Search Results

The SentrySuite Product line is intended to be used for measurements, data collection and analysis of lung function (PFT) parameters, aiding in the diagnosis of related conditions. All the measurements are performed via a mouthpiece, a mask or nasal adapters. The results of the test can be viewed online with the help of a computer screen and can be printed after the test. The test results can be saved for further referral or report generation purposes. Use of the Option Bronchial Challenge requires the supervision of a physician familiar with emergency medicine.

The products can be utilized for patients from 4 years on and older as long as they can cooperate in the performance - no special limit to patient's sex or height. Measurements will be performed under the direction of a physician in a hospital environment, physician's office or similar settings.

The SentrySuite Product line when operating on the existing hardware for MasterScreen Pneumo, MasterScreen IOS, APS Pro and MasterScreen PFT will be as functional as the existing version of JLAB software for all the available measuring programs and options for these devices.

• The SentrySuite software replaces the JLAB software and got a brand-new graphical surface.
• Measurement can be accomplished under SentrySuite software equivalent as it was possible under the previously powerful JLAB software
• The results of the tests can be viewed on-line on the computer screen during the test and can be saved on the computer hard disk for further referral or report generation purposes.
• SentrySuite provides the functionality currently available on the MasterScreen devices using the JLAB software.
• SentrySuite can be operated on workstations and on servers.

Measurements:

• Spiormetry
• Flow Volume
• Maximal Voluntary Ventilation (MVV)
• Incentive Spirometry
• R-Occlusion
• Impulse oscillometry
• Bronchial test
• FRC Helium Rebreathing
• Real Time Single Breath Diffusion
• Intra Breath Diffusion
• Bodyplethysmography
• Respiratory Drive P0.1
• PI/PE Max (MIP/MEP)
• Single Breath Diffusion CO/He

The acceptance criteria for the SentrySuite Product Line, specifically for the updated SentrySuite 2.7 software, are based on the statistical correlation of its performance with the predicate JLAB software. The study's objective was to demonstrate substantial equivalence by showing that the new software generates results that are highly correlated with the predicate software.

Here's a breakdown of the requested information:

Acceptance Criteria and Reported Device Performance:

Study that Proves the Device Meets Acceptance Criteria:

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

   • Sample Size: The document states that "Human subjects were tested," but does not explicitly provide the number of subjects used in the test set.
   • Data Provenance: The study was likely conducted by CareFusion Germany 234 GmbH, suggesting data of European origin (Germany). The study involved "human subjects" tested on the devices. It appears to be a prospective study where new data was collected for the purpose of comparing the two software versions on the same subjects.

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

   • This type of study does not involve "ground truth" established by experts in the sense of a diagnostic interpretation task. Instead, the study compares the measurements generated by two software versions (new SentrySuite 2.7 vs. predicate JLAB) on physical measurements from human subjects. The gold standard in this context is the predicate device's established performance, and the "ground truth" for each measurement is effectively the value reported by the predicate JLAB software. There isn't an expert review process for determining the "truth" of a spirometry reading in this comparison.

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

   • Not applicable. This was a direct comparison of numerical outputs from two software versions, not an interpretation task requiring adjudication.

4. 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 comparative effectiveness study was done. This device is a software update for pulmonary function testing equipment, which measures physiological parameters. It is not an AI-assisted diagnostic tool that would typically involve human readers interpreting images or data with and without AI.

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

   • Yes, this study is effectively a standalone performance evaluation of the SentrySuite 2.7 software compared to the predicate JLAB software. While both systems are used by humans to perform measurements, the comparison itself focuses on the outputs generated by the software algorithms from the same physical inputs (human subject physiological responses). The study assesses the statistical correlation between these direct algorithmic outputs.

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

   • The "ground truth" in this context is the performance of the legally marketed predicate device running the JLAB software. The new SentrySuite 2.7 software is being evaluated for substantial equivalence to the predicate, meaning its outputs should be statistically similar to those of the predicate when given the same inputs.

7. The sample size for the training set:

   • The document describes a comparison study, not the development of a machine learning model, so there is no "training set" in the traditional sense for an AI/ML algorithm. The software is stated to "supersede" previous versions and "replaces" existing software, implying a re-implementation or enhancement of established algorithms, rather than training a de novo AI model.

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

   • Not applicable, as there is no training set for an AI/ML algorithm described in this submission. The ground truth for the comparison study is the predicate device's performance.

Ask a specific question about this device