(62 days)
The intended function and use of the Invacare Model Venture HomeFill II with oxygen conserver is to provide supplemental oxygen to patients in the home and to supply pressurized oxygen to fill gas cylinders for the patient's personal ambulatory use. It is not intended to sustain or support life.
The Invacare Venture Home Fill II with oxygen conserver is an electromechanical, prescription device designed for use in the home, by patients that require supplemental oxygen. It consists primarily of a 5 liter per minute (1pm) oxygen concentrator, a compressor module, and a portable oxygen cylinder with specially adapted cylinder fitting that includes an oxygen conserver. The oxygen conserver delivers oxygen to the user at the beginning of each breath instead of on a continuous basis.
The concentrator provides continuous flow of oxygen at concentrations of 87% to 96%, at flow rates of 0 to 51pm. The compressor fills the cylinder with oxygen concentrations of 90% to 96%. and the cylinder regulator allows flow rates of 0 to 6 lpm. The oxygen supplied by the oxygen concentrator is supplemental and is not considered to be life susporting or life sustaining. The system is not sold or labeled as sterile.
The provided text is a 510(k) summary for Invacare Corporation's Model Venture HomeFill II with Oxygen Conserver. This document is a premarket notification to the FDA for a medical device and is primarily focused on demonstrating substantial equivalence to a legally marketed predicate device.
Crucially, this document does not contain the specific information requested about acceptance criteria for device performance or a detailed study proving the device meets those criteria, especially in the context of an AI-powered device or human-in-the-loop studies.
The section "Performance Data" states: "A number of mechanical and electrical tests were conducted on the Invacare Model HomeFill II with oxygen conserver and the oxygen conserver to demonstrate that the device performs as intended." However, it does not provide details of what those tests were, what the acceptance criteria were, or what the reported performance was against those criteria. It also does not mention any studies involving AI, human readers, or image analysis, as assumed in many of the questions.
Therefore, I cannot populate the requested table and answer many of the questions based on the provided text.
Here's what I can infer or definitively state from the provided text, addressing the questions as much as possible:
1. A table of acceptance criteria and the reported device performance
Based on the provided text, this information is not available. The document states "A number of mechanical and electrical tests were conducted... to demonstrate that the device performs as intended," but it does not specify what those tests were, what the acceptance criteria were, or the performance results.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
Based on the provided text, this information is not available. The document mentions "mechanical and electrical tests" but gives no details about sample sizes or data provenance.
3. 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)
Based on the provided text, this information is not applicable and not available. This device is an oxygen concentrator, not an AI diagnostic device that would typically involve expert-established ground truth for a test set in the way a medical imaging AI would.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Based on the provided text, this information is not applicable and not available. See point 3.
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
No MRMC study was done, and this information is not applicable. The device described is an oxygen concentrator, not an AI system intended to assist human readers in interpretation.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
This is not an AI algorithm, so this concept is not applicable. The device is an electro-mechanical oxygen concentrator.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
Based on the provided text, this information is not applicable in the typical sense for AI/diagnostic devices. For an oxygen concentrator, "ground truth" would likely relate to objective measurements of oxygen concentration, flow rates, and other physical parameters, validated against established scientific standards for medical gases and equipment, rather than expert consensus on a diagnostic image. The document does state the concentrator provides "oxygen at concentrations of 87% to 96%" and "fills the cylinder with oxygen concentrations of 90% to 96%", suggesting these are measured performance characteristics.
8. The sample size for the training set
Based on the provided text, this information is not applicable and not available. This device does not involve a "training set" in the context of machine learning or AI.
9. How the ground truth for the training set was established
Based on the provided text, this information is not applicable and not available. See point 8.
§ 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).