(124 days)
The CerroZone Mini is intended as a room recirculating air cleaner. The system is used for filtering out and inactivating airborne particles (i.e., bacteria and viruses) from the air for medical purposes.
The CerroZone Mini is a medical recirculating air cleaner that uses multiple inactivation processes, including use of reactive oxidizing species (ozone) and ultraviolet radiation, to inactivate bacteria and viruses in the CerroZone Mini may be used in medical facilities. Once turned on, inlet air is passed through CerroZone Mini's inline flow-through design which inactivates bacteria and viruses in a single pass flow-through. The device generates 110 cubic feet of air per minute (CFM), or 2.00 air changes per hour (ACH) in a standard 5,600 cubic foot room. The process of air being inlet, purified, then outlet, lasts approximately 1.2 seconds. A 4 LOG reduction, or 99.99% reduction, of airborne particles in a standard 579 cubic foot room is achieved in 45 minutes or less.
The prompt requests information about a study proving that a medical device meets acceptance criteria. The provided text is an FDA 510(k) clearance letter for the CerroZone Mini, a medical recirculating air cleaner. The document details the device, its indications for use, comparison to a predicate device, and summarizes non-clinical testing.
However, the provided text does not contain the specifics of a study proving device acceptance criteria in the way one might expect for an AI/algorithm-driven medical device, which is what the prompt implies by asking about sample sizes for test and training sets, expert ground truth, adjudication methods, and MRMC studies. The device in question is an air cleaner, and the "studies" mentioned are laboratory tests assessing its ability to reduce airborne biological agents and ozone emissions, not clinical trials or AI performance evaluations involving human-in-the-loop scenarios.
Therefore, many of the requested points are not applicable to the data provided for this specific device. I will address only the points for which information is available in the text.
Here's the analysis based on the provided document:
1. A table of acceptance criteria and the reported device performance
| Test Methodology | Purpose | Acceptance Criteria | Reported Device Performance |
|---|---|---|---|
| MS2 bacteriophage aerosolized into a sealed environmental bioaerosol chamber containing the CerroZone Mini. | To evaluate the efficacy of the CerroZone Mini at reducing viability of aerosolized MS2 bacteriophage by a combination of entrainment and destruction. | Greater than 4 log reduction (99.99%). | Average net log reduction / time, MS2 bacteriophage, 5.76 ± 0.20 / 45 mins. |
| Methicillin Resistant Staphylococcus epidermidis (MRSE) aerosolized into a single-pass flow through chamber that modeled the CerroZone Mini. | To evaluate the efficacy of the CerroZone Mini at reducing viability of aerosolized bacteria by a combination of entrainment and destruction. | Greater than 3 log reduction (99.99%) in single-pass testing. | Demonstrated effectiveness against Staphylococcus epidermidis. |
| Ozone Emissions assessed per Section 40 of UL 867 & CSA C22.2 No.187. | To ensure that ozone emissions are within acceptable levels. | Within the maximum acceptable level of ozone, 0.050 ppm, given in 21 CFR 801.415. | Emits between 0.000 and 0.002 ppm of Ozone with a measured absolute max of 0.002 ppm. |
| Electromagnetic Compatibility and Electrical Safety (EN/IEC 60601-1-2, UL 867 & CSA C22.2 No.187). | To demonstrate safety regarding electromagnetic disturbances and electrical safety. | Compliance to EN/IEC 60601-1-2 and UL 867 & CSA C22.2 No.187. | The subject device is equivalent to a predicate device that tested in compliance. |
2. Sample sizes used for the test set and the data provenance
The document does not specify exact "sample sizes" in terms of number of runs or specific data points for the biological agent reduction tests, nor does it explicitly state the precise "data provenance" (e.g., country of origin, retrospective/prospective). These are laboratory efficacy and safety tests, not clinical studies with human subjects or large datasets typical for AI model validation. The tests were performed in a controlled laboratory environment.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable. "Ground truth" in the context of this device's testing refers to measured physical/biological parameters (e.g., log reduction of bacteria/viruses, ozone concentration), not expert interpretation of medical images or other data typically associated with AI/diagnostic devices. The results are based on quantitative laboratory measurements.
4. Adjudication method for the test set
Not applicable. There was no need for adjudication as the "ground truth" was established through direct laboratory measurements, not subjective evaluations or consensus processes.
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
Not applicable. This device is an air cleaner, not an AI-assisted diagnostic or decision support tool for human readers. No MRMC study was performed.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Not applicable beyond the device's inherent standalone function as an air cleaner. There is no AI algorithm in the traditional sense that performs a diagnostic or interpretive function. The device's performance is its inherent physical and chemical action on airborne particles.
7. The type of ground truth used
The ground truth for the biological agent reduction tests was established through direct quantitative laboratory measurements of the reduction in viable MS2 bacteriophage and Staphylococcus epidermidis concentrations. For ozone emissions, the ground truth was direct measurement of ozone concentration in ppm. For electrical compatibility and safety, the ground truth was compliance with specified international and national standards (EN/IEC 60601-1-2, UL 867, CSA C22.2 No.187), verified through standard engineering tests.
8. The sample size for the training set
Not applicable. This device is an air cleaner with a physical mechanism of action, not a machine learning model that requires a "training set."
9. How the ground truth for the training set was established
Not applicable as there is no training set for this device.
§ 880.5045 Medical recirculating air cleaner.
(a)
Identification. A medical recirculating air cleaner is a device used to remove particles from the air for medical purposes. The device may function by electrostatic precipitation or filtration.(b)
Classification. Class II (performance standards).