Search Results

The Capnostream20 combined capnograph/pulse oximeter monitor is intended to provide professionally trained health care providers the continuous, non invasive measurement and monitoring of carbon dioxide concentration of the expired and inspired breath and respiration rate, and for the continuous non-invasive monitoring of functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate. It is intended for use with neonatal, pediatric and adult patients in hospital type facilities, intra hospital transport and home environments.

The Capnostream20 bedside monitor is a two parameter monitor consisting of a miniMediCO2 capnography module and a pulse oximetry module implemented in a host device. The host device displays parameters received from the respective modules and generates alarms when preset alarm thresholds are crossed. The device is classified as CCK Class II according to 21 CFR § 868.1400 - Carbon Dioxide Analyzer. This device has two modules that are classified as follows: 21 CFR 868.1400, Carbon Dioxide Analyzer (Classification CCK) . 21 CFR870.2700 Pulse Oximeter (Classification DQA) . Each module is controlled by dedicated software that is an integral part of the respective module. Each module provides parameters to the host software (the Capnostream20 device software) which then controls the display of the received parameter values and creates alarms when the values cross the preset thresholds. The miniMediCO2 capnography module software presented in this submission includes an adaptive averaging algorithm defined as the A Algorithm for calculating the respiration rate from the CO2 waveform introduced in software version 2.31 of the miniMediCO2 capnography module software. The calculated respiration rate parameter is then provided to the host (the Capnostream20 device software). The host makes no modification to the values received from the module. The host triggers an alarm when the respiration rate high or respiration rate low thresholds have been crossed. The algorithm employed in the respiration rate calculation reduces false positive alarms by filtering out noise and instantaneous fluctuations without missing true alarms that may indicate a clinically significant change to respiration rate. By employing the adaptive averaging algorithm, the respiration rate accurately reflects the patient's condition and significantly reduces the generation of nuisance alarms by the host.

The provided text describes a 510(k) summary for the Capnostream20 with A2 (adaptive averaging) software for its miniMediCO2 module. This submission is for an updated software version (2.31) that introduces an adaptive averaging algorithm for calculating respiration rate, aiming to reduce false positive alarms while maintaining accuracy.

Here's an analysis of the acceptance criteria and study information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of acceptance criteria for the A2 software's performance in terms of specific sensitivity, specificity, accuracy, or alarm reduction metrics. Instead, it focuses on demonstrating substantial equivalence to a predicate device.

The "reported device performance" related to the new software is described functionally: "The algorithm employed in the respiration rate calculation reduces false positive alarms by filtering out noise and instantaneous fluctuations without missing true alarms that may indicate a clinically significant change to respiration rate. By employing the adaptive averaging algorithm, the respiration rate accurately reflects the patient's condition and significantly reduces the generation of nuisance alarms by the host."

While the device meets the safety and performance standards of the predicate device, it doesn't quantify the improvement of the A2 software against specific targets. The performance metrics are implicitly "reduces false positive alarms" and "accurately reflects the patient's condition."

2. Sample Size Used for the Test Set and Data Provenance

The document states: "Test data are provided to validate the performance of the software and its substantial equivalence to the predicate device." However, specific details regarding the sample size used for the test set and the data provenance (e.g., country of origin, retrospective or prospective) are NOT provided in this summary.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of those Experts

This information is NOT provided in the document. The text does not describe how ground truth was established for evaluating the performance of the new algorithm.

4. Adjudication Method for the Test Set

This information is NOT provided in the document.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done an 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 is NOT mentioned in the document. The new algorithm is for an automated respiration rate calculation, not an AI-assisted human reading task.

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

Yes, the study described is a standalone (algorithm only) performance evaluation. The focus is on the "adaptive averaging algorithm" (A2 software) for calculating respiration rate, which operates autonomously within the miniMediCO2 module. The output (respiration rate) is then provided to the host device. The document states: "The host makes no modification to the values received from the module." This confirms it's an algorithm-only evaluation.

7. The Type of Ground Truth Used

The type of ground truth used is NOT explicitly stated. Given that the algorithm calculates respiration rate from the CO2 waveform, it is most probable that the ground truth would involve:

• Manual, expert review and calculation of respiration rate from raw CO2 waveforms or
• Comparison to another highly accurate, validated respiration rate measurement method.

8. The Sample Size for the Training Set

The document does NOT provide any information about a training set or its sample size. This is a software update described as an "adaptive averaging algorithm," but details on its development or any training data are not included in this 510(k) summary.

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

As no training set is mentioned, information on how its ground truth was established is NOT provided.

Ask a specific question about this device