Search Results

The Infinity Acute Care System Workstations Neonatal Care consist of monitoring and control displays and additional therapy units. They are intended to be used as integrated, networked, and configurable workstations to provide specific therapy in neonatal intensive care. The Infinity Acute Care System Workstations Neonatal Care are intended to be used by qualified and trained medical personnel.

The Infinity C Series Medical Cockpits, consisting of the C500 and the C700, are monitoring and control displays for the Infinity Acute Care System (IACS). Medical Cockpits are intended to be used to monitor waveforms, parameter information, and alarms as well as to control settings. The Infinity Series Medical Cockpits are intended to be used in environments where patient care is provided by trained healthcare professionals.

The Babylog VN500 ventilation unit of the Infinity Acute Care System is intended for the ventilation of neonatal patients from 0.4 kg (0.88 lbs) up to 10 kg (22 lbs) and pediatric patients from 5 kg (11 lbs) up to 20 kg (44 lbs) bodyweight. Babylog VN500 offers mandatory ventilation modes for spontaneous breathing support and airway monitoring. The Babylog VN500 ventilation unit is used with Infinity C Series Dräger Medical Cockpits. The Babylog VN500 ventilation unit is intended for use in different medical care areas.

Babylog VN500 is intended for stationary use in hospitals and medical rooms or for patient transportation within the hospital.

The Infinity Acute Care System Workstation Neonatal Care provides Neonatal-Care specific functionality. It is made up of the ventilation unit Babylog VN500 and the Infinity Medical Cockpit C500.

The ventilation unit provides Neonatal-Care specific ventilation and monitoring data of ventilation parameters. The Infinity Medical Cockpit C500 is the control and display unit which runs a ventilation application. The patient monitoring data are displayed on the Infinity Medical Cockpit C500, which is also used to control ventilation settings including alarms.

The ventilation unit Babylog VN500 of the Infinity Acute Care System Workstation Neonatal Care is a microprocessor-controlled ventilator. The Babylog VN500 provides overpressure ventilation and adjustable oxygen concentration with pressure- and volume-controlled automatic and spontaneous breathing modes.

The ventilation application software on the Infinity Medical Cockpit C500 is needed to allow the user to display and control all ventilation parameters of the ventilation unit. The combination of the ventilation software application on the Infinity Medical Cockpit C500, together with the Babylog VN500, provides the functionality of a complete ventilator (e.g. Evita XL).

The ventilation application supports simultaneous display of patient waveforms, parameter data, alarm display and annunciation, in addition to supporting graphical or textual display of historical data.

The Infinity Acute Care System can interface with specific Dräger Medical therapeutic and diagnostic equipment, as well as third party devices via a MEDIBUS data connection.

The user interface of the Infinity Acute Care System Workstation Neonatal Care is the Infinity Medical Cockpit C500, a standardized display and control unit for the connected monitoring and therapy units.

The Infinity Medical Cockpit C500 is a standard platform, using common hardware, software, and user interface components to facilitate ease of use for clinicians.

The provided text is a 510(k) summary for the Dräger Infinity Acute Care System Workstation Neonatal Care, a medical device that includes a ventilator. This document focuses on demonstrating substantial equivalence to predicate devices and adherence to relevant standards for safety and performance.

It is important to note that this document is a 510(k) summary for a ventilator, not an AI/ML-powered diagnostic device. Therefore, many of the requested criteria (such as sample sizes for test/training sets, data provenance, number/qualification of experts, adjudication methods, MRMC studies, standalone performance, and ground truth establishment) are generally not applicable to this type of traditional medical device submission.

The document details the device's functionality, indications for use, and a list of performance testing against various IEC and ISO standards, as well as FDA guidance for ventilators. This performance testing confirms the device's safety and effectiveness according to established engineering and medical device standards.

Here's an attempt to address the requested information based on the provided text, indicating when information is not present or not applicable:

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

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

• Sample Size for Test Set: Not applicable/not mentioned. Traditional ventilator submissions typically involve bench testing, engineering verification and validation, and clinical good-use practices rather than test sets with patient data.
• Data Provenance: Not applicable. The testing is primarily engineering and performance-based, not data-driven in the sense of patient datasets.

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. The "ground truth" for a ventilator's performance is its ability to meet specified engineering and safety parameters, often validated by qualified engineers and verified through objective measurements against regulatory standards. There is no concept of "expert ground truth" in the diagnostic sense for this device.

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

• Not applicable. Adjudication methods like 2+1 or 3+1 are typically used for establishing ground truth in diagnostic studies involving human interpretation or expert consensus on medical images or clinical cases. This is not relevant to a ventilator's performance testing.

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. MRMC studies are used for evaluating the performance of diagnostic imaging devices, especially those involving human interpretation, and comparing human performance with and without AI assistance. This device is a ventilator, not a diagnostic AI tool.

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

• Not applicable. This device is a standalone ventilator system; however, it is not an algorithm-only device or an AI system that would have a "standalone" algorithmic performance distinct from its human-in-the-loop operation. Its performance is its standalone mechanical and electronic functionality.

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

• Type of Ground Truth: The "ground truth" for this device's performance is defined by its adherence to the specified technical standards (e.g., IEC 60601 series, ISO 14971) and functional specifications (e.g., accurate delivery of ventilation modes, stable oxygen concentration, correct alarm functionality). This is established through engineering testing, verification, and validation against a predetermined set of technical requirements and regulatory benchmarks.

8. The sample size for the training set

• Not applicable. This device is a traditional ventilator and does not employ AI/Machine Learning models that require training sets.

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

• Not applicable. No training set is used for this type of device.

Ask a specific question about this device

The Fabius GS/Fabius Tiro is indicated as a continuous flow anesthesia system. The Fabius GS/Fabius Tiro can be used for spontaneous, manually assisted, automatic, pressure support, or synchronized mandatory intermittent ventilation, delivery of gases and anesthetic vapor, and monitoring oxygen concentration, breathing pressure and respiratory volume of patients during anesthesia. Federal law restricts this device to sale by or on the order of a physician.

The Fabius GS/Fabius Tiro is a continuous flow gas anesthesia system.

The provided document is a 510(k) summary for the Fabius GS/Fabius Tiro Anesthesia System, specifically for a software modification to include Synchronized Intermittent Mandatory Ventilation with Pressure Support (SIMV/PS) as an optional ventilation mode.

Based on the content, here's an analysis of the acceptance criteria and study information:

Description of Acceptance Criteria and Reported Device Performance

The document describes the addition of SIMV/PS mode to the existing Fabius GS/Fabius Tiro Anesthesia System. The acceptance criteria are implicitly based on demonstrating substantial equivalence to existing predicate devices (Evita 4 Ventilator K961687 and 7900 Ventilator K023366) with SIMV with Pressure Support ventilation modes. The substantial equivalence is claimed based on functional similarities and that the device "meets" these similarities.

Study Details:

This document describes a 510(k) submission, which primarily relies on demonstrating substantial equivalence to predicate devices rather than a standalone clinical study on the device's performance against specific acceptance criteria. Therefore, many of the requested details typically found in the clinical study report are not explicitly present.

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

   • Test Set Sample Size: Not applicable in the context of this 510(k) submission. No patient-level test set data is mentioned for performance evaluation in the conventional sense. The "test set" here refers to the parameters and functionalities that were verified against the predicate devices.
   • Data Provenance: Not specified. The submission relies on a comparison of technical specifications and features with previously cleared predicate devices.

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

   • Not applicable as this is a comparison against predicate devices' functionalities, not a diagnostic or clinical performance study requiring expert ground truth establishment. The "ground truth" for substantial equivalence is the functionality of the predicate devices.

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

   • Not applicable. There's no clinical data adjudication described in this type of submission.

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 MRMC study was conducted. This device is an anesthesia system, not an AI-powered diagnostic tool for human readers.

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

   • No standalone algorithm performance study was described. The submission focuses on the integration of a new ventilation mode (software change) into an existing, cleared anesthesia system. Performance claims are based on similarity to predicate devices already cleared for use.

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

   • The "ground truth" for this submission is the established functionality and regulatory clearance of the predicate devices (Evita 4 Ventilator and 7900 Ventilator) regarding their SIMV with Pressure Support ventilation modes. The new device's SIMV/PS mode is deemed substantially equivalent based on matching these functionalities and parameters.

7. The sample size for the training set:

   • Not applicable. This is not a machine learning or AI algorithm in the sense that it requires a training set of data. The "training set" would implicitly be the established engineering and design principles used to develop the software, which are not quantified in terms of sample size here.

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

   • Not applicable for the same reasons as above. The "ground truth" for the development of the SIMV/PS mode would stem from medical knowledge of ventilation, engineering specifications, and the functionality observed in the predicate devices.

Ask a specific question about this device

The Fabius GS and Fabius Tiro are indicated as a continuous flow anesthesia systems. The Fabius GS and Fabius Tiro are indicated for spontaneous, manually assisted, automatic or pressure support ventilation; delivery of gases and anesthetic vapor of patients during anesthesia. The Fabius GS and Fabius Tiro can monitor inspired oxygen concentration, breathing pressure and respiratory volume of patients during anesthesia. The Fabius GS and Fabius Tiro are to be used only in the order of a physician.

The Fabius GS and Fabius Tiro are continuous flow gas anesthesia systems.

The provided document does not contain specific acceptance criteria or a detailed study description for the Fabius GS and Fabius Tiro Anesthesia Systems' Apnea Ventilation feature in the same way one would expect for a machine learning or AI-driven device.

Instead, the document focuses on demonstrating substantial equivalence to existing predicate devices based on a hazard analysis, system-level qualification, and verification/validation tests. The Apnea Ventilation feature is described as a software change.

Therefore, many of the requested details (like sample sizes for test/training sets, data provenance, expert ground truth, MRMC studies, standalone performance, etc.) are not applicable or not provided in this type of regulatory submission, which predates the common expectations for AI/ML device descriptions.

However, I can extract the available information and indicate where details are not provided.

1. Table of Acceptance Criteria and Reported Device Performance

Given that this is a 510(k) submission for a software change to an existing device, the "acceptance criteria" are framed in terms of maintaining safety and effectiveness and demonstrating substantial equivalence to predicates. Performance is described functionally rather than with quantitative metrics typically found in AI/ML performance tables.

• User Alert: All three devices (Fabius GS/Tiro, Evita 4, 7900 Ventilator) alert the user to the apnea condition.
• User Disablement: The Apnea Ventilation feature can be disabled by the user, similar to the predicate devices.
• Backup Function: Intended as a short-term backup to prevent apnea if spontaneous effort fails.
• Core Functionality: Basic infrastructure, operating principle, alarm strategies, fault detection circuitry, and mechanical/pneumatic subassemblies remain unchanged. |
  | Hazard Analysis & Qualification Success | Qualification included hazard analysis, system level qualification, and verification/validation tests were performed, implying successful completion. (Specific results or metrics from these tests are not detailed in this summary). |
  | Functional Equivalence | - All devices are triggered if a user-selected time elapses without a spontaneous breath during pressure support ventilation.
• All prevent an apnea condition.
• All alert the user to the condition.
• All can be disabled by the user. |
  | (Implied) No adverse impact on existing device features | The document states the change is "software only" and that the "basic infrastructure... remain unchanged," implying functionality not related to the Apnea Ventilation feature is unaffected. |

Study Details:

The document describes the evidence for substantial equivalence, which primarily constituted a comparison to predicate devices and internal qualification processes.

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

• Not Applicable / Not Provided: This submission focuses on a software change to an existing device and its substantial equivalence to predicate devices. There is no mention of a "test set" in the context of patient data or algorithm performance used in a way that generates sample sizes for statistical analysis relevant to AI/ML. The "test" here refers to verification and validation of the software feature itself and its integration into the system.

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

• Not Applicable / Not Provided: Ground truth in the context of patient data adjudicated by experts is not described for this type of submission. The "ground truth" here would relate to the functional correctness of the software and its ability to prevent apnea as designed, which is established through engineering and clinical validation rather than expert labeling of empirical patient data.

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

• Not Applicable / Not Provided: As no "test set" requiring expert adjudication is described, no adjudication method is mentioned.

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 Provided: This device is an anesthesia system with an apnea detection and response feature, not a diagnostic AI/ML tool designed to assist human readers (e.g., radiologists). Therefore, an MRMC study is irrelevant to this submission.

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

• Partially Applicable / Implicitly Done: The "Apnea Ventilation feature" is a software algorithm that operates autonomously when triggered by the absence of spontaneous breaths. The "system level qualification, and verification/validation tests" would have evaluated its standalone (algorithm-only) performance within the device infrastructure. However, specific performance metrics or a detailed description of these tests (e.g., how apnea was simulated and how the system responded) are not provided in this summary. The device's overall use involves a human operator, but the apnea feature itself is an automated response.

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

• Functional/Design Specification Ground Truth: The "ground truth" for this device's feature would be its adherence to engineering specifications for detecting apnea conditions and successfully delivering a pressure support breath as designed, and its equivalence to the functional behavior of the predicate devices. This would be established through bench testing, simulated scenarios, and potentially animal or human studies to confirm physiological response, though details are not supplied in this specific summary.

8. The sample size for the training set

• Not Applicable / Not Provided: This is a deterministic software feature, not a machine learning algorithm that requires a "training set" in the conventional sense. The "training" here would refer to software development and debugging.

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

• Not Applicable / Not Provided: As there is no "training set" for an AI/ML model, this question is not relevant. The ground truth for the device's design and function comes from established medical standards for ventilation and anesthesia, engineering principles, and the functional behavior of predicate devices.

Ask a specific question about this device

The Fabius GS is indicated as a continuous flow anesthesia system. The Fabius GS can be used for spontaneous, manually assisted, automatic or pressure support ventilation, delivery of gases and ancillaries in patients during anesthesia. Federal law restricts this device to sale by or on the order of a physician.

The modified Fabius GS is a continuous flow gas anesthesia system.

The provided text does not contain information on acceptance criteria for a device, nor does it describe a study proving a device meets such criteria. The document is a 510(k) summary for a medical device (Fabius GS Anesthesia System) establishing its substantial equivalence to a predicate device. It focuses on device description, intended use, and the regulatory process for clearance.

Therefore, I cannot fulfill your request for:

1. A table of acceptance criteria and reported device performance.
2. Sample size used for the test set and data provenance.
3. Number of experts and their qualifications for ground truth.
4. Adjudication method for the test set.
5. MRMC comparative effectiveness study details.
6. Standalone algorithm performance.
7. Type of ground truth used.
8. Sample size for the training set.
9. How ground truth for the training set was established.

Ask a specific question about this device

The AVEA is intended to provide continuous respiratory support in an institutional health care environment. It may be used on adult, pediatric, and neonatal patients. Properly trained clinical personnel, under the direction of a physician should only operate it.

The AVEA is a servo-controlled, software-driven ventilator. It has a dynamic range of breathing gas delivery that provides for neonatal through adult patients. Its user interface module provides maximum flexibility with simple operator interaction. It has a flat panel color LCD with real time charting and digital monitoring capabilities, a touch screen for interaction, membrane keys and a dial for changing settings and operating parameters. It also has an internal gas delivery system with servo controlled active inhalation and exhalation functions. The AVEA may be configured as a conventional ventilator or non-invasive positive pressure ventilator (NPPV). It has been designed to function using most commonly available accessories.

The provided text is a 510(k) summary for the AVEA Ventilator. It describes the device, its intended use, and states that performance testing and analysis verified the device meets its requirements and is substantially equivalent to legally marketed predicate devices. However, it does not contain the specific details required to complete your request: acceptance criteria, reported device performance metrics, and the specifics of a study proving those criteria were met.

Therefore, I cannot provide a table of acceptance criteria and reported device performance or details about the study, as that information is not present in the provided document.

Here's a breakdown of what can be extracted and what cannot:

A. Information NOT present in the document:

1. A table of acceptance criteria and the reported device performance: The document states "Performance testing and analysis will have verified that the AVEA Ventilator meets its performance requirements," but it does not list these specific requirements or the results.
2. Sample size used for the test set and the data provenance: Not mentioned.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable as there's no mention of a diagnostic AI component requiring ground truth from experts. The device is a ventilator.
4. Adjudication method: Not applicable.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done: Not mentioned, and generally not applicable for a device like a ventilator.
6. If a standalone study (i.e. algorithm only without human-in-the-loop performance) was done: Not mentioned, and not a typical study for a ventilator.
7. The type of ground truth used: Not applicable in the context of a ventilator's performance validation.
8. The sample size for the training set: Not applicable as no AI/algorithm training is explicitly described for a diagnostic purpose.
9. How the ground truth for the training set was established: Not applicable.

B. Information that can be inferred or stated from the document:

• Study type: The document generally refers to "Performance testing and analysis" and "Validation" which are typical for medical device clearance processes to ensure the device performs as intended and is safe and effective. It's not a diagnostic AI study.
• Purpose of the study: To demonstrate that the AVEA Ventilator meets its performance requirements and is substantially equivalent to predicate devices.
• Predicate Devices: A list of 7 predicate ventilators from Puritan Bennett, Drager, SIEMENS, Bear Medical Systems, Bird Products Corporation, and DATEX-OHMEDA is provided.

In summary, the provided 510(k) summary for the AVEA Ventilator does not contain the detailed study results, acceptance criteria, or methodological specifics typically found in a clinical study report for an AI/diagnostic device that would allow me to populate your request. It primarily focuses on the regulatory submission process and substantial equivalence to existing devices.

Ask a specific question about this device

The 840 Ventilator System with ET/Tracheostomy Tube Compensation, TC, Option is used to provide continuous ventilation to patients requiring respiratory support. This device is used for a wide range of patients from infant to adult and for a wide variety of clinical conditions.

The 840 Ventilator System is a "Continuous Ventilator", a Class II device, per 21 CFR Part 868.5895. This device is designated as Class I, Type B equipment, per IEC 601-1. The 840 Ventilator's gas delivery system consists of two proportional solenoid valves, PSOLs and an active expiratory valve. Previously cleared modes of ventilation include Assist Control, AC, Synchronized Intermittent Mandatory Ventilation, SIMV and Spontaneous, SPONT. The 840 Ventilator System supplies mandatory or spontaneous breaths with a preset level of positive end expiratory pressure, PEEP, trigger sensitivity and oxygen concentration. A mandatory breath can be either pressure or volume controlled, except in the optional BiLevel mode, when it is always pressure-controlled. A spontaneous breath type allows patient inspiratory flows of up to 200 L/min, with or without pressure support. This 840 Ventilator modification comprises the addition of a new ET/Tracheostomy Tube Compensation, "TC", feature. This feature is implemented on the 840 Ventilator through additional functionality in software and by using the existing User Interface panel. "TC" has been added as a Breath Type choice in the Touch Screen SPONT Type menu. The ventilator's pneumatic design and electrical circuitry remain functionally unchanged.

The provided text is a summary of a 510(k) submission for a medical device, the Puritan-Bennett 840 Ventilator System with ET/Tracheostomy Tube Compensation Option. This type of submission is for demonstrating substantial equivalence to a legally marketed predicate device, rather than proving that a device meets specific acceptance criteria through a clinical study in the way one might for a novel diagnostic AI.

The document does not contain information about acceptance criteria or a study designed to prove the device meets those criteria in the context of a new diagnostic algorithm. Instead, it focuses on demonstrating that the modified ventilator is substantially equivalent to existing predicate devices.

Therefore, many of the requested sections (Table of acceptance criteria, sample size for test set, number of experts for ground truth, adjudication method, MRMC study, standalone performance, type of ground truth, sample size for training set, how training ground truth was established) cannot be answered from the provided text. These are typically elements of studies designed to validate the performance of new diagnostic or predictive algorithms, which is not the primary purpose of this 510(k) submission.

The relevant information from the document pertains to the device's intended use and the regulatory pathway.

Here's a breakdown of what can be extracted based on the nature of the submission:

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

This information is not present in the provided document. The document describes the device modification and its intended use, emphasizing its substantial equivalence to predicate devices. It does not lay out specific performance acceptance criteria (e.g., accuracy, sensitivity, specificity for a diagnostic claim) or report detailed numerical performance metrics for the modified feature. The assessment in a 510(k) is about safety and effectiveness in comparison to predicates, not usually a standalone performance trial against specific numerical targets.

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 present in the provided document. The 510(k) does not describe a clinical study with a "test set" in the context of evaluating a new algorithm's performance. The review focuses on design controls, verification, and validation testing (software, etc.) to ensure the modification is safe and effective compared to predicates, but details of such testing, including sample sizes for clinical data, are not provided.

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 present in the provided document, as no such "test set" and ground truth establishment are described.

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

This information is not present in the provided document, as no such "test set" and adjudication process are 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:

This information is not present in the provided document. This type of study is relevant for AI-powered diagnostic aids, which is not the nature of this ventilator modification.

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

This information is not present in the provided document. The device is a ventilator, not an AI-only algorithm. The "TC" feature is an integrated software function.

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

This information is not present in the provided document.

8. The sample size for the training set:

This information is not present in the provided document. The "TC" feature is described as an "additional functionality in software" using the existing user interface. It's not presented as a machine learning model requiring a discrete "training set" in the common sense of AI development.

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

This information is not present in the provided document.

Summary of what is known from the document:

• Device: Puritan-Bennett 840 Ventilator System with ET/Tracheostomy Tube Compensation (TC) Option.
• Modification: Addition of a new ET/Tracheostomy Tube Compensation, "TC", feature implemented via additional software functionality using the existing User Interface.
• Regulatory Pathway: 510(k) Pre-market Notification, asserting substantial equivalence to predicate devices (Puritan-Bennett 7200 Series Ventilator and Drager Evita 4 Ventilator).
• Basis for Equivalence: The intended use, materials, and design are similar to predicate devices. The technical characteristics of the modification do not introduce new questions of safety or effectiveness. Compensation for ET/Tracheostomy Tube resistance via positive pressure support is common clinical practice.
• Software Development: Followed FDA's Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices (May 29, 1998) and internal company requirements for verification and validation testing.
• Intended Use: To provide continuous ventilation for infant, pediatric, and adult patients (tidal volume 25 - 2500 mL) requiring respiratory support in hospitals and hospital-type facilities. Not for transport between facilities or in the presence of flammable anesthetics. For use and servicing by trained and qualified clinicians/persons only, and by prescription.

Ask a specific question about this device

The 840 Ventilator System with BiLevel Option is used to provide continuous ventilation to patient's requiring respiratory support. This device is used for a wide range of patients from infant to adult and for a wide variety of clinical conditions.

The 840 Ventilator System is a Class II device, "Continuous Ventilator", per 21 CFR Part 868.5895. This device is designated a Class I Type B equipment per IEC 601-1. The 840 Ventilator's gas delivery system consists of two proportional solenoid valves (PSOLs) and an active expiratory valve. Previosly cleared modes of ventilation include Assist Control (AC), Synchronized Intermittent Mandatory Ventilation (SIMV), and Spontaneous (SPONT). The 840 Ventilator System supplies mandatory or spontaneous breaths with a preset level of positive end expiratory pressure (PEEP), trigger sensitivity, and oxygen concentration. A mandatory breath can be pressure- or volume-controlled, except in the optional BiLevel mode, when it is always pressure-controlled. A spontaneous breath mode allows the patient inspiratory flows of up to 200 L/min, with or without pressure support. The 840 Ventilator modification is the addition of two new features for this device, the BiLevel Option and Inspiratory Pause. The BiLevel mode and Inspiratory Pause features are implemented on the 840 Ventilator through additional functionality in software and by using the existing User Interface panel. "BiLevel" has been added as a mode choice in the touch screen MODE menu. The INSP PAUSE key on the user interface, is activated to perform the inspiratory pause function. The pneumatic design and the electrical circuitry (apart from the User Interface printed circuit board) has remained unchanged functionally.

This document describes a 510(k) premarket notification for the Puritan-Bennett 840 Ventilator System with a new BiLevel Option and Inspiratory Pause features. The submission focuses on demonstrating substantial equivalence to previously cleared devices rather than providing a detailed study proving the device meets specific acceptance criteria with quantifiable performance metrics.

Therefore, many of the requested sections (Table of acceptance criteria, sample size, number of experts, adjudication method, MRMC study, standalone performance, sample size for training, ground truth for training) cannot be extracted from the provided text as they are not present in this type of regulatory submission for a modification to an existing device.

Here's what can be extracted and inferred based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

This information is not explicitly provided in the document as it is a 510(k) submission for a modification to an existing device, focusing on substantial equivalence rather than primary functional performance testing against novel acceptance criteria.

The submission states: "Puritan-Bennett Corp. asserts that a) the intended use of the 840 Ventilator with BiLevel Option, as described in its labeling, has not changed from that of the cleared device, the 840 Ventilator, and b) the fundamental scientific technology of the 840 Ventilator with BiLevel Option has not changed from that of the 840 Ventilator."

It also mentions that "The BiLevel mode and Inspiratory Pause features are currently included in cleared predicate devices, providing justification for substantial equivalence." This implies that the 'acceptance criteria' are implicitly met if the device functions equivalently to these predicate devices for the new features.

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

This information is not provided in the document. The submission references "verification and validation testing, test and software quality procedures" but does not detail the size or nature of the test sets used for these activities, nor the provenance of data. This type of detail is typically internal to the company's design control documentation rather than explicitly stated in a 510(k) summary.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of Those Experts

This information is not provided in the document. The assessment described is based on engineering verification and validation against design specifications and comparison to predicate devices, not typically through expert-adjudicated ground truth as would be common for diagnostic AI algorithms.

4. Adjudication Method for the Test Set

This information is not provided in the document.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No, an MRMC comparative effectiveness study was not mentioned or relevant to this 510(k) submission. This type of study is more common for diagnostic imaging or AI devices where human reader performance is augmented or compared. The 840 Ventilator is medical equipment; the submission focuses on its functional equivalence and safety.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

This concept is not directly applicable to a ventilator. While the device contains software algorithms, the "standalone performance" is integrated into the device's overall function and directly assessed as part of its verification and validation. The submission does not describe a separate "algorithm only" performance study in the context of typical AI device evaluations.

7. The Type of Ground Truth Used

The "ground truth" for this device's performance is based on engineering specifications, functional testing against those specifications, and demonstrated equivalence to previously cleared predicate devices. For example, the device must accurately deliver a preset tidal volume or maintain a target pressure. This would be verified through direct measurement with calibrated equipment during testing, rather than through expert consensus, pathology, or outcomes data in the way these terms are typically used for diagnostic devices.

8. The Sample Size for the Training Set

This information is not provided in the document. The device's operation is based on deterministic algorithms and control systems, not learning models that require a "training set" in the machine learning sense.

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

This information is not provided in the document, as it doesn't describe a machine learning model with a training set. The "ground truth" for its development would be the fundamental principles of respiratory mechanics, engineering design standards, and pre-defined performance parameters derived from clinical requirements for ventilators.

Ask a specific question about this device