(168 days)
The SERVO-U ventilator system is:
- intended for respiratory support, monitoring and treatment of neonatal, pediatric and adult patients
- to be used only by healthcare providers
- to be used only in professional healthcare facilities and for transport within these facilities
For NAVA and Edi monitoring, it is in addition intended:
- to provide monitoring of the patient's breathing drive
- to improve synchrony between the ventilator system and patient when the electrical signal from the brain to the diaphragm is active
- for use on all patients with no contraindication for insertion/exchange of a nasogastric tube
The SERVO-n ventilator system is:
- intended for respiratory support, monitoring and treatment of neonatal and pediatric patients
- to be used only by healthcare providers
- to be used only in professional healthcare facilities and for transport within these facilities
For NAVA and Edi monitoring, it is in addition intended:
- to provide monitoring of the patient's breathing drive
- to improve synchrony between the ventilator system and patient when the electrical signal from the brain to the diaphragm is active
- for use on all patients with no contraindication for insertion/exchange of a nasogastric tube
The SERVO-U/n Ventilator System is available in two models, SERVO-U and SERVOn. The SERVO-U/n Ventilator System consists of a Patient Unit where gases are mixed and administered, and a User Interface where the settings are made and ventilation is monitored.
The SERVO-U/n Ventilator System is built on the same architecture as the cleared predicate device SERVO-i Ventilator System (K123149). The ventilation modes in the SERVO-U/n Ventilator System are identical to the ventilation modes in the cleared predicate device, even though the standard configurations of available modes and optional modes differ between the devices i.e. SERVO-U, SERVO-n and the cleared predicate device SERVO-i Ventilator System (K123149).
The ventilator delivers controlled or supported breaths to the patient, with constant flow. constant pressure or pressure proportional to the Edi signal (the electrical activity of the diaphragm) of the patient, using a set oxygen concentration.
NAVA (Neurally Adiusted Ventilatory Assist) is a supported mode for SERVO-U/n that uses the Edi signal as an addition to the flow/pressure trigger to synchronize the patient efforts with the onset and cycle off of supported breaths. NAVA is available in invasive and non-invasive modes. These ventilation modes are identical in the SERVO-U/n Ventilation system and the cleared predicate device SERVO-i Ventilator System (K123149). Furthermore, the included hardware parts Edi module and Edi catheters are also identical to the ones used for the cleared predicate device SERVO-i Ventilator System (K123149).
SERVO-U/n contains a dedicated controller circuit for the Aerogen Pro and Solo nebulizers (included as standard). In the cleared predicate device SERVO-i Ventilator System (K123149) the corresponding nebulizer function is available as an optional module.
Accessories for CO2 monitoring and flow and pressure measurements at the Y piece (Y sensor) are integrated as options. The CO2 monitoring option is updated with Capnostat 5 and the Y sensor is based on a new technology and measuring function compared to the corresponding options for the cleared predicate device SERVO-i Ventilator System (K123149).
The SERVO-U/n Ventilator System will produce visual and audible alarms if any parameter varies beyond preset or default limits and produce alarm recordings. The alarm handling is very similar to the one used in the cleared predicate device SERVO-i Ventilator System (K123149), except the possibility to set alarm off for leakage related alarms in Neonatal Patient category when leakage compensation is activated. Additionally, an Inspiratory tidal volume (VT) too high alarm has been added in the neonatal patient category and three alarms have been removed in the Non-invasive modes.
The system contains provisions for battery modules to supply the system in the case of mains power failure or during in-hospital transport. The batteries are identical to the one used for the cleared predicate device SERVO-i Ventilator System (K123149).
System parts:
The SERVO-U/n Ventilator System consists of the following parts:
- User interface, where all user interactions are performed.
- Patient unit with all connections to the patient, to power and gases.
- Mobile cart, on wheels, for using the ventilator on either the left or the right side of the patient.
This document describes the premarket notification (510(k)) for the SERVO-U and SERVO-n Ventilator System. It largely focuses on demonstrating substantial equivalence to a predicate device (SERVO-i Ventilator System, K123149) rather than presenting a study to prove acceptance criteria for novel device performance. Therefore, the information typically requested regarding acceptance criteria and a proving study for a new AI/ML device is not fully available in this document.
However, based on the provided text, here's what can be extracted and inferred:
1. A table of acceptance criteria and the reported device performance:
The document doesn't present a formal table of acceptance criteria with reported performance in the way one might expect for a new device claiming specific performance metrics. Instead, "acceptance criteria" are implied by the demonstration of substantial equivalence to the predicate device and compliance with relevant standards. The "reported device performance" is mainly a statement that the device performs "within its specifications and within the limits of the applied product performance standards."
| Acceptance Criteria (Implied by Substantial Equivalence and Standards) | Reported Device Performance (as stated in document) |
|---|---|
| Intended Use Equivalence: Similar therapeutic and monitoring use as predicate device, with minor differences not affecting safety/effectiveness. | The SERVO-U/n Ventilator System's intended use/indication for use is "very similar" to the predicate, with minor rephrasing and differences (SERVO-n for neonatal/pediatric only, no MR/Heliox options for SERVO-U/n) that are believed "will not affect the therapeutic or monitoring use." |
| Technology Equivalence: Built on the same architecture, re-uses software algorithms for ventilation and alarms, identical ventilation modes. Updates made (GUI, software platform, microprocessors, Y sensor, CO2 analyzer, leakage compensation, alarm changes) are described as improvements or adaptations. | "SERVO-U/n Ventilator System is built on the same architecture as the cleared predicate device SERVO-i Ventilator System (K123149). Software algorithms for ventilation and alarms are re-used... ventilation modes... are identical." |
| Performance within Specifications: Device performs as intended and meets design input requirements. | Design verification and validation have demonstrated that the SERVO-U/n Ventilator System "performs within its specifications." |
| Compliance with Product Standards: Adherence to recognized national and international standards. | "performs... within the limits of the applied product performance standards." Specific standards listed include ANSI/AAMI ES 60601-1, IEC 60601-1-2, IEC 60601-1-8, ISO 80601-2-12, ISO 80601-2-55, ISO 5356-1, CGA V-5. |
| Biocompatibility: New materials in gas pathway are biocompatible. | Biocompatibility evaluation performed in accordance with AAMI/ANSI/ISO 10993-1:2009 for components with new materials contacting the gas pathway. Cytotoxicity and sensitization testing performed. |
| Usability/Risk Management: Identification and mitigation of potential use errors; device meets user needs. | Usability activities performed, including formative tests and summative usability validation. Potential use errors identified and estimated during usability risk analysis, informing human factors testing. |
| Safety and Effectiveness Equivalence: As safe and effective as the predicate device. | "MAQUET has concluded that the performance data for the SERVO-U/n Ventilator System show that it is as safe and as effective as the already cleared predicate device SERVO-i Ventilator System (K123149)." |
2. Sample size used for the test set and the data provenance:
- Sample size for test set: Not explicitly stated as a single "test set" in the context of typical AI/ML evaluation. The design verification and validation activities involved various types of testing (code review, unit tests, integration tests, system tests, Free User Testing, regression testing, biocompatibility testing, usability testing, and an animal study). The number of test cases or "samples" for each of these activities is not quantified.
- Data provenance: Not directly applicable in the sense of a clinical dataset. The testing conducted was primarily non-clinical (engineering verification, lab testing, animal study).
- Animal study: Done to evaluate the performance of the Y sensor algorithm at different degrees of humidity and leakage and its effect on tidal volume measurements. Provenance (e.g., country) is not specified.
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. The ground truth for the verification and validation activities would largely be established by engineering specifications, regulatory standards, and expert review within the company. For "Free User Testing" and "usability validation," the "experts" would be representative users (healthcare providers), but their number and specific qualifications are not detailed.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
Not applicable in the context of this 510(k) submission. Adjudication methods are typically relevant for human review of clinical data, especially in studies involving subjective assessments of images or patient outcomes. The testing described here is primarily technical and performance-based.
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 MRMC comparative effectiveness study was done. This device is a ventilator, not an AI-powered diagnostic or assistive tool for human readers.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
The device itself is a standalone medical device (a ventilator). The "performance" described is of the device's various functions and components, rather than the performance of an isolated algorithm. The document emphasizes the integration of hardware and software.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
The "ground truth" for the various verification and validation activities would primarily consist of:
- Engineering specifications and design input requirements: For system tests, unit tests, integration tests, and code reviews.
- Applicable product standards: For compliance testing.
- Predefined performance ranges and accuracy limits: For sensor evaluations (e.g., Y sensor in animal study, CO2 analyzer).
- Simulated physiological conditions: Used in lab testing.
- User expectations and safety requirements: For usability and risk analysis.
8. The sample size for the training set:
Not applicable. This document describes a medical device (ventilator), not an AI/ML system that undergoes "training" in the conventional sense.
9. How the ground truth for the training set was established:
Not applicable, as no training set for an AI/ML algorithm is described.
§ 868.5895 Continuous ventilator.
(a)
Identification. A continuous ventilator (respirator) is a device intended to mechanically control or assist patient breathing by delivering a predetermined percentage of oxygen in the breathing gas. Adult, pediatric, and neonatal ventilators are included in this generic type of device.(b)
Classification. Class II (performance standards).