Search Results

The RAPHAEL Color^sV ventilator is a continuous ventilator designed for ventilation of adult and pediatric patients weighing between 5 and 200 kg. The RAPHAEL ColorASV ventilator is intended for use by properly trained personnel under direct supervision of a licensed physician. The RAPHAEL Color450 is intended for use in a hospital or hospital-type facility, including use at a patient bedside or for intra-facility transport, provided compressed gas is supplied.

The RAPHAEL Color's is a software modified version of the legally marketed device RAPHAEL Color (K052863). The RAPHAEL Color^SV is a full-functioned intensive care ventilator. It can ventilate adult and pediatric patients weighing between 5 and 200 kg. The RAPHAEL Color488 offers a full spectrum of modalities, from the conventional to the new included Adaptive Support Ventilation, ASV. ASV is designed to maintain at least the minute ventilation set by the clinician. ASV does this without exceeding a preset plateau pressure. ASV provides full ventilation in apnea or low-drive conditions, and then automatically returns control to the patient as spontaneous ventilation begins. ASV works automatically by continuous repetition of 3 steps: 1. Assess the patient breath-by-breath. 2. Calculate an optimal breath pattern based on the minimal work of breathing method by Otis (J Appl Physiol 1950: 592-607). 3. Approach the target by automatically adjusting mandatory rate and inspiratory pressure.

The Hamilton Medical RAPHAEL ColorASV is a software-modified version of the RAPHAEL Color (K052863) continuous ventilator, with the addition of the Adaptive Support Ventilation (ASV) mode. The ASV mode itself is comparable to the ASV mode found in the HAMILTON GALILEO GoldASV (K061090) ventilator.

Acceptance Criteria and Reported Device Performance:

The provided 510(k) summary does not explicitly state numerical acceptance criteria in a typical "Pass/Fail" or quantitative threshold format. Instead, the acceptance is based on demonstrating substantial equivalence to predicate devices through performance testing.

Study Details:

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

   • The submission describes "performance/qualification testing" on "modular, integration and system level." It also mentions evaluation in accordance with "ASTM Standard F1100-90."
   • However, specific sample sizes (e.g., number of test conditions, simulated patient scenarios, or test cycles) are not explicitly stated in the provided text.
   • The data provenance is internal testing performed by Hamilton Medical AG ("Switzerland" is the country of origin for the 510(k) owner). The testing is non-clinical/bench testing.

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

   • This was a non-clinical, bench testing study. Therefore, there were no human experts establishing ground truth in the context of clinical outcomes or imaging interpretation. The "ground truth" was based on meeting engineering specifications, adherence to standards (ASTM F1100-90), and comparison against the known performance of predicate devices.

3. Adjudication method for the test set:

   • Not applicable as this was non-clinical performance testing. The "adjudication" would have been through verification against specified performance parameters and standard compliance by the manufacturer's testing personnel.

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, an MRMC comparative effectiveness study was not performed as this device is a continuous ventilator, not an AI-assisted diagnostic tool for human readers.

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

   • The testing described is essentially "standalone algorithm/device performance" in a simulated, non-clinical environment. The ASV algorithm's performance and the overall ventilator's function were tested without direct human-in-the-loop performance in a clinical setting for this particular submission. The "algorithm" (ASV mode) was tested as an integral part of the device's functionality.

6. The type of ground truth used:

   • The "ground truth" for this ventilator was based on engineering specifications, compliance with relevant industry standards (e.g., ASTM F1100-90), and demonstrated equivalence to the performance of legally marketed predicate devices. It was not based on expert consensus, pathology, or patient outcomes data in this submission, as it focused on device safety and functional performance.

7. The sample size for the training set:

   • The RAPHAEL ColorASV is a ventilator with an embedded control algorithm (ASV). The ASV mode itself is based on a method described by Otis (J Appl Physiol 1950: 592-607). This is not a machine learning or AI algorithm that undergoes a "training set" in the modern sense. Therefore, there is no stated sample size for a training set. The algorithm's parameters are likely based on physiological models and engineering design rather than data-driven machine learning.

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

   • As established above, this is not a machine learning algorithm with a training set. The ASV algorithm's underlying "ground truth" or design principles are based on established physiological models of respiratory mechanics and work of breathing, as evidenced by the reference to Otis's method. The development of such control algorithms involves engineering design, mathematical modeling, and physiological understanding, rather than empirical training data with associated ground truth labels.

Ask a specific question about this device