Search Results

This device will produce visual and audible alarms if any of these parameters vary beyond preset limits and produce timed or alarm recordings. This device will connect to R50 recorders, either directly or via the INFINITY network.

When a GammaXL is connected to a SCIO module sampled breathing gases from adults and pediatrics can be displayed. The gas module continuously measures the content of CO2, N20, O2 and one of the anesthetic agents, Halothane, Isoflurane, Enflurane, Sevoflurane and Desflurane in any mixture and communicates real time and derived gas information to the GammaXL.

The device is intended to be used in an environment where patient care is provided by Healthcare Professionals, i.e. physicians, nurses, and technicians, trained on the use of the device, who will determine when use of the device is indicated, based upon their professional assessment of the patient's medical condition.

The devices are intended for use in the Adult, Pediatric and Neonatal populations, with the exception of Arrhythmia and ST Segment Analysis which are not intended for the neonatal population.

not available with Infinity Vista

Device Description

Software version VF5 is the latest release of the INFINITY Gamma/GammaXL and the Infinity Vista monitor (a variant of the Infinity GammaXL with fewer options). It supports a new serial connection to the Scio gas module, as well as other minor software modifications. Testing in accordance with internal design control procedures has verified that the INFINITY Gamma/GammaXL and Vista with VF5 modifications are as safe and effective as submitted in 510(k) K040188, K041087 and K033600.

AI/ML Overview

The provided text describes a Special 510(k) for device modifications to the INFINITY Gamma/GammaXL and Vista with VF5 software. This submission focuses on verification and validation testing to demonstrate that the software modifications do not alter the fundamental technology and the device remains as safe and effective as previous versions.

Here's a breakdown based on your requested information:

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

The submission does not provide specific acceptance criteria or reported device performance metrics in a quantitative manner. It states:

Acceptance Criteria (Implied): The modifications implemented with software version VF5 are as safe and effective as previous versions and have not altered the fundamental technology of the device(s). This is a qualitative statement of equivalence.
Reported Device Performance: "Verification and validation testing performed indicates that the modifications implemented with software version VF5 are as safe and effective as previous versions and have not altered the fundamental technology of the device(s)." This is also a qualitative statement, indicating successful completion of internal testing without providing granular results or specific performance metrics.

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

The document does not specify the sample size used for the test set or the data provenance. It only mentions "Verification and validation testing performed."

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)

This information is not provided in the document. The text does not describe an expert-driven ground truth establishment process for the testing. The testing appears to be internal verification and validation against design specifications and previous versions of the device, rather than a clinical study with expert ground truth.

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

This information is not provided. There is no mention of an adjudication process for the testing performed.

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

A multi-reader multi-case (MRMC) comparative effectiveness study was not done. The device in question is a physiological patient monitor with software modifications, not an AI-assisted diagnostic tool that would typically involve human readers.

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

The document does not explicitly describe a "standalone" performance study in the context of an algorithm's performance without human intervention. The testing performed was "Verification and validation testing" to ensure the modifications were safe and effective, implying functional and performance testing of the device itself.

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

The document does not specify the type of ground truth used. Given the nature of the device (physiological monitor) and the reported testing (verification and validation of software modifications), the "ground truth" would likely be based on:

Engineering specifications and requirements: Ensuring the device functions as designed and meets its technical parameters.
Comparison to previous versions: Confirming that the modified software performs equivalently to the predicate devices.
Internal reference standards: Using calibrated equipment or established reference values for physiological parameters.

8. The sample size for the training set

This is not applicable and therefore not provided. The submission describes modifications to existing software for a physiological monitor, not the development of a new AI/machine learning algorithm that requires a training set.

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

This is not applicable and therefore not provided, as there is no training set for an AI/machine learning algorithm described in this submission.

Ask a Question

Ask a specific question about this device

Page 1 of 1