Search Results

The SERVO i Ventilator System is intended for treatment and monitoring of patients in the range of neonates, infants, and adults with respiratory failure or respiratory insufficiency. SERVO-i is a ventilator system to be used only by healtheare providers in hospitals or healthcare facilities and for in-hospital transport.

The added indications for use of the NAVA option is when the electrical signal from the diaphragm is intact; NA VA will improve synchrony between the ventilator and patients with no contraindication for insertion/exchange of a Naso-Gastric tube.

The SERVO-i Ventilator is classified as MR Conditional for 1.T. 1.5T and 3T MR scanners. This means that it is safe to use in the MR environment if the MR Environment Declaration for SERVO-i are met.

The SERVO-i Ventilator System with Heliox option is indicated for use with the delivery of Air, Oxygen, or Heliox (a mixture of Helium and Oxygen).

The SERVO-s Ventilator System is intended for treatment and monitoring of patients in the range of neonates, infants, and adults with respiratory failure or respiratory insufficiency. SERVO-s is a ventilator system to be used only by healthcare providers in hospitals or healthcare facilities and for in-hospital transport.

The SERVO-i Ventilator System (here after called SERVO-i) is intended to provide continuous ventilation for neonate to adult patients in the weight range 0.5-250 kg and with tidal volumes from 2 mL to 4000 mL. SERVO-i 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 ventilator delivers controlled or supported breaths to the patient, with either constant flow or constant pressure, using a set oxygen concentration. SERVO-i will produce visual and audible alarms if vital parameters vary beyond pre-set, or default, limits. The system contains provisions for at least two battery modules to supply the system in the case of mains power failure or during in-hospital transport. The ventilator functionality is controlled by software. The SERVO-i Ventilator System is available in three software versions. Infant. Adult and Universal.

The NAVA (Neurally Adjusted Ventilatory Assist) option is a supported mode for SERVO-i that uses the Edi signal (the electrical activity of the diaphragm) as an addition to the flow/pressure trigger to synchronize the patient efforts with the onset and cycle off. The NAVA option is available in invasive and non-invasive mode.

SERVO-i is MR conditional. The SERVO-i ventilator with MR option have been tested with 1.0, 1.5, 3.0 T scanners without impairing its performance or the image quality of the scanner. Each scanner and its environment form an individual device. The MR Environment Declaration describes how a SERVO-i with MR option can be qualified to be used with an MR scanner forming a safe Medical System. All vital parts of the ventilator have been tested for performance in excessive magnetic fields.

The SERVO-i with Heliox option requires a different mechanical adaptor on the air supply inlet to allow a mixture of Helium and Oxygen to be connected. Furthermore is the software updated to allow safe delivery and monitoring of the Heliox gas mixture.

Accessories for CO2-monitoring, nebulization and flow monitoring at the Y -piece (Y-sensor) are integrated as options in the SERVO-i and the drivers are controlled by the software in the ventilator.

This 510(k) submission for the SERVO-i include changes to receive a new baseline based on compatibility to the third edition standard package of AAMVANSI 60601-1 :2005 and its collateral and particular standards for intensive care ventilators. The submission does also include modifications of the software and hardware to update existing functionalities since the last submission (K073149).

The SERVO-s ventilator system (here after called SERVO-s) is based on the SERVO-i ventilator family platform. SERVO-s ventilation system is a downscaled version based on the SERVO-i ventilator system notified in K041223.

The SERVO-s Ventilator System is intended to provide continuous ventilation for neonate to adult patients in the weight range 2-250 kg and with tidal volumes from 10 mL to 2000 mL. The SERVO-s 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 ventilator delivers controlled or supported breaths to the patient, with either constant flow or constant pressure, using a set oxygen concentration. SERVO-s Ventilator System will produce visual and audible alarms if vital parameters vary beyond preset, or default, limits. The system contains two internal batteries to supply the system with power in the case of mains power failure or during inhospital transport. The ventilator functionality is controlled by software. The SERVO-s Ventilator System is available in two software versions, Infant and Adult.

This 510(k) submission for the SERVO-s include changes to receive a new baseline based on compatibility to the third edition standard package of IEC 60601-1 :2005 and its collateral and particular standards for intensive care ventilators. The submission does also include addition of the Infant option, patient weight range 2-10 kg, with tidal volumes from 10 mL to 350 mL and modifications of the software and hardware to update existing functionalities.

Here's a breakdown of the acceptance criteria and the studies mentioned in the provided 510(k) summary for the GETINGE GROUP SERVO-i and SERVO-s Ventilator Systems, organized according to your requested format.

It's important to note that this document is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device. Therefore, the "studies" described are primarily verification and validation activities rather than formal clinical trials designed to prove efficacy from scratch. The acceptance criteria are largely implied by compliance with standards and successful performance in these verification and validation tests.

Acceptance Criteria and Device Performance

This section synthesizes the implicit acceptance criteria from the various verification and validation activities described and attempts to align them with the reported "performance" based on the conclusions drawn in the document.

Study Information

The document describes verification and validation activities rather than a single, formal "study" with a defined test set sample size for regulatory approval of this specific 510(k) submission's changes. The clinical activities mentioned are more akin to post-market evaluations or validation of specific features, built upon the foundation of the predicate devices.

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

• Test Set (General Verification & Validation): Not explicitly stated as a uniform "test set" in terms of number of patients or specific data points for the entire device. The document refers to "existing and new test cases at the system and subsystem level" and "regression tests."
• Data Provenance (General): Not specified. Likely a combination of lab simulations, engineering tests, and potentially previous datasets from predicate device development.
• Specific Clinical Validation Activities (SERVO-i):
  • Nuisance Alarm Reduction (NAVA RR/MV): 22 patient treatments recorded across 6 sites. Provenance: Post-market evaluation, specifics (e.g., country) not stated but likely within markets where MAQUET operates.
  • Stress Index (SI): 10 adult patients with ALI or ARDS. Provenance: Not stated, likely clinical settings (hospitals).
  • Apnea Ventilation/Alarm Behavior (NAVA): Patients in 3 sites during four weeks. 25 clinicians involved. Provenance: Post-market evaluation, likely clinical settings.

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

• General V&V: "Software testers and clinicians" were involved in "Free User Testing (FUT)" in MAQUET's test laboratory. Specific number and qualifications not detailed.
• Specific Clinical Validation Activities (SERVO-i):
  • Nuisance Alarm Reduction (NAVA RR/MV): "Evaluation at MAQUET showed that the new algorithms did effectively calculate RR and MV while reducing the occurrence of nuisance RR and MV alarms." This implies internal experts at MAQUET (engineers, potentially medical staff) evaluated the data. Qualifications not specified.
  • Stress Index (SI): Comparison against "an existing system used in multiple published articles." This "existing system" acts as the de facto ground truth reference. The evaluation of results was likely done by MAQUET's internal team.
  • Apnea Ventilation/Alarm Behavior (NAVA): 25 clinicians filled in questionnaires. Their responses, evaluated by MAQUET, established the "ground truth" (or acceptance) that the new algorithm was acceptable and reduced nuisance alarms. Their specific qualifications (e.g., years of experience, specialty) are not detailed beyond "clinicians."

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

• No formal adjudication method like "2+1" or "3+1" is described. Evaluations were made by MAQUET internally or based on comparison with existing systems/feedback from clinicians.

4. If a multi-reader multi-case (MRMC) comparative effectiveness study was done:

• No, an MRMC comparative effectiveness study was not done. The device is a ventilator, not an AI diagnostic tool where human readers interpret output.

• Effect size of how much human readers improve with AI vs without AI assistance: Not applicable, as it's not an AI-assisted diagnostic tool for human readers. The "AI" (software algorithms) are intrinsic to the device's function.

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

• Yes, implicitly. The extensive "design verification and validation" for both SERVO-i and SERVO-s, including requirement verification, regression testing, code review, static code analysis, and compliance with product standards, represents standalone testing of the algorithm (software) and hardware. The "Free User Testing" involves human interaction, but the core functionality tests are against specifications.

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

• General V&V: Primarily established by device specifications, regulatory requirements (standards), and comparison to predicate device performance.
• Specific Clinical Validation Activities (SERVO-i):
  • Nuisance Alarm Reduction: Reduced frequency of nuisance alarms (an objective metric) and effective calculation of RR/MV (comparison to expected values).
  • Stress Index: Outputs from "an existing system used in multiple published articles."
  • Apnea Ventilation/Alarm Behavior: Clinician feedback via questionnaires, representing user acceptance and perceived reduction in nuisance alarms.

7. The sample size for the training set:

• Not applicable. This device is a medical ventilator (hardware and software) and not a machine learning model that undergoes a distinct "training phase." The "training" for the device's development involves engineering design, coding, and iterative testing, not data-driven machine learning in the conventional sense.

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

• Not applicable, as there is no specific "training set" in the context of a machine learning model. The "ground truth" for the device's design and functionality is established through engineering principles, adherence to medical device standards, clinical requirements, and performance of existing predicate devices.

Ask a specific question about this device

The HAMILTON-G5 ventilator is intended to provide positive pressure ventilatory support to adults, pediatrics, and optionally infants. The device is intended for use in the hospital and institutional environment where healthcare professionals provide patient care, including use as a patient bedside for intra-facility transport, provided compressed gas is supplied. The device is not intended for transportation outside the hospital or for use in the home environment.

The HAMILTON-G5 is an electronically controlled pneumatic intensive care ventilator ventilation system. It uses oxygen and air to ventilate adult, pediatric and optionally infant patients. It is powered by ac with battery backup to protect against power failure or unstable power and to facilitate intrahospital transport.

The HAMILTON-G5's pneumatics deliver gas, and its electrical systems control pneumatics, monitor alarms, and distribute power.

The user interface consists of a LCD-display with touch screen, keys, and a press-andturn knob.

The HAMILTON-G5 provides audible and visual patient- and ventilator-related alarms.

The provided 510(k) summary for the HAMILTON-G5 ventilator focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed study with specific acceptance criteria and performance metrics in the format usually associated with AI/ML device evaluations.

Here's a breakdown of the available information based on your request, along with explanations for missing sections:

1. Table of Acceptance Criteria and Reported Device Performance

The submission does not specify numerical acceptance criteria or present performance data in a quantitative table. The evaluation relies on demonstrating that the HAMILTON-G5 ventilator "conforms to the FDA recognized standards for safety and performance issues with lung ventilators" and that "the test results indicated that the device performed as specified." This implies that the device met pre-established engineering and regulatory standards, but these are not explicitly listed as "acceptance criteria" with corresponding "reported device performance" values in the document.

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

This information is not provided in the document. The submission states "Performance tests were performed," but does not detail the nature of these tests, the number of devices or scenarios tested, or the origin of any data (e.g., country of origin, retrospective/prospective). This is typical for a traditional medical device submission where the focus is on engineering and safety standards rather than clinical data sets.

3. Number of Experts Used to Establish Ground Truth and Qualifications

This information is not applicable/not provided. The HAMILTON-G5 is a continuous ventilator, not an AI/ML diagnostic or predictive device that would require expert-established ground truth for its performance evaluation in the context of this 510(k) summary. Its performance would be assessed against technical specifications and safety standards for ventilation.

4. Adjudication Method for the Test Set

This information is not applicable/not provided. As explained above, the device's performance is not evaluated based on expert adjudication of "ground truth" data in this context.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

This information is not applicable/not provided. The HAMILTON-G5 is a standalone medical device, not an AI-assisted diagnostic or decision support tool for human readers. Therefore, an MRMC study comparing human readers with and without AI assistance is not relevant to this submission.

6. Standalone (Algorithm Only) Performance Study

This information is not applicable/not provided. The HAMILTON-G5 is a physical ventilator, not an algorithm. Its performance is inherent to its mechanical and electronic design and operation, not a software algorithm that can be evaluated in isolation.

7. Type of Ground Truth Used

This information is not applicable/not provided. The concept of "ground truth" (e.g., pathology, outcomes data) usually applies to diagnostic or predictive devices being evaluated against a definitive standard. For a ventilator, performance is typically assessed against engineering specifications, safety standards, and physiological parameters (e.g., delivered tidal volume accuracy, pressure control, alarm thresholds) that are measurable and verifiable.

8. Sample Size for the Training Set

This information is not applicable/not provided. The HAMILTON-G5 is a hardware medical device with embedded software, not a machine learning model that undergoes a "training" phase with a dataset in the conventional sense. Its development involves engineering design, testing, and validation according to established medical device development processes.

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

This information is not applicable/not provided for the same reasons as #8.

In summary:

The provided 510(k) summary for the HAMILTON-G5 ventilator demonstrates substantial equivalence to predicate devices based on technological characteristics and performance specifications. It states that "performance tests were performed, and the test results indicated that the device performed as specified," and that the device "conforms to the FDA recognized standards for safety and performance issues with lung ventilators." However, it does not contain the detailed, quantitative acceptance criteria, study methodologies, or data provenance typically found in submissions for AI/ML-driven devices. The nature of the device (a continuous ventilator) means many of the requested categories (e.g., expert-established ground truth, MRMC studies, training sets) are not relevant to its 510(k) clearance process.

Ask a specific question about this device