Search Results

CIMVA Universal is indicated for analyzing patterns of variation of physiological parameters (heart rate and respiratory rate) derived from the output of third party monitoring systems. CIMVA Universal is not designed for vital signs monitoring or self-monitoring of patients.

The CIMVA Universal software is resident in a hospital server or other computer that is periodically connected to a repository of recorded data from third party physiological monitors. The current version of the software has four functions:

1. Allows the user to import a specified amount of recorded monitor data (e.g. up to 96 hours) stored in external repositories.
2. Allows the physician to choose the type of multi-organ variability analysis that he/she desires.
3. Calculates the selected measures of Variability.
4. Provides a physician-configurable report of the calculations
   CIMVA Universal also allows the clinician to measure the degree to which multi-organ variability measures are altered in response to clinical events that are input by the user.
   The calculations performed by CIMVA Universal are algorithms available in the public domain (as described in journal articles, etc.). None of the variability measures are proprietary to TMS. The results of these analyses could help physicians conduct research on the potential clinical utility of one or more of these variability measurements.

The provided document is a 510(k) premarket notification for the "CIMVA Universal" device. It is a software that analyzes patterns of variation of physiological parameters (heart rate and respiratory rate) from third-party monitoring systems.

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

The document does not explicitly state quantitative acceptance criteria or detailed device performance metrics in the format of a table. Instead, it makes a general statement about compliance.

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 provenance of the data (e.g., country of origin, retrospective or prospective). It states that the software "allows the user to import a specified amount of recorded monitor data (e.g. up to 96 hours) stored in external repositories" and that "all analyses are retrospective."

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

The document does not mention the use of experts to establish ground truth for a test set. The device performs calculations based on public domain algorithms and does not involve clinical interpretation or diagnostic capabilities that would require expert-established ground truth in the traditional sense for performance evaluation against human experts.

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

The document does not specify any adjudication method, as it doesn't describe a study comparing the device's output against expert ground truth.

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 multi-reader multi-case (MRMC) comparative effectiveness study is mentioned. The device is not intended to assist human readers in interpretation or diagnosis; rather, it provides variability calculations that "could help physicians conduct research on the potential clinical utility of one or more of these variability measurements."

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

The document implies a standalone evaluation in terms of software validation. It states, "Software validation has demonstrated that the CIMVA Universal is in compliance with the FDA's Guidance..." and "Testing has demonstrated that the software device operates in accordance with its labeling claims." However, this evaluation is not in the context of clinical performance (e.g., diagnostic accuracy vs. ground truth) but rather in terms of software functionality and regulatory compliance. The device itself is stated to be "not a stand-alone analysis device, rather it is intended to be an adjunct to third party physiological monitors."

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

The concept of "ground truth" as typically used in diagnostic performance studies (e.g., expert consensus, pathology) is not applicable or explicitly mentioned in the context of the device's validation. The device calculates "measures of variability" using "algorithms available in the public domain." The ground truth for such an evaluation would likely be the mathematical correctness of these calculations, which would be verified through software testing rather than clinical expert review.

8. The sample size for the training set

The document does not mention a training set or its sample size. The calculations performed by CIMVA Universal are based on "algorithms available in the public domain (as described in journal articles, etc.)" and are not described as being derived from or trained on a specific dataset within the context of this submission.

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

Since no training set is mentioned in the context of machine learning model development, the establishment of ground truth for a training set is not applicable to the information provided.

Ask a specific question about this device