K Number
K101154
Manufacturer
Date Cleared
2011-03-28

(339 days)

Product Code
Regulation Number
868.5440
Panel
AN
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The intended use of the Device is to generate and deliver USP 93% oxygen for supplemental oxygen use only or filling cylinders. The device must not be used for or with any life-supporting applications.

The Device is intended to be used only by trained personnel in hospitals, health care facilities or remote locations where bottled oxygen is not readily available.

The instruction manual of the device recommends an alternate source of supplemental oxygen in the event of a power outage, alarm condition, or mechanical failure.

Device Description

Air contains 21 % oxygen, 78% nitrogen, 0.9% argon, and 0.1% other gases. AirSep PSA Oxygen units separate this small percentage of oxygen from the compressed air through a unique Pressure Swing Adsorption (PSA) process. The compressed air flows through a filter assembly before the air enters the adsorber vessels. A particulate/foam filter removes condensed water, oil, dirt, scale, etc. from the feed air, and then, a separate coalescing filter (if present) removes additional oil and water vapor.

The oxygen generator uses in its adsorber vessels an inert ceramic material called molecular sieve to separate compressed air into oxygen and other gases. The unique properties of molecular sieve allow it to attract, or adsorb, nitrogen physically from air under pressure. This allows oxygen to exit the adsorbers as a product gas.

While one adsorber produces oxygen, the other depressurizes to exhaust the waste gases it adsorbed (collected) during the oxygen production cycle. The entire oxygen generating process is completely regenerative, which makes it both reliable and virtually maintenancefree. The molecular sieve does not normally require replacement.

The medical devices in this submission refer to the following oxygen concentrators manufactured by AirSep Corporation:

| Model | Flow (scfh) | Oxygen Delivery
Pressure (psig) |
|---------|-------------|------------------------------------|
| Centrox | 32 | 50 |
| Ultrox | 17 | 20 |
| Reliant | 17 | 50 |

All of these devices are designed to deliver the oxygen with USP 93 % purity. Centrox and Reliant units are also available for cylinder filling option. Ultrox is used only to fill cylinders.

Centrox, Ultrox and Reliant units are comprised of an air compressor that uses ambient air to produce higher pressure feed air.

These models have the same indications for use. Together these products are referred to as Device.

The device is intended to be USP 93% oxygen generator. As such, to assure the purity, an Oxygen Analyzer is integrated in each device and an alarm is activated if the purity is outside of the safe range.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study information based on the provided text:

Acceptance Criteria and Device Performance

Acceptance CriteriaReported Device Performance
Delivers USP 93% oxygen purityVerified to deliver USP 93% oxygen purity
Oxygen flow rate per modelTested and verified (Centrox: 32 scfh, Ultrox: 17 scfh, Reliant: 17 scfh)
Oxygen delivery pressure per modelTested and verified (Centrox: 50 psig, Ultrox: 20psig, Reliant: 50 psig)
Total Volatile Organic Compounds (VOC's)Well below accepted standards
ParticulatesWell below accepted standards
Functionality under component failureAbility to deliver USP 93% oxygen verified
Functionality under improper valve cyclingAbility to deliver USP 93% oxygen verified
Functionality under overdrawingParameters verified
Compliance to EMC requirementsConfirmed
Compliance to electrical safety standardsConfirmed

Study Details

  • Sample size used for the test set and the data provenance: Not explicitly stated. The document mentions "various phases, internal testing, verification and validation as well as external testing and validation" and that "every device to deliver USP 93% oxygen was verified." This suggests a comprehensive internal testing process on a representative sample of devices, but specific numbers and provenance (e.g., country of origin, retrospective/prospective) are not detailed. An "Independent laboratory testing" was also performed.

  • Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. This device is an oxygen concentrator, and its performance (purity, flow rate) is measured objectively using instruments, not subjective expert assessment.

  • Adjudication method for the test set: Not applicable. Performance metrics are objective and measurable by instruments.

  • 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 devices where human interpretation is involved.

  • If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: Yes, the performance testing described is a standalone evaluation of the device's ability to produce oxygen of a certain purity at specified flow rates and pressures. There is no human involved in the core function of oxygen generation.

  • The type of ground truth used: Instrumental measurements and chemical analysis.

    • Oxygen purity (USP 93%) was measured directly.
    • Flow rate and pressure were measured directly.
    • VOC's and particulates were measured through independent laboratory testing.
  • The sample size for the training set: Not applicable. This device is a mechanical system, not an AI/machine learning algorithm that requires a "training set" in the conventional sense. The design and engineering process involved iterative testing and refinement, but not a formally defined "training set" of data.

  • How the ground truth for the training set was established: Not applicable, as there isn't a "training set" in the AI/ML context. The design was likely developed and refined based on engineering principles, predicate device performance, and iterative physical testing during the design process to meet the specified performance targets (e.g., USP 93% oxygen).

§ 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).