Search Results

The SV600, SV800 Ventilators are intensive care situations for long-term or during transport within a professional healthcare facility. The SV600, SV800 Ventilators are intended to provide ventilation assistance and breathing support for adult and pediatric patients with a minimum body weight of 10 kg (all pediatric subgroups except newborns (neonates)). The SV600, SV800 Ventilators should be operated by properly-trained and authorized medical personnel. This equipment is not suitable for use in an MRI environment.

The SV600 and SV800 Ventilators are pneumatically-driven and electronically-controlled ventilators. The Ventilators consists of a main unit (including pneumatic circuit, electronic system, mechanical structure, display, CO2 module, SpO2 module), trolley and support arm.

This document outlines the substantial equivalence of the Mindray SV600 and SV800 Ventilators to a predicate device (Evita XL Ventilator K083050) and reference devices. The submission focuses on technical comparisons and various types of performance testing to demonstrate safety and effectiveness.

Here's a breakdown of the requested information based on the provided text:

1. A table of acceptance criteria and the reported device performance

The document does not explicitly provide a table of acceptance criteria with corresponding device performance for specific thresholds. Instead, it states that "The functional and system level testing showed that the devices continue to meet specifications and the performance of the device is equivalent to the predicate." It also notes that the device "meets its accuracy specification and is substantially equivalent to the predicate device."

The closest to "acceptance criteria" are the technical characteristics compared to the predicate and reference devices, and the standards the device was tested against. The "reported device performance" is implied by the statement of compliance with these standards and equivalency to the predicate.

Here's an example of how one might infer "acceptance criteria" from the technical characteristics table:

2. Sample sized used for the test set and the data provenance

The document mentions "functional and system level testing" and "bench testing" but does not specify the sample sizes for these tests. It also does not specify the data provenance (e.g., country of origin of the data, retrospective or prospective) for any of the testing. The nature of these tests (bench, functional, system level) generally implies laboratory or simulated environments, rather than patient data from a specific country or clinical setting.

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

This information is not provided in the document. The testing described (biocompatibility, software, EMC, electrical safety, bench testing) does not typically involve "experts establishing ground truth" in the way a clinical study would. These are generally engineering and performance evaluations against defined specifications and standards.

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

This information is not provided. Adjudication methods are typically relevant in clinical studies (e.g., for image interpretation or diagnosis) to resolve discrepancies between multiple evaluators. The types of testing described here (functional, system, bench, safety, EMC) do not involve such adjudication.

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

There is no mention of a multi-reader multi-case (MRMC) comparative effectiveness study. This document describes a ventilator (hardware and software for life support), not an AI-assisted diagnostic or interpretative device that would typically involve human "readers" or "AI assistance" in that context.

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

The document does not explicitly use the term "standalone" in the context of an algorithm. However, the majority of the testing described (software verification and validation, electromagnetic compatibility, electrical safety, bench testing) are inherently evaluations of the device's performance without continuous human intervention during the test itself, focusing on the device's adherence to specifications and standards. The "human factors testing" mentioned relates to the usability and user interface, ensuring safe and effective interaction for the intended users (medical personnel), rather than a "human-in-the-loop" performance study of an AI algorithm.

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

The concept of "ground truth" as typically understood in clinical or AI performance studies (e.g., pathology for a biopsy, expert consensus for an image diagnosis) is not directly applicable or explicitly stated for the types of testing described. For this device (ventilator), the "ground truth" for its performance is its adherence to:

• Engineering specifications (e.g., flow range, pressure range accuracy)
• Consensus standards (e.g., ISO, IEC for safety, EMC, performance characteristics)
• Functional requirements (e.g., does it deliver the correct ventilation modes)

These are verified through various physical and software tests against known engineering principles and standardized test methods.

8. The sample size for the training set

This information is not applicable/not provided. Ventilators are not typically "trained" using data sets in the way AI/ML algorithms are. This is a traditional medical device whose functionality is based on pre-programmed logic, control algorithms, and pneumatic/electronic design.

9. How the ground truth for the training set was established

This information is not applicable/not provided for the same reason as point 8.

Ask a specific question about this device

The CARESCAPE R860 ventilator is designed to provide mechanical ventilation or support to neonatal, pediatric, and adult patients weighing 0.25 kg and above.

The CARESCAPE R860 ventilator is a microprocessor based, electronically controlled, pneumatically driven ventilator that includes integrated monitoring of FiO2, airway pressure, flow, and volume. Additional respiratory gas monitoring capabilities are supported through the use of optional GE patient monitoring modules.

Not all features are available for all patient types or product configurations.

O2 Therapy is intended to be used for all adult patients and pediatric patients greater than 10 kg in weight.

The CARESCAPE R860 ventilator is not a pulmonary function calculation device.

The system is designed for facility use, including within-facility transport, and should only be used under the orders of a clinician.

The CARESCAPE R860 is a flexible, adaptable, intuitive critical care ventilator offering invasive and non-invasive ventilation support. Touchscreen capability allows the user to quickly and easily access patient information and procedures. A wide selection of performance options gives the user full control of the system configuration. Icons represent configurable views of past (historical trends), present (patient status), and future patient needs (clinical decision support). The CARESCAPE R860 features patient monitoring, patient ventilation, and the capability of interfacing with central information management systems.

The CARESCAPE R860 ventilator is intended for healthcare facility use, including withinfacility transport.

The ventilator offers multiple ventilation modes:

• A/C VC (Assist Control Volume Control)
• A/C PC (Assist Control Pressure Control)
• A/C PRVC (Assist Control Pressure Regulated Volume Control)
• SIMV VC (Synchronized Intermittent Mandatory Ventilation Volume Control)
• SIMV PC (Synchronized Intermittent Mandatory Ventilation Pressure Control)
• CPAP/PS (Continuous Positive Airway Pressure/Pressure Support)
• SBT (Spontaneous Breathing Trial)
• nCPAP (nasal Continuous Positive Airway Pressure)
• SIMV PRVC (Synchronized Intermittent Mandatory Ventilation Pressure . Regulated Volume Control)
• BiLevel
• BiLevel VG (BiLevel airway pressure ventilation Volume Guaranteed)
• VS (Volume Support)
• NIV (Non-Invasive Ventilation)
• APRV (Airway Pressure Release Ventilation)

In addition, a breathing support mode, O2 Therapy, is being added as a new feature in this 510(k). The O2 Therapy mode is available for adult and pediatric patients weighing greater than 10kg.

Optional functionality includes integrated respiratory gas monitoring, capabilities to measure SpiroDynamics, and calculation of functional residual capacity of mechanically ventilated patients. The integrated respiratory gas monitoring is provided via the Datex-Ohmeda Gas Modules, which are physically integrated into the CARESCAPE R860, can receive electronic power from the CARESCAPE R860 and communicate measured values to the CARESCAPE R860 for display on the system display unit.

This document is a 510(k) Pre-market Notification for a medical device (CARESCAPE R860 ventilator). It focuses on demonstrating substantial equivalence to a previously cleared predicate device, rather than proving that a new AI/ML-based device meets specific performance criteria through a traditional clinical study with ground truth.

Therefore, many of the requested elements (e.g., acceptance criteria for AI performance, sample size for test sets, expert adjudication methods, MRMC studies, standalone performance, ground truth types for training/test sets) are not applicable in this context.

The document describes engineering verification and validation testing and compliance with recognized consensus standards to demonstrate that the modified device remains safe and effective and is substantially equivalent to its predicate.

Here's the information that is applicable and can be extracted from the provided text, along with explanations of why other points are not relevant:

1. A table of acceptance criteria and the reported device performance

The document doesn't present specific acceptance criteria in the format of a clinical performance study with AI metrics (like sensitivity, specificity, or AUC). Instead, it discusses the device's functional performance specifications and how they align with the predicate device and relevant standards. The "performance" is demonstrated through verification and validation that the modified device continues to meet its functional specifications and standards.

The closest to "acceptance criteria" are the specifications listed in the "Substantial Equivalence to the predicate CARESCAPE R860" and "Substantial Equivalence to the reference device, Hamilton G5" tables. The "reported device performance" is implied by the statement that the device meets these specifications and has undergone "Verification and validation was performed to demonstrate that the changes to the software continue to comply with applicable standards and guidances, and the product continues to meet the performance specifications."

Here's a partial summary derived from the tables:

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

This information is not applicable as this is not a study involving a clinical test set from patient data for AI model evaluation. The "test set" here refers to engineering and software verification and validation activities. The document states:

• "Non-clinical testing was performed to establish substantial equivalence of the CARESCAPE R860."
• "Verification and validation testing has been performed according to predetermined acceptance criteria..."
• "Testing included: Software verification and validation, Waveform comparison analysis, System verification, Accuracy testing, Stress testing."
• "Where the changes to the ventilator affected compliance with applicable consensus standards, testing was performed to confirm continued compliance, or to demonstrate compliance with the recognized version of the standard."

The document does not detail specific sample sizes for these engineering tests (e.g., number of test cycles, duration of stress tests, number of waveforms analyzed). Data provenance (country of origin, retrospective/prospective) is also not applicable for this type of non-clinical testing.

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)

Not applicable. This submission focuses on hardware and software changes to a ventilator, not on a diagnostic AI device requiring expert-labeled ground truth from patient data. The "ground truth" for this device's performance is typically defined by engineering specifications, relevant industry standards, and established methods for measuring ventilator performance using test lungs and specialized equipment.

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

Not applicable. Adjudication methods are relevant for clinical studies where human experts disagree on interpretations of medical data used as ground truth for an AI assessment. This is an engineering verification and validation submission for a physical device.

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

Not applicable. This is not an AI-assisted diagnostic or clinical decision support device that would involve human readers.

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

Not applicable. This device (a ventilator) is not a standalone algorithm in the sense of AI/ML. Its performance is inherent in its electromechanical and software operation, which is verified against engineering specifications, not evaluated as an "algorithm only" with data processing outputs.

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

The "ground truth" in this context is based on engineering specifications, established physical principles, and recognized consensus standards for medical device performance. For example, accuracy testing involves comparing device measurements (e.g., FiO2, flow, volume) against known, precise inputs from calibrated equipment. Waveform comparison analysis involves comparing generated waveforms against theoretical or expected waveforms.

8. The sample size for the training set

Not applicable. This device introduction does not describe the development or training of an AI/ML model from a "training set" of data. The software development follows traditional engineering processes, not AI model training.

9. How the ground truth for the training set was established

Not applicable. Per point 8, there is no AI/ML training set as described in the context of diagnostic or prognostic AI.

Ask a specific question about this device

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

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

The Servo-u MR 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
• to be used in MR environment according to specified conditions
• with 1.5 T or 3 T MR scanners
• outside magnetic fields >20 mT/200 Gauss

The Servo-u/n/u MR Ventilator Systems 4.1 consist 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/u MR Ventilator Systems 4.1 are based on the cleared predicate device Servo-u/n Ventilator Systems 2.1 (K180098) with some improvements. The ventilation modes in the Servo-u/n/u MR 4.1 are the same as the predicate device. Standard configurations of available modes and optional modes do differ between the devices, i.e. Servo-u/n/u MR 4.1.

The ventilators deliver controlled or supported breaths to the patient, with constant flow, constant pressure, using a set oxygen concentration. The ventilators can also deliver High Flow therapy with a constant flow.

The Electrical activity of the diaphragm (Edi) is a measurement of the patients own breathing efforts. The Edi functionality makes it possible to monitor Edi activity in all ventilation modes, High Flow therapy as well as in Standby.

NAVA stands for Neurally Adjusted Ventilatory Assist and is a supported mode of ventilation based on the Edi, delivering assist in proportion to and synchronized with the patient's respiratory drive. NAVA is available as an invasive and a non-invasive mode. The included parts related to this mode, such as Edi module and Edi catheters are identical to the cleared predicate devices Servo-u/n 2.1 (K180098).

Servo-u/n contain a dedicated controller circuit for the Aerogen Solo nebulizer (included as standard). It is identical to the cleared predicate devices Servo-u/n 2.1 (K180098). Not available on Servo-u MR.

Accessories for CO2 monitoring and flow and pressure measurements at the Y piece (Y sensor) are integrated as options. It is identical to the cleared predicate devices Servo-u/n 2.1 (K180098).

The Servo-u/n/u MR Ventilator Systems will produce visual and audible alarms if any parameter varies beyond pre-set or default limits and log alarm recordings. The alarm handling is similar to the one used in the cleared predicate devices Servo-u/n 2.1 (K180098).

The Servo-u/n/u MR Ventilator Systems contain provisions for battery modules to supply the system in the case of mains power failure or during intra-hospital transport. The batteries are identical to the one used for the cleared predicate devices Servo-u/n 2.1 (K180098).

Based on the provided text, the device in question is the "Servo-u Ventilator System 4.1, Servo-n Ventilator System 4.1, Servo-u MR Ventilator System 4.1". This document is a 510(k) premarket notification to the FDA, asserting substantial equivalence to previously cleared predicate devices.

*Crucially, this document does not contain any information regarding clinical studies, acceptance criteria, or performance data in the context of an AI/human reader study. It focuses on the technical modifications, safety, and regulatory compliance of a medical device (ventilator systems) to demonstrate substantial equivalence to a predicate device.

Therefore, I cannot provide the requested information for the following reasons:

• No AI component or human reader study: The document describes hardware and software updates to ventilator systems. There is no mention of an Artificial Intelligence (AI) component or any study involving human readers or expert consensus on clinical images/data.
• Focus on Substantial Equivalence: The primary goal of this 510(k) submission is to demonstrate that the updated ventilator systems are "substantially equivalent" to previously cleared predicate devices, primarily through engineering testing, software verification, and adherence to performance standards, not through clinical comparative effectiveness trials in the way an AI diagnostic tool would be evaluated.
• Type of Testing: The non-clinical testing listed (code review, static code analysis, unit tests, integration tests, specification and system-level verification testing, waveform testing, biocompatibility, human factors validation testing) are typical for medical device development to ensure functionality and safety, not AI model performance.

In summary, the provided text does not contain the information necessary to answer your request about acceptance criteria and a study proving an AI device meets those criteria. The document pertains to the clearance of ventilator systems, not an AI diagnostic or assistive device.

Ask a specific question about this device

The HAMILTON-C6 ventilator is intended to provide positive pressure ventilatory support to adults and optionally infants and neonates.

Intended areas of use:

• In the intensive care ward, intermediate care ward, emergency ward, long term acute care hospital or in the recovery room

• During transfer of ventilated patients within the hospital

The HAMILTON-C6 ventilator is a medical device intended for use by qualified, trained personnel under the direction of a physician and within the limits of its stated technical specifications.

The HAMILTON-C6 is designed for adult, pediatric, infant, and neonatal patients requiring invasive or noninvasive ventilation support. It covers a full range of clinical requirements, including invasive ventilation, automated ventilation with Adaptive Support Ventilation (ASV), and noninvasive ventilation.

The HAMILTON-H900 and IntelliCuff control options for the HAMILTON-C6 allow the remote control of the HAMILTON-H900 humidifier and IntelliCuff cuff pressure controller through the HAMILTON-C6 ventilator.

This document is a 510(k) summary for the Hamilton-C6 continuous ventilator. It focuses on demonstrating substantial equivalence to a predicate device (Hamilton-C3) and a reference device (Hamilton-G5), rather than providing details of an AI-based system. Therefore, much of the requested information regarding acceptance criteria and a study proving an AI device's performance cannot be extracted directly from this document.

However, I can provide information about the general performance criteria that were referenced for the device in question, a continuous ventilator.

1. A table of acceptance criteria and the reported device performance

The document does not provide specific numerical acceptance criteria (e.g., accuracy, sensitivity, specificity) with corresponding reported device performance values. Instead, it states that:

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

The document does not specify a "test set" in the context of an AI algorithm, nor does it provide details about sample sizes, data provenance, or whether data was retrospective or prospective. The testing mentioned appears to be general device performance and safety testing.

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 applicable to the type of device and testing described in the document. Ground truth for an AI algorithm is not mentioned as this is not an AI device submission.

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

This information is not applicable to the type of device and testing described in the document.

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 as the HAMILTON-C6 is a continuous ventilator, not an AI-assisted diagnostic or interpretive device. There is no mention of human readers or AI assistance in this context.

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

This information is not applicable. The HAMILTON-C6 is a physical medical device (ventilator), not a standalone algorithm.

7. The type of ground truth used (expert concensus, pathology, outcomes data, etc)

The concept of "ground truth" in the context of expert consensus, pathology, or outcomes data is not applied in this document, as it is a submission for a continuous ventilator, not an AI diagnostic/interpretive system. The "ground truth" used for performance testing of the ventilator would have been based on established engineering standards and validated physical measurements against expected device outputs.

8. The sample size for the training set

This information is not applicable to the type of device and testing described in the document. There is no training set for an AI algorithm mentioned.

9. How the ground truth for the training set was established

This information is not applicable.

Ask a specific question about this device