Search Results

The Primus US is indicated as a continuous flow anesthesia system. The Primus US may be used for manually assisted, or automatic ventilation, and delivery of gases, anesthetic vapor, and monitoring of; oxygen and CO2 concentration, breathing pressure, respiratory volume, and anesthetic agent identification and concentration. Federal law restricts this device to sale by or on the order of a physician.

The Primus US, is a continuous flow gas anesthesia system that delivers anesthetic vapor, provides for automatic and manual modes of ventilation, and is equipped with a monitoring system for ventilation, inspired and expired gas, and agent identification.

The acceptance criteria and summary of the study for the Primus US Anesthesia Workstation are detailed below based on the provided document.

Acceptance Criteria and Device Performance

The provided document describes a 510(k) premarket notification for the "Primus US Anesthesia Workstation." This type of submission relies on demonstrating substantial equivalence to legally marketed predicate devices, rather than establishing specific performance acceptance criteria for a new clinical study. Therefore, the "acceptance criteria" here refer to the criteria for demonstrating substantial equivalence based on comparisons to predicate devices, and "reported device performance" refers to the features and functionalities of the Primus US that align with or improve upon those of the predicates.

Study Details

The provided document describes a 510(k) premarket notification, which is primarily a regulatory submission demonstrating substantial equivalence to predicate devices. It does not contain details of a de novo clinical study with specific acceptance criteria in the typical sense (e.g., sensitivity, specificity, or reader performance metrics). Instead, the "study" referred to is the process of comparing the new device, Primus US, against several predicate devices to establish that it is as safe and effective as those already on the market.

1. Sample size 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 in the context of a 510(k) summary focused on substantial equivalence. There is no "test set" of patient data in the clinical trial sense described for this type of submission. The comparison is feature-by-feature and functionality-by-functionality against established predicate devices.
• Data Provenance: The document does not refer to clinical data. The manufacturer is Dräger Medical AG & Co KGaA, Luebeck, Germany.

2. 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. Ground truth, in the sense of clinical outcomes or expert consensus on clinical findings, is not established for this type of substantial equivalence submission. The "ground truth" implicitly relies on the established safety and effectiveness of the predicate devices.

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

• Not applicable. There is no test set or adjudication process for clinical findings described.

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

• Not applicable. This is not an AI/CADe device or an MRMC study. It is an anesthesia workstation.

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

• Not applicable. This is not an algorithm, but a medical device (anesthesia workstation).

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

• Not applicable in the sense of a clinical ground truth for a new study. The "ground truth" for this 510(k) submission is the demonstrated safety and effectiveness of the legally marketed predicate devices:
  • Fabius GS Anesthesia Workstation (K041622)
  • Julian Anesthesia Workstation (K983635)
  • Narkomed 6400 w/IPM Anesthesia Workstation (NM6400) (K033498)
  • Divan Ventilator (K980208)
  • Vamos w/ Return Sample Gas (Vamos w/ RGS) (K040847)
  • Scio patient gas monitor (K031340)

7. The sample size for the training set

• Not applicable. This is not a machine learning or AI device that requires a training set.

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

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

Summary of the "Study" (Substantial Equivalence Demonstration):

The "study" in this context is the comparison of the Primus US device to several legally marketed predicate devices based on their technological characteristics, indications for use, and performance claims. The manufacturer conducted a risk analysis, system-level qualification, and verification/validation testing to ensure the Primus US met its design specifications and performed as intended. The document highlights similarities in:

• Indications for Use: Both the Primus US and predicates are continuous flow anesthesia systems used for ventilation, gas delivery, and monitoring.
• Technological Characteristics:
  • Integrated electronic monitoring (similar to Fabius GS, Julian).
  • Gas measurement technology (same as Scio patient gas monitor).
  • User interface (similar to NM6400).
  • Battery backup system (similar to Fabius GS).
  • Electronic flow sensor technology (similar to Fabius GS).
  • Oxygen Ratio Controller (ORC) (identical to Fabius GS).
  • Ventilator (electronically controlled, electrically driven piston with fresh gas decoupling, similar to Fabius GS).
  • Integrated breathing system (similar to Fabius GS).
  • Heated breathing circuit (similar to Divan ventilator in NM6400).
  • Gas and agent delivery capabilities.
  • Anesthesia Gas Scavenger compatibility.
  • Automated pre-use checkout (similar to NM6400).
  • Vaporizer compatibility.
• Performance: The document asserts that the Primus US provides comparable functionality and safety features to the predicates. Notably, it also describes an enhancement with the addition of an inspiratory flow sensor, which improves leak detection, inspiratory valve monitoring, and trigger performance.

The FDA's review and clearance (K042607) confirm that the agency found the Primus US to be substantially equivalent to the predicate devices, thereby deeming it safe and effective for its intended use without requiring new clinical performance studies beyond the verification and validation testing performed by the manufacturer.

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 D-Vapor is an electronic calibrated vaporizer designed to enrich the fresh gas flow of an anesthesia delivery system with a controlled amount of anesthetic vapor. The D-Vapor is intended for use with Desflurane. It is not intended for use with Enflurane, Halothane, Isoflurane, or Sevoflurane or for use in a breathing circuit. Federal law restricts this device to sale by or on the order of a physician.

The D-Vapor is an electronic calibrated vaporizer designed to enrich the fresh gas flow of an anesthesia delivery system with a controlled amount of Desflurane anesthetic vapor in concentrations of 2 to 18 vol.%.

The provided document is a 510(k) premarket notification for a medical device called "D-Vapor," an anesthetic vaporizer. This type of regulatory submission in 2004 did not typically include detailed performance studies with acceptance criteria in the format requested, as it relies on demonstrating substantial equivalence to a legally marketed predicate device rather than presenting de novo clinical trial data.

Therefore, many of the requested data points (like sample sizes for test/training sets, data provenance, number of experts for ground truth, adjudication methods, MRMC studies, standalone performance, and ground truth establishment for training) are not applicable (N/A) or not provided in this type of document for this class of device at this time.

Here's an attempt to answer the questions based only on the provided text, recognizing the limitations:

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't explicitly state "acceptance criteria" in a quantitative, pass/fail manner. Instead, it describes features and functionalities that demonstrate substantial equivalence to predicate devices (Tec 6 Plus and Vapor 2000). The "performance" is implied by matching or having similar characteristics to these existing devices.

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

• Sample Size: Not specified. The submission focuses on device description and comparison to predicates, not a clinical test set.
• Data Provenance: Not applicable for a traditional "test set" in this context. The data provided describes the device's features and its relation to predicate devices.

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

• Number of Experts: Not specified. The submission does not describe a process of establishing ground truth with experts for a test set.
• Qualifications of Experts: Not specified.

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

• Adjudication Method: Not applicable. No test set requiring expert adjudication 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

• MRMC Study: No. This device is an anesthetic vaporizer, not an AI-powered diagnostic device, so an MRMC study with human readers assisting AI is not relevant or described.
• Effect Size: Not applicable.

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

• Standalone Performance: Not applicable in the context of an algorithm. The device's performance is described in terms of its mechanical and electronic functions. The device is a standalone functional unit within an anesthesia delivery system.

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

• Type of Ground Truth: Not applicable in the sense of a diagnostic or predictive algorithm. The "truth" for this device lies in its ability to accurately deliver a controlled concentration of Desflurane, as verified through engineering tests and comparison to established predicate devices. The document implies that the predicate devices' long-standing safe and effective use serves as a form of "ground truth" for the overall device category's functionality.

8. The sample size for the training set

• Sample Size for Training Set: Not applicable. This is not an AI/ML device requiring a training set.

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

• Ground Truth for Training Set: Not applicable.

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 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 Tiro is indicated as a continuous flow anesthesia system. The Fabius Tiro can be used for spontaneous, manually assisted or automatic 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 and Fabius Tiro are continuous flow gas anesthesia systems.

The compact breathing system (COSY) used with the Fabius GS (K030624) and Fabius Tiro (K031400) anesthesia systems is being modified to incorporate a heater plate. The addition of a heater plate is a hardware change only. The basic infrastructure, operating principle, alarm strategies, fault detection circuitry, and mechanical/pneumatic subassemblies within the Fabius GS/Tiro remain unchanged.

The heater consists of a heater foil, metal plate and insulator plate that are mounted between the absorber canister and COSY block. The heater subassembly is connected via a power cable to a separate power supply mounted externally to a Fabius GS/Tiro Anesthesia System.

Like the heater plate utilized in the NM6400's (K033498) Divan ventilator, the heater incorporated into the COSY is intended to warm the breathing system to minimize moisture accumulation in the breathing system components, especially during cases utilizing low flow anesthesia and/or during cases of low ambient environmental temperatures. It is not intended to control or maintain a set temperature of the patient breathing gas or to humidify the gas. Once activated, the heating plate in the COSY, like the NM6400, heats up to a constant temperature. This heat is then transferred, through conduction, to the components of the breathing system above it. In the NM6400, the heater plate is activated when the NM6400 System Power switch is turned to the "On" position and is de-activated when the NM6400 is switched to "Standby." With the COSY, heater activation is independent of the Fabius GS/Tiro. To activate the heater, the user is required to switch the heater power supply to the "On" position. To deactivate, the user is required to switch the power supply to the "Off" position.

This document describes the Fabius GS and Fabius Tiro Anesthesia Systems with a modification: the addition of a heater plate to the compact breathing system (COSY). The acceptance criteria and supporting study details are based on the provided text, which is a 510(k) premarket notification summary.

It's important to note that this document is a 510(k) summary for a hardware modification to an existing medical device, not a new, AI-powered diagnostic device. Therefore, many of the typical elements expected for AI/ML device studies (e.g., sample size for AI, ground truth establishment, MRMC studies) are not applicable here. The evaluation focuses on the safety and effectiveness of the hardware change relative to predicate devices.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria in a table format with specific performance metrics such as accuracy, sensitivity, or specificity, as would be common for diagnostic AI algorithms. Instead, the "acceptance criteria" are implied by the scope of the premarket notification: to demonstrate that the modified device remains substantially equivalent to legally marketed predicate devices and that the hardware change does not introduce new safety or effectiveness concerns.

The performance is implicitly demonstrated by the comparison to predicate devices and the completion of standard engineering verification and validation.

Study Details:

The supporting "study" is a collection of engineering tests and regulatory analyses performed to ensure the modified device (Fabius GS/Tiro with heater plate) remains safe and effective and continues to be substantially equivalent to its predicate devices.

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

• Sample Size for Test Set: This concept doesn't directly apply in the context of this 510(k) for a hardware modification. There isn't a "test set" of patient data in the way an AI/ML diagnostic algorithm would have. Instead, the "testing" involves internal engineering verification and validation of the physical device, including hazard analysis and system-level qualification. The sample size for these engineering tests would likely refer to the number of units tested, the number of test cycles, or the specific operating conditions evaluated, which are not detailed in this summary.
• Data Provenance: Not applicable in the context of patient data for an algorithm. The "data" comes from internal engineering and manufacturing records, hazard analyses, and performance testing of the device hardware.

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

Not applicable. There is no "ground truth" established by experts for a test set of data in this context. The evaluation is of hardware performance and substantial equivalence to predicate devices, not of diagnostic accuracy.

4. Adjudication Method for the Test Set

Not applicable. No expert adjudication method (like 2+1, 3+1 consensus) would be used for this type of hardware modification submission.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

No. An MRMC study is relevant for evaluating the impact of an AI algorithm on human reader performance (e.g., radiologists interpreting images). This submission is for a hardware modification to an anesthesia machine and does not involve human readers analyzing medical cases with or without AI assistance.

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

No. This device is a piece of hardware, an anesthesia machine, which inherently requires human operation and interaction for its intended use. There is no standalone "algorithm only" performance to evaluate.

7. The Type of Ground Truth Used

Not applicable in the typical sense of diagnostic algorithms (e.g., pathology, outcomes data). The "ground truth" for this submission revolves around:

• Engineering specifications and design requirements.
• Performance against established safety standards.
• Functional equivalence compared to predicate devices (e.g., the NM6400's heater plate).
• Results from internal verification and validation testing, which confirm the device meets its design intent.

8. The Sample Size for the Training Set

Not applicable. There is no AI/ML algorithm involved, and therefore no "training set" of data.

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

Not applicable, as there is no training set for an AI/ML algorithm.

Ask a specific question about this device

The Vamos Anesthetic Gas monitor is indicated for measuring and monitoring CO2 concentration, functional oxygen saturation (SPO2), pulse rate and the concentrations of N2O, Halothane, Isoflurane, Enflurane and Desflurane.

The modified Vamos is an integrated monitoring system used for the multiple gas analysis (CO2), N2O), and anesthetic agent concentrations). Pulse Oximetry may also be included as an option.

This document is a 510(k) premarket notification for the Vamos Anesthetic Gas Monitor, which is a modified version of an existing device. The notification primarily focuses on demonstrating substantial equivalence to predicate devices, particularly regarding the ability to return sample gas to the breathing circuit. It is not a study report that describes acceptance criteria, device performance results, or a detailed study design.

Therefore, many of the requested elements for describing acceptance criteria and a study that proves the device meets them cannot be found in the provided text. The document is a regulatory submission for market clearance, not a scientific publication detailing a performance study against specific acceptance criteria.

Here's what can be extracted and what cannot:

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

• Cannot be provided. The document does not specify quantitative acceptance criteria or report device performance against such criteria. It states that "Testing was performed to assure that there would be no adverse effects to the patient as a result of the sample gas passing through the Vamos and back to the breathing circuit instead of being routed to the scavenger." This is a qualitative statement about the purpose of testing, not a report of the test results themselves or the criteria used to deem them acceptable.

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

• Cannot be provided. The document does not detail any specific test set, its sample size, or data provenance.

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)

• Cannot be provided. No information about ground truth establishment or experts is included.

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

• Cannot be provided. No 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

• Cannot be provided. This device is an anesthetic gas monitor, not an AI-assisted diagnostic tool for human readers. No MRMC study or AI component is mentioned.

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

• Cannot be provided. This question is not applicable as the device is a monitor, not an algorithm, and the concept of "standalone performance" in the AI sense does not apply here.

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

• Cannot be provided. No specific ground truth methodology is mentioned. The "testing" referred to appears to be engineering or bench testing related to the gas return mechanism, not a clinical study requiring ground truth for diagnostic accuracy.

8. The sample size for the training set

• Cannot be provided. This document describes a modification to an existing device, which doesn't typically involve a "training set" in the context of machine learning or AI.

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

• Cannot be provided. See point 8.

In summary: The provided text is a regulatory submission for premarket clearance based on substantial equivalence, not a scientific or clinical study report. It focuses on the device's description, intended use, and its similarities to previously cleared devices, particularly highlighting a modification and confirming testing was done without adverse effects. It does not contain the detailed performance data, acceptance criteria, or study methodologies requested.

Ask a specific question about this device

The NM6400 w/IPM is indicated as a continuous flow anesthesia system. The NM6400 w/IPM may be used for manually assisted, or automatic ventilation, and delivery of gases, anesthetic vapor, and monitoring of; oxygen concentration, breathing pressure, respiratory volume, cardiovascular parameters, anesthetic agent identification and concentration and provides printed data. Federal law restricts this device to sale by or on the order of a physician.

The Narkomed 6400 w/ Integrated Patient Monitoring is a continuous flow gas anesthessa system with cardiovascular monitoring.

This document is a 510(k) premarket notification for a medical device called the "Narkomed 6400 w/ Integrated Patient Monitoring." It describes the device, its intended use, and claims substantial equivalence to previously marketed devices. However, it does not contain information about acceptance criteria or a study proving the device meets acceptance criteria in the way typically expected for an AI/CADe (Computer-Aided Detection/Diagnosis) device, which is what the prompt's questions are tailored for.

The Narkomed 6400 is an anesthesia workstation, a physical device, not a software algorithm that provides diagnostics or interpretations. Therefore, the concepts of "test set," "ground truth," "expert consensus," "AI assistance," or "standalone algorithm performance" are not applicable in this context.

The "Qualification of the NM6400 w/ IPM" mentioned in the document states it "included a hazard analysis and system level qualification testing." This implies standard engineering and medical device testing for safety and functional performance, but it does not detail specific performance metrics against pre-defined acceptance criteria in the format requested.

Therefore, I cannot fill in the table or answer the specific questions about acceptance criteria and study design as no such information, relevant to AI/CADe devices, is present in the provided text.

The document mainly focuses on:

• Device Description: A continuous flow gas anesthesia system with cardiovascular monitoring.
• Intended Use: For spontaneous, manually assisted, or automatic ventilation during anesthesia, delivery of gases and anesthetic vapor, and monitoring of oxygen, breathing pressure, respiratory volume, CO2, N2O, cardiovascular parameters, and anesthetic agent identification and concentration.
• Substantial Equivalence: Claims equivalence to Narkomed 6000 w/ Cardiovascular and Strip Chart Recorder Pods (K993826), Marquette SL Series Transport Remote Acquisition (TRAM) (K921669), and Solar 7000/8000 System (K993757). The key difference highlighted is the addition of Wedge Pressure information via TRAM technology and cardiac trial calculations.
• Regulatory Information: 510(k) number (K033498), classification, and FDA's determination of substantial equivalence.

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 Fabius Tiro is indicated as a continuous flow anesthesia system. The Fabius Tiro can be used for spontaneous, manually assisted or automatic 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 modified Fabius GS (Fabius Tiro) is a continuous flow gas anesthesia system.

The provided document, K031400, is a 510(k) premarket notification for the Fabius Tiro Anesthesia System. This type of submission is for demonstrating substantial equivalence to a legally marketed predicate device, rather than proving that a device meets specific performance criteria through a detailed clinical study with acceptance criteria.

Therefore, the document does not contain the information requested in your prompt regarding acceptance criteria, study details, sample sizes, expert ground truth, or MRMC studies. The content focuses on describing the device, its intended use, and the modifications from its predicate device (Fabius GS Anesthesia System) to establish substantial equivalence.

Here's why the requested information is absent based on the provided text:

• Acceptance Criteria and Device Performance: The document does not list specific measurable acceptance criteria that the Fabius Tiro had to meet. Instead, it describes modifications from a predicate device and states that "Qualification of the Fabius Tiro included a hazard analysis, system level qualification, and verification tests." However, the results or specific acceptance criteria for these tests are not detailed.
• Sample Size, Data Provenance, Ground Truth, Experts, Adjudication, MRMC, Standalone Performance: These are elements typically found in clinical studies or performance validation studies designed to establish efficacy or diagnostic accuracy. A 510(k) submission primarily relies on demonstrating that a new device is "substantially equivalent" to an existing legally marketed device, often through engineering modifications, bench testing, and comparisons to the predicate's specifications, rather than new clinical trials with human subjects.
• Training Set Size and Ground Truth for Training Set: Since this is a hardware device (anesthesia system), it doesn't involve machine learning or AI in the sense of a "training set" for an algorithm. The software changes mentioned are purely cosmetic (changing "Fabius GS" to "Fabius Tiro").

In summary, the provided document does not contain the information necessary to complete the table and answer the specific questions about acceptance criteria and a study design as typically associated with performance validation studies for AI/ML devices or novel therapies. The FDA's letter explicitly states that they have reviewed the 510(k) and determined the device is "substantially equivalent," which is the core of this type of submission.

Ask a specific question about this device

The NM-MRI-2 can be used for spontaneous, manually assisted or automatic ventilation, delivery of gases and anesthetic vapor, and monitoring oxygen concentration, breathing pressure and respiratory volume of patients during anesthesia. The NM-MRI-2 is intended for use with Dräger-Vapor® vaporizers. The NM-MRI-2 can be used in MRI scanner rooms with magnet strengths up to 3.0 tesla without distance limitations.

The Narkomed MRI-2 (NM-MRI-2) is a continuous flow gas anesthesia system.

The provided text describes a 510(k) premarket notification for the Narkomed MRI-2 Anesthesia System, focusing on expanding its indications for use in stronger MRI environments. However, it does not contain the level of detail regarding device performance metrics, study designs, sample sizes, or expert qualifications that would typically be found in a study proving a device meets specific acceptance criteria in the context of an AI/medical device performance study.

Based on the provided text, the device is an anesthesia system, not an AI or imaging diagnostic device, which explains the lack of certain types of information. The "study" here is essentially qualification testing to expand its operating environment.

Here's the information extracted and, where not available, noted as such:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size (Test Set): Not applicable in the traditional sense for an AI/diagnostic device. The "test set" here would refer to the various scenarios and conditions under which the anesthesia system was tested in a 3.0 Tesla MRI environment. The document does not specify the number of tests, specific configurations, or duration of tests performed during "qualification testing."
• Data Provenance: Not specified. This "data" would be the results of the physical and functional tests conducted in MRI environments. It is presumably prospective testing specific to the device.

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

• This is not applicable as this is a safety/performance validation of an anesthesia machine in an MRI environment, not an AI or diagnostic imaging device requiring expert interpretation for ground truth. The "ground truth" is established by physical measurements and functional checks against engineering specifications and MRI compatibility standards.

4. Adjudication method for the test set

• Not applicable for this type of device and testing. Test results would be compared directly against pre-defined engineering and safety limits, not adjudicated by human experts in the way that diagnostic image interpretations are.

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. This is not an AI-powered device nor one that involves human readers interpreting diagnostic cases.

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

• No. This is a medical device, an anesthesia system, not an algorithm. Its standalone performance is its functionality as an anesthesia machine. The qualification testing assesses its "standalone" performance within a 3.0T MRI environment.

7. The type of ground truth used

• The "ground truth" for this device's qualification testing would be derived from:
  • Physical measurements: E.g., attractive force measurements using a force gauge, magnetic field distortion measurements using specific MRI sequences/phantoms.
  • Functional tests: Verification that all device functions (ventilation, gas delivery, monitoring, alarms) operate correctly and within specifications while exposed to a 3.0T MRI field.
  • Image quality assessment: Potentially using phantoms or standard test objects to ensure the device's presence does not degrade the diagnostic quality of MRI images.
  • Hazard Analysis: The document mentions a hazard analysis, which would identify potential risks and verify mitigation.

8. The sample size for the training set

• Not applicable. This is not an AI/machine learning device that uses a "training set."

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

• Not applicable, as there is no training set.

Ask a specific question about this device