Search Results

The Nihon Kohden NKV-550 Series Ventilator System is intended to provide continuous ventilation for adult, pediatric and neonatal patients who require invasive or noninvasive respiratory support. The NKV-550 offers mandatory and spontaneous ventilation modes as well as respiratory monitoring. The NKV-550 is intended for use in hospitals and hospital-type facilities, as well as, for in-hospital transportation.

The Nihon Kohden NKV-550 Series Ventilator System consists of a graphic user interface (GUI) and a breath delivery unit (BDU). The GUI allows clinicians to set ventilator control parameters such as tidal volume and inspiratory pressure, to set alarm limits such as high inspiratory pressure alarm, to view monitored numeric values, to view waveform and loops, and to operate various features through the apps. The BDU contains a microprocessor that receives inputs from the electronic system and controls the pneumatic system for breath delivery to the patient. It also provides various alarms, a safety valve, and other design features to maximize patient safety.

This document, K192307, is a 510(k) premarket notification for a medical device (Nihon Kohden NKV-550 Series Ventilator System). It asserts substantial equivalence to a predicate device. As such, the FDA does not require a clinical study with human patients to demonstrate device performance against specific acceptance criteria for a new AI/ML algorithm. Instead, the focus is on demonstrating that the revised device meets the same performance and safety standards as the predicate device.

Therefore, the requested information about "acceptance criteria" and "study that proves the device meets the acceptance criteria" in the context of an AI/ML algorithm (including sample sizes, ground truth establishment, expert adjudication, MRMC studies, and standalone performance) is not applicable to this submission. This submission is for a ventilator, not an AI/ML diagnostic or therapeutic device.

The document discusses non-clinical performance data and states that clinical performance data was not required to demonstrate substantial equivalence.

Here's a breakdown of why the specific questions about an AI/ML study can't be answered from this document:

• 1. A table of acceptance criteria and the reported device performance: The document does not provide a table of performance acceptance criteria in the context of an AI/ML algorithm's output. It mentions "Met ISO 80601-2-12 requirements on essential performance of critical care ventilator," which refers to international safety and performance standards for ventilators, not an AI's diagnostic accuracy.
• 2. Sample sizes used for the test set and the data provenance: Not applicable. There is no AI/ML test set.
• 3. Number of experts used to establish the ground truth for the test set and the qualifications: Not applicable. There is no AI/ML ground truth establishment.
• 4. Adjudication method (e.g., 2+1, 3+1, none) for the test set: Not applicable.
• 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 device.
• 6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable.
• 7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not applicable.
• 8. The sample size for the training set: Not applicable. There is no AI/ML training set.
• 9. How the ground truth for the training set was established: Not applicable.

What the document does provide regarding device performance:

The document states that the performance of the Nihon Kohden NKV-550 Series Ventilator System was demonstrated by various non-clinical tests performed in compliance with Design Controls:

• Software Verification
• Electrical Safety & EMC Testing
• Device Functionality Testing
• Performance of Therapy Types and Ventilation Modes
• Environmental Testing
• Cleaning & Disinfection
• Risk Management
• Accessory Compatibility
• Regression Testing

The key "performance" criterion mentioned is meeting ISO 80601-2-12 requirements on essential performance of critical care ventilators. This is a general safety and effectiveness standard for the device's physical and functional operation, not related to an AI's analytical accuracy.

In summary, this 510(k) submission is for a conventional medical device (a ventilator) with minor modifications, and as such, the detailed clinical study and AI/ML-specific acceptance criteria information requested is not part of this type of regulatory submission.

Ask a specific question about this device

The bellavista 1000/1000e ventilator is intended to provide positive pressure ventilatory support to adult and pediatric patients and optionally infant and neonatal patients by qualified, trained personnel under the direction of a physician.

Environment of use: hospitals, sub-acute care facilities and intra-hospital transfer

When used on neonatal patients: The environment of use is the Neonatal Intensive Care Unit (NICU).

bellavista is an electronically controlled pneumatic ventilation system. It is powered by AC or DC and also provided with an internal battery. The bellavista pneumatic system supplies respiratory gas whilst the electrical systems control the pneumatics and provides the power supply.

The user can enter values or parameters in the bellavista via the touch screen. These inputs entail instructions for bellavista's pneumatic system to ventilate the patient with a precisely controlled gas mixture. bellavista gathers readings from the proximal flow sensor within the ventilator.

I am sorry, but the provided text does not contain the information required to answer your request. The document is an FDA 510(k) clearance letter and summary for a medical device (ventilator). It describes the device, its intended use, a comparison to predicate devices, and the basis for substantial equivalence.

However, it does not include details about acceptance criteria, specific device performance numerical results, sample sizes for test or training sets, data provenance, expert qualifications, ground truth establishment, or any details about a multi-reader multi-case (MRMC) study or standalone algorithm performance, as these are typically part of a clinical validation study and not usually found in a 510(k) summary for a ventilator.

The document discusses the ventilatory support capabilities and patient populations for which the device is intended, but not the kind of detailed performance metrics usually required for AI/algorithm-based diagnostic devices.

Ask a specific question about this device

The Unity Network ID is indicated for use in data collection and clinical information management through networks with independent bedside devices. The Unity Network ID is not intended for monitoring purposes, nor is the Unity Network ID intended to control any of the clinical devices (information systems) it is connected to.

The Unity Network ID system communicates patient data from sources other than GE Medical Systems Information Technologies, Inc. equipment to a clinical information system, central station, and/or GE Medical Systems Information Technologies Inc. patient monitors.

The Unity Network ID acquires digital data from eight serial ports, converts the data to Unity Network protocols, and transmits the data over the monitoring network to a Unity Network device such as a patient monitor, clinical information system or central station.

This document primarily describes a 510(k) premarket notification for the GE Healthcare Unity Network ID, focusing on its substantial equivalence to a predicate device, Unity Network ID V8 (K170199). It does not contain information about acceptance criteria for device performance with specific metrics or detailed study results where a device's performance is measured against those criteria.

The information provided describes the device's function (data collection and clinical information management), its intended use, and the changes made from the predicate device (primarily software updates to support new third-party devices).

However, it explicitly states:
"The Unity Network ID V9 was tested to assure that the device meets its design specifications. Testing included all new or modified features."
and
"The subject of this premarket submission, Unity Network ID V9, did not require clinical studies to support substantial equivalence."

Therefore, based on the provided text, I cannot describe the acceptance criteria and study as requested, because specific performance acceptance criteria and a study demonstrating the device meets those criteria are not detailed.

The document only states that non-clinical tests were performed to ensure compliance with voluntary standards and design specifications. It lists general quality assurance measures applied during development and testing but does not provide specific performance metrics, sample sizes, ground truth establishment, or expert involvement as typically found in a clinical performance study for AI/machine learning devices.

Here's a breakdown of the specific points you requested, noting what is and isn't available in the provided text:

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

   • Not Available: The document does not provide a table of acceptance criteria nor reported device performance metrics against such criteria. It states the device "meets its design specifications" and "comply with, applicable voluntary standards," but no specifics are given.

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

   • Not Available: No test set sample sizes or data provenance are mentioned as no clinical studies were performed. The testing described is non-clinical verification and validation of design specifications.

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/Not Available: Since no clinical studies were required and no test sets with ground truth are described, there is no information about experts establishing ground truth.

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

   • Not Applicable/Not Available: No clinical test set or adjudication method is described.

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/Not Available: This device is a data collection and management system, not an AI-assisted diagnostic tool. No MRMC study was performed or is relevant for this type of device.

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

   • Not Applicable/Not Available: This device is not an algorithm for diagnostic or prognostic purposes, but rather an interface for data transmission. Standalone performance in the context of an algorithm is not relevant here.

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

   • Not Applicable/Not Available: No ground truth in the context of a clinical performance study is mentioned.

8. The sample size for the training set

   • Not Applicable/Not Available: This device is not an AI/machine learning model that requires a training set in the conventional sense. Its "training" would involve configuring it to correctly interpret and transmit data from specific third-party devices, which is part of its design and verification process, not a machine learning training process.

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

   • Not Applicable/Not Available: See point 8.

Ask a specific question about this device

The Puritan Bennett 980 Series Ventilator System is designed for use on patient population sizes from Neonatal (NICU) through Adult who require respiratory support or mechanical ventilation and weigh a minimum of 0.3kg (0.66lb). It is suitable for service in hospital (institutions) and intra-hospital transport to provide continuous positive pressure ventilatory support using medical oxygen and compressed medical air from either an internal air compressor or external air sources to deliver oxygen concentrations of 21% to 100%. Ventilatory support can be delivered invasively or non-invasively to patients who require the following types of ventilator support

• Positive Pressure Ventilation, delivered invasively (via endotracheal tube or tracheotomy tube) or noninvasively (via mask or nasal prongs)
• Assist/Control, SIMV, or Spontaneous modes of ventilation

The Puritan Bennett 980 Series Ventilator System is a dual-microprocessor-based, touch-screen controlled; critical care ventilator intended to provide continuous ventilation for neonate to adult patients who require either invasive ventilation or non-invasive ventilation. It can be used in hospitals and institutions and for intra –hospital transport applications with access to the appropriate services.
The ventilator system offers features for patient comfort while delivering sensitive, precise breaths to critically ill patients. The product ventilates Neonatal, Pediatric, and Adult patients with predicted body weights from 0.3 kg, and with tidal volumes for mandatory volume controlled breaths from 2 mL to 2500 mL.

The provided text is a 510(k) summary for the Puritan Bennett 980 Ventilator System. It details the device's characteristics, indications for use, and a comparison to predicate devices, primarily focusing on non-clinical evidence for substantial equivalence.

Based on the provided information, I can only provide limited answers to your request as the document does not contain details about acceptance criteria, device performance metrics, or a study that would involve a test set with ground truth, experts, or MRMC studies. This is because the submission is for a ventilator, not an AI/CADe device.

Here's an attempt to answer based on the available information, noting when the information is not available in the provided document:

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

This information is not available in the provided document. The document focuses on demonstrating substantial equivalence through non-clinical verification and validation, rather than specific performance metrics against acceptance criteria for an AI/CADe system.

2. Sample sized 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 and not available in the provided document. The submission is for a ventilator, which does not typically involve a "test set" of data for performance evaluation in the way an AI/CADe device would. The "test sets" mentioned relate to engineering tests (e.g., electrical safety, EMC) rather than clinical data for AI model evaluation.

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 and not available in the provided document. As it's a ventilator, there isn't a "ground truth" establishment by medical experts for image interpretation or diagnosis.

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

This information is not applicable and not available in the provided 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

This information is not applicable and not available in the provided document. MRMC studies are typically used for assessing the impact of AI/CADe systems on human performance in diagnostic tasks, which is not relevant to a ventilator submission.

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

This information is not applicable and not available in the provided document. A ventilator's performance is not typically evaluated as a "standalone algorithm" in this context.

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

This information is not applicable and not available in the provided document.

8. The sample size for the training set

This information is not applicable and not available in the provided document. The ventilator has software, but it is not described as an AI or machine learning system that requires a "training set" in the context of image analysis or diagnostic tasks.

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

This information is not applicable and not available in the provided document.

Ask a specific question about this device