restart feature, should the oxygen purity fall below acceptable limits (cylinder filling stopped), then recover above the acceptable limits (cylinder filling restarted).
The provided document is a 510(k) summary for the "Respironics Omni 5 Total O2 Delivery System." This is a premarket notification for a medical device modification, not a study evaluating an AI algorithm or a diagnostic tool. Therefore, much of the requested information, such as acceptance criteria for AI performance metrics, sample sizes for test sets in an AI context, expert qualifications, adjudication methods, MRMC studies, standalone algorithm performance, and training set details, is not applicable to this type of regulatory submission.
The document focuses on demonstrating substantial equivalence to a predicate device, meaning the modified device is as safe and effective as a legally marketed device. This is achieved through design verification tests and a comparison of technological characteristics.
Here's an analysis of the provided information relative to your request:
1. Table of Acceptance Criteria and Reported Device Performance:
The document broadly states: "Design verification tests were performed on the Respironics Omni 5 Total O2 Delivery System as a result of the risk analysis and product requirements. All tests were verified to meet the required acceptance criteria."
However, the specific quantitative acceptance criteria and the detailed test results are not provided in this summary. The summary focuses on the modifications and their impact rather than a complete performance study for a novel device.
The key modifications and their implied performance improvements are:
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Modification #1: Continuous oxygen flow range (0-5 lpm) | Allows continuous oxygen flows and settings from 0 - 5 liters per minute (upgraded from 0-3 lpm) |
| Modification #2: Automatic cylinder filling restart function | Incorporates an automatic cylinder filling restart feature when oxygen purity recovers above acceptable limits. |
| Overall Safety and Effectiveness | Device is concluded to be safe and effective for its intended use. |
| Compliance with Predicate Device's Safety & Effectiveness | Substantially equivalent to the predicate device (Total O2 Delivery System, K013472). |
2. Sample size used for the test set and the data provenance:
- This is not applicable as this is a device modification submission, not a study on an AI algorithm's performance on a dataset. The "test set" refers to design verification tests performed on the physical device and its software, not a dataset of medical images or patient information.
- The document mentions "Design verification tests," which implies physical and functional testing of the device itself.
- No information on data provenance (country of origin, retrospective/prospective) is provided, as it's not relevant to this type of device submission.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- This is not applicable. The "ground truth" for a physical device's performance against design requirements is established through engineering specifications, standards compliance, and measurement instruments, not expert consensus on medical data.
4. Adjudication method for the test set:
- Not applicable for the reasons stated above.
5. If a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done:
- No, an MRMC study was not done. This type of study is relevant for diagnostic imaging AI, where the effectiveness of human readers with and without AI assistance is compared. The device in question is an oxygen delivery system, not a diagnostic tool.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- This question is based on the premise of an AI algorithm. The device, while containing software, is a physical medical device. The software modifications are for control and functionality (like automatic restart), not for independent diagnostic or predictive tasks that would typically constitute "standalone algorithm performance" in the context of an AI submission.
- "Software verification and validation" were conducted, which assesses the software's performance against its requirements, but not in a "standalone algorithm" sense as applied to diagnostic AI.
7. The type of ground truth used:
- For the hardware modifications (e.g., flow rate), the ground truth would be established by direct measurement using calibrated equipment against engineering specifications.
- For software modifications (e.g., automatic restart), the ground truth would be established by testing the software's logic and behavior against its functional requirements and design specifications, simulating conditions where purity falls/recovers.
- This is not "expert consensus, pathology, or outcomes data" in the typical sense of AI ground truth.
8. The sample size for the training set:
- Not applicable. This is not an AI algorithm developed through machine learning on a training set of data.
9. How the ground truth for the training set was established:
- Not applicable for the reasons stated above.
In Summary:
The provided document describes a 510(k) submission for a modification to a portable oxygen generator. The device's acceptance criteria are based on its mechanical performance, safety, and functionality, as demonstrated through design verification tests and comparison to a predicate device. The information requested regarding AI particularities (test set sample size, expert ground truth, MRMC, training sets) is not relevant to this type of medical device regulatory filing.
§ 868.5440 Portable oxygen generator.
(a)
Identification. A portable oxygen generator is a device that is intended to release oxygen for respiratory therapy by means of either a chemical reaction or physical means (e.g., a molecular sieve).(b)
Classification. Class II (performance standards).