Search Results

The Viewing Client Mobile is a software application that is intended to be used by qualified medical professionals for the review of medical images derived from multiple modalities. Clinical reports can also be viewed using this device.

The Viewing Client Mobile application can be used to perform image manipulation (for example, window width and level, zoom, pan, rotation) and measurement. It can display both lossless and lossy compressed images. For lossy images, the user must determine if the level of loss is acceptable for their purposes.

The Viewing Client Mobile application provides wireless and portable access to medical images from only the following modalities: MRI, CT, X-ray and Ultrasound. It is not intended to replace a full workstation and should be used only when there is no access to one.

The Viewing Client Mobile application must not be used for the primary interpretation of mammographic images.

AXON Medical Technology Corp.'s Viewing Client Mobile is a viewer that facilitates the secure viewing of 2D, DICOM 3.0-compliant soft-copy imaging studies both within and without the Enterprise context. The product operates through an API.

Viewing Client Mobile is used under mobile viewing conditions within the device's intended use. Viewing Client Mobile app runs on iOS platforms.

Core measurement and image manipulation tools provided by the Viewing Client Mobile include zoom, pan, invert, W/L, Pixel Value/ Line/ Angle, ROI and CINE. The Viewing Client Mobile also supports multiseries and study display.

The Viewing Client Mobile app operates on the iPad, a portable, "off-the-sheh" hardware device, used to wirelessly access medical images under mobile conditions, and is therefore more sensitive to factors not typical for reading room workstations (e.g. display condition, variable lighting, viewing angle, etc.). The user is therefore instructed to properly follow the operating instructions provided with the hardware device, utilize the Viewing Client Mobile's risk mitigation features and heed precautions related to safe device use.

The provided text describes the AXON Medical Technologies Corp.'s "Viewing Client Mobile" device and its performance testing.

Here's an analysis of the acceptance criteria and study details based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't provide a specific table with quantitative acceptance criteria for diagnostice performance and measured values against those criteria. Instead, it states that "in each case acceptance criteria was met" for bench testing and that clinical testing resulted in positive qualitative feedback.

Bench Testing:

Clinical Testing:

2. Sample Size and Data Provenance

• Bench Testing: The sample size for bench testing is not explicitly stated as a number of devices or platforms, but it was performed "on all supported off-the-shelf mobile platforms." The data provenance is internal to AXON Medical Technologies Corp.
• Clinical Testing: The document does not specify the exact sample size (number of patient cases or images) used for the clinical image quality demonstration study. The data provenance (country of origin, retrospective/prospective) is not mentioned.

3. Number of Experts and Qualifications for Ground Truth

• Bench Testing: A single expert "in luminance and illuminance testing" validated the test plan. Their specific qualifications (e.g., years of experience, certifications) are not detailed beyond being an "expert."
• Clinical Testing: The ground truth was established by "certified Radiologists." The number of radiologists is referred to as "All radiologists," implying at least more than one, but a specific count is not provided. Their qualifications are stated as "certified Radiologists," but no further details (e.g., years of experience, subspecialty) are given.

4. Adjudication Method

The document does not describe a formal adjudication method (e.g., 2+1, 3+1) for either the bench testing or the clinical testing. For clinical testing, it states "All radiologists indicated" a consensus, but the process to reach that consensus (e.g., independent review followed by discussion, or a single collective assessment) is not specified.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No, a MRMC comparative effectiveness study was not explicitly described. The clinical study was an "Image Quality Demonstration study" where radiologists performed a "side-by-side comparison of the predicate and Viewing Client Mobile to evaluate and compare the overall image quality." This appears to be a qualitative comparison rather than a formal MRMC study to quantify performance improvement with/without AI assistance.

6. Standalone Performance

Yes, a standalone performance assessment was conducted. The "Viewing Client Mobile" is the device being assessed in isolation (i.e., its performance in displaying images), with radiologists acting as the "human-in-the-loop" for qualitative assessment. The study was focused on the device's ability to display images acceptably for diagnostic reads by human radiologists, not on an algorithm's diagnostic output without human review.

7. Type of Ground Truth Used for Test Set

• Bench Testing: The ground truth was established by conformance to "test guidelines provided in AAPM Assessment of Display Performance for Medical Imaging Devices (2005)" and internal specifications validated by an expert.
• Clinical Testing: The ground truth for the clinical study was expert consensus based on the qualitative assessment of image quality by "certified Radiologists" compared to a predicate device. It was not pathology, or outcomes data.

8. Sample Size for the Training Set

The document does not mention a training set. This device is a medical image viewer and processing software, not an AI/CAD algorithm that typically requires a large training dataset for model development.

9. How the Ground Truth for the Training Set Was Established

Not applicable, as no training set is mentioned for an AI/CAD algorithm. The device is a viewer; its functionality is based on display and manipulation of existing DICOM data, not on learning from a dataset to make diagnostic predictions.

Ask a specific question about this device

To remove unwanted anesthetic gases from the patient breathing circuit

This device uses two anesthetic vapor adsorbent canisters connected to an anesthesia delivery system to prevent unwanted anesthetic vapors emanating from within an anesthesia gas machine from reaching a patient.

Here's a breakdown of the acceptance criteria and study information for the Vapor-Clear device, based on the provided text:

Acceptance Criteria and Device Performance

Study Details

The provided document describes non-clinical bench testing to demonstrate the substantial equivalence of the Vapor-Clear device to its predicate.

1. Sample size used for the test set and the data provenance:

   • Test Set Sample Size: Not explicitly stated as a "sample size" in terms of patient data. The testing involved multiple units of the Vapor-Clear device and utilized two modern anesthesia gas machines (Draeger Apollo and Ohmeda Aestiva) for the residual vapor scavenging test. "A single Vapor-Clear canister" was used for the removal capacity test. "Product containing activated charcoal that has been aged for 71 months" was tested for product life testing.
   • Data Provenance: The data is from non-clinical bench testing. The country of origin is not specified but is implied to be related to the manufacturer (Axon Medical Inc., Park City, Utah, USA) and the FDA submission process. This is retrospective in the sense that the studies were completed before the 510(k) submission.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • Number of Experts: Not applicable. The ground truth for this non-clinical testing was established through direct measurement using analytical instruments (e.g., anesthetic gas analyzer capable of detection 99% removal) was determined by comparing measured input and output concentrations.

3. The sample size for the training set:

   • Training Set Sample Size: Not applicable. This device is a physical medical device and does not involve AI or machine learning models that require a training set.

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

   • Ground Truth for Training Set: Not applicable. As above, no training set was used.

Ask a specific question about this device

The AneFin 100 is intended to speed emergence from the effects of volatile inhaled anesthetics by removing unwanted anesthetic gas and generating through partial rebreathing. It is intended for use with only Isoflurane, Sevoflurane and Desflurane.

The AneFin combines an anesthetic gas absorber to remove anesthetic gas from the breathing circuit and an anesthetic gas CO₂-sensor which allows increased patient ventilation while preventing hypocapnia during emergence from volatile inhaled anesthesia.

The provided document, K033028 for the Axon Medical AneFin 100, is a 510(k) premarket notification. This type of submission by the FDA focuses on demonstrating substantial equivalence to existing legally marketed devices, rather than establishing new safety and effectiveness through clinical trials with defined acceptance criteria and human performance studies common for novel AI/ML medical devices.

Therefore, the requested information regarding acceptance criteria, device performance against those criteria, study specifics (sample size, ground truth, expert involvement, MRMC studies, standalone performance), and training set details is not present in this document.

The document mainly demonstrates equivalence through a comparison table of attributes between the AneFin 100 and predicate devices, as well as descriptive information about the device and its intended use. Here's a breakdown of what is available:

1. A table of acceptance criteria and the reported device performance

• Not applicable / Not provided. This document does not establish specific performance acceptance criteria for the AneFin 100 against which its performance is then measured. The evaluation is based on demonstrating substantial equivalence to predicate devices, which implies meeting similar safety and performance profiles. The comparison table (labeled "Comparison to Predicate Devices to demonstrate substantial equivalence") highlights physical and functional attributes but not quantitative performance metrics against acceptance criteria.

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

• Not provided. No test set or associated sample sizes are mentioned. The substantial equivalence pathway typically relies on bench testing, engineering analysis, and literature review of predicate devices, rather than new clinical testing on a specific "test set" for performance evaluation in the same way an AI device would be assessed.

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)

• Not provided. Since no specific test set is described, there's no mention of experts establishing ground truth. The "ground truth" for substantial equivalence is primarily defined by the established safety and effectiveness of the predicate devices.

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

• Not provided. No adjudication method is described as no test set requiring such expert review is mentioned.

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 / Not provided. The AneFin 100 is a physical medical device (anesthetic gas absorber/rebreathing device), not an Artificial Intelligence (AI) or Machine Learning (ML) driven product. Therefore, an MRMC study or assessment of human reader improvement with AI assistance is entirely irrelevant to this device and its regulatory submission.

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

• Not applicable / Not provided. As the AneFin 100 is a physical device and not an algorithm, the concept of "standalone performance" in the context of AI without human interaction does not apply.

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

• Not applicable / Not provided. As noted, the "ground truth" in this context is the established safety and effectiveness of predicate devices, which would have been determined through their own regulatory pathways (e.g., historical use, clinical studies at their time of clearance). There's no new "ground truth" derivation described for this specific submission.

8. The sample size for the training set

• Not applicable / Not provided. As this is not an AI/ML device, there is no "training set."

9. How the ground truth for the training set was established

• Not applicable / Not provided. As this is not an AI/ML device, there is no "training set" or ground truth for it.

Summary of the K033028 Submission:

The K033028 submission for the Axon Medical AneFin 100 is a 510(k) premarket notification to demonstrate substantial equivalence to legally marketed predicate devices. The device is an anesthetic gas absorber with rebreathing capabilities intended to speed emergence from volatile inhaled anesthetics.

The method used to "prove" the device meets the regulatory requirements for clearance is through comparison to predicate devices already cleared by the FDA. The application argues that the AneFin 100 shares the same intended use, technological characteristics, and safety profile as the identified predicates, or that any differences do not raise new questions of safety and effectiveness.

• Predicate Devices:
  • RFS Vacuum gauge scavenging circuit, K033503
  • "Protect-OR" filter, Charcoal based scavenging device, Pre-Amendment (Foregger)
  • Model A100 CO2 absorber with bypass valve (Penlon), 510(k) exempt
  • Non invasive cardiac output monitor, NICO (Novametrix), K030886 - This appears to be used as a predicate just for the mechanism of increasing CO2 via dead space tubing and rebreathing volume.

The document explicitly states: "There are no significant differences between the intended device and the identified predicates." This statement is the core of the substantial equivalence argument.

Ask a specific question about this device