Search Results

The Virtus Metabolic Monitor is indicated for the measurement of Resting Energy Expenditure (REE) for mechanically ventilated patients, who are non-spontaneous breathing, and who are at least 18 years of age.

The Virtus Metabolic Monitor is intended to be used in Intensive Care Units (ICUs) in professional healthcare facilities only.

The Virtus Metabolic Monitor is for prescription use only.

Virtus Metabolic Monitor is a metabolic monitors designed for the measurement of resting energy expenditure (REE) for mechanically ventilated adult patients in the Intensive Care Unit (ICU).

The device is enclosed in a metal casing with a color touch screen on front for user interaction and measurement results. On the left-hand side pneumatic connections to the flow and gas sensor (Flow Sensor) and on the rear the mains power inlet, on-switch, charging indicator and USB-connector for export of results.

The Virtus Metabolic Monitor is portable and is supplied from the built-in battery or from mains, where it is automatically charged.

Here's a breakdown of the acceptance criteria and study information for the Virtus Metabolic Monitor, based on the provided text:

1. Acceptance Criteria and Reported Device Performance

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

The document describes a "side-by-side" test against the predicate device. However, the specific sample size for this test set (number of measurements, number of patients) is not provided. The data provenance (country of origin, retrospective/prospective) is also not explicitly stated. It's implied to be a testing scenario rather than a clinical study on patients, given the wording.

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

The document does not mention the use of experts to establish ground truth for this non-clinical, side-by-side comparison test. The comparison was made against the measurements of a cleared predicate device (Cosmed Q-NRG+).

4. Adjudication Method for the Test Set

Since the ground truth was established by comparison to a predicate device's measurements in a laboratory setting, there was no expert adjudication method described.

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

No, an MRMC comparative effectiveness study was not done. The described testing is a non-clinical side-by-side comparison of device measurements, not a study involving human readers or their improvement with AI assistance.

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

Yes, the described testing is a standalone performance evaluation of the Virtus Metabolic Monitor. It directly compares the device's measurements (V'O2, V'CO2, REE) against those of a predicate device in a controlled setting, without a human-in-the-loop context.

7. The Type of Ground Truth Used

The "ground truth" for the non-clinical side-by-side test was the measurements provided by the predicate device (Cosmed Q-NRG+). The study aimed to show "acceptable agreement of measurements between the subject device and the predicate device."

8. The Sample Size for the Training Set

The document does not mention any training set or related sample size. The device calculates metabolic parameters using the standard Weir formula and relies on measured V'O2 and V'CO2. There's no indication of a machine learning-based algorithm requiring a training set in this summary.

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

As no training set is mentioned or implied, the method for establishing its ground truth is not applicable.

Ask a specific question about this device

The intended use of the BEACON Caresystem is to provide

• respiratory mechanics monitoring in adult patients in the Intensive Care Unit (ICU)
• on-demand ventilator-dependent open-loop advice in mechanically ventilated adult patients as prescribed by the clinician

Patients should be hemodynamically stable.

The device is intended for use by properly trained clinicians. BEACON Caresystem is for prescription use, only.

BEACON Caresystem is an Intensive Care Unit (ICU) ventilation assist system. BEACON Caresystem will provide ICU clinicians with on-demand ventilator-dependent open-loop advice for ventilating adult patients.

BEACON Caresystem uses inputs measured by BEACON Caresystem and data inputs from the ventilator and manual data entry by the clinician into a computer program that has been designed to provide advice for changes to the ventilator settings for the individual patient undergoing mechanical ventilation.

BEACON Caresystem is an adjunct to third party legally marketed ICU mechanical ventilators.

BEACON Caresystem consists of the following components:

• BEACON Display Unit
• BEACON Gas Module
• BEACON Power Adaptor
• NONIN XPOD SpO2 Analyzer

BEACON Caresystem utilizes the following cleared accessories:

• BEACON Flow Sensor (Adult) private label version of Metaphor E-Z Flow Sensor, Size Adult [K093080]
• BEACON Water Trap (Adult) [K182075 & K171292]
• NONIN Finger Clip SpO2 sensor NONIN 8000AA1 [K071285]
• NONIN Ear Clip SpO2 sensor- NONIN 8000Q2 [K080255]
• NONIN Forehead Reflectance SpO2 sensor NONIN 8000R [K071285]

The BEACON Display Unit is a standard off-the-shelf tablet touch-screen computer. The BEACON display unit connects through a USB port to the NONIN XPOD SpO2 analyzer for pulse oximetry measurements and serial data ports for connection to the BEACON Gas Module and the connected ICU ventilator. The BEACON Display unit includes the BEACON Caresystem Software. The BEACON Gas Module performs measurement of patient airway flow and inspired and expired fractions of CO2 and O2 in the airway.

As described above, BEACON Caresystem combines the functionalities of a spirometric monitor, respiratory gas monitor, and pulse oximeter. Each of these functions, respectively, is intended for:

• Respiratory mechanics monitoring (i.e. airway flow/volume)
• Measurement of expired and inspired breathing gases (CO2, O2) and respiration rate
• Non-invasive measurement of functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate.

The BEACON Caresystem Software utilizes the monitored parameters above with data from the connected ICU ventilator and clinician entered values to generate on demand, open-loop advice for changes to the ventilator settings for an adult patient undergoing mechanical ventilation.

The BEACON Caresystem is intended to provide respiratory mechanics monitoring and on-demand ventilator-dependent open-loop advice for mechanically ventilated adult patients in the Intensive Care Unit (ICU).

Here's an analysis of the acceptance criteria and study data based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text does not explicitly state acceptance criteria in a quantifiable table with specific thresholds (e.g., accuracy > 90%). Instead, it describes a comparative approach where the BEACON Caresystem's performance is deemed "comparable" to a legally marketed predicate device.

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

The document states that five clinical studies were submitted, and these appear to form the basis of the test set for the advice generation. However, it does not explicitly state the sample size (number of patients or cases) for any of these clinical studies or for the bench tests.

The provenance of the data (country of origin, retrospective or prospective) is not explicitly stated in the provided text.

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

The information provided does not specify the number of experts used to establish ground truth for the clinical studies. For the study evaluating BEACON Caresystem advice and active clinicians, it mentions "active clinicians" but does not detail their number or specific qualifications. For the study on spontaneous breathing patients, it mentions using an "esophageal catheter" as a reference technique, implying a technical measurement rather than expert consensus for that specific ground truth.

4. Adjudication Method for the Test Set

The document does not explicitly describe any specific adjudication method (e.g., 2+1, 3+1) for establishing ground truth in the clinical studies. For the study evaluating BEACON Caresystem advice and active clinicians, it states it was evaluated "blindly," but further details on adjudication are missing.

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

The provided text does not indicate that a Multi Reader Multi Case (MRMC) comparative effectiveness study was performed to assess how much human readers improve with AI vs. without AI assistance. The clinical studies primarily focus on the agreement and appropriateness of the BEACON Caresystem's advice, not on human reader performance with or without the device. The fifth study did "evaluate blindly the BEACON Caresystem advice and active clinicians in patient cases," but it's not described as an MRMC comparative effectiveness study to measure improvement from AI assistance.

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

Yes, a standalone evaluation of the algorithm's performance (advice generation and measurement accuracy) appears to have been a significant part of the testing.

• Bench Tests: Gas and flow measurements (EtCO2, VA, RR, VO2, VCO2, EE) were evaluated in "bench test comparisons with predicate and reference devices." This suggests a standalone evaluation of the device's measurement accuracy against established standards without direct human-in-the-loop influence on the measurement results.
• Patient Simulator Test: A "head-to-head test comparing the advice presented by BEACON and the predicate device was performed on a patient simulator." This is a standalone evaluation of the advice generation algorithm.
• Clinical Studies: The clinical studies primarily assessed the advice generated by the BEACON Caresystem ("agreement of BEACON Caresystem advice," "effect of the applied advice," "ability of BEACON Caresystem advice to find appropriate breathing effort levels"), implying an evaluation of the device's output.

7. The Type of Ground Truth Used

The ground truth for different aspects of the device's performance appears to vary:

• Advice Generation: Ground truth appears to be established through:
  • Comparison with the predicate device's advice on a patient simulator.
  • "Clinical practice agreement" in three clinical studies, suggesting agreement with established medical best practices or expert clinical judgment (though details on how this was established are scarce).
  • Reference technique (esophageal catheter) for breathing effort levels in one study.
  • Comparison with "active clinicians" in patient cases in the fifth study.
• Gas and Flow Measurements: Ground truth was established by comparison with predicate and reference devices in bench tests.

8. The Sample Size for the Training Set

The provided text does not contain any information about the training set for the BEACON Caresystem software or algorithm. This document focuses on the S510(k) submission, which typically emphasizes testing of the final product rather than describing the development and training phases.

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

Since no information is provided about the training set (see point 8), there is no information on how its ground truth was established.

Ask a specific question about this device

The Aisys CS2 Anesthesia System is intended to provide general inhalation anesthesia and ventilatory support to a wide ride range of patients (neonatal, pediatric, adult). The device is intended for volume or pressure control ventilation.

The GE Datex-Ohmeda Aisys CS2 is intended to provide general inhalation anesthesia and ventilatory support to a wide range of patients (neonatal, pediatric, adult). It represents one of the systems in a long line of products based on the Datex-Ohmeda Excel, Aestiva, Aespire, and Avance Anesthesia Systems. It is to be used only by trained and qualified medical professionals.

The Aisys CS2 supplies set flows of medical gases to the breathing system using electronic gas mixing. Interfaces to control the system include the touch screen, keypad and rotary controller on the main display unit. Selected gas flows are displayed as electronic flow indicators on the system display unit. The Aisys CS2 is equipped with a pneumatic back-up O2 delivery system and traditional flow tube, as well. A large selection of frames, gases, and vaporizer cassettes are available to give the user control of the system configuration. The Aisys CS4 systems are also available in pendant models. The system shall support a maximum of two-cylinder supply connections mounted inboard on the machine and supported by cylinder yokes. All models have O2. The Aisys CS2 comes with up to two optional gases (air, N20). Safety features and devices within the Aisys CS2 are designed to decrease the risk of hypoxic mixtures, agent mixtures and complete power or sudden gas supply failures. The Aisys CS2 system is available with optional integrated respiratory gas monitoring. When supplied as an option, the integrated respiratory gas monitoring is provided via the CARESCAPE Modules cleared via K123195 (E-sCAiO, EsCAiOV) and K150245 (E-sCAiOVX). The Aisys CS2 is also compatible with legacy M-Gas and E-Gas modules which are in the installed base but are no longer in forward production (M-CAiO and M-CAiOV cleared via K001814, and E-CAiOVX cleared via K051092).

The above modules can be physically integrated into the Anesthesia device, receive electronic power from the said device and communicate measured values to the said device for display on the system display unit.

The anesthetic agent delivery for the Aisys CS2 is controlled via an anesthesia computer through user input from the central display. The vaporization technology is based upon the electronic vaporizer cleared as part of the Datex-Ohmeda Anesthesia Delivery Unit (ADU) cleared via K973985. An Aladin 2 is inserted into the active cassette bay. The cassette holds the agent to be delivered - Isoflurane, Desflurane or Sevoflurane. Agent is delivered as a percent volume/volume. The Aisys CS2 is designed to allow only one active cassette at a time. Per the user input into the main display, valves within the active cassette bay will open and allow agent to be delivered. The agent is mixed with gas from the FGC unit. After mixing, the combination of gases and agent is delivered to the breathing system and then onto the patient.

The Datex-Ohmeda 7900 Anesthesia Ventilator is used in the Aisys CS2. It is a microprocessor based, electronically controlled, pneumatically driven ventilator that provides patient ventilation during surgical procedures. The 7900 ventilator is equipped with a built-in monitoring system for inspired oxygen, airway pressure and exhaled volume. Sensors in the breathing circuit are used to control and monitor patient ventilation as well as measure inspired oxygen concentration. This allows for the compensation of compression losses, fresh gas contribution and small leakage in the breathing absorber, bellows and system. User setting and microprocessor calculations control breathing patterns. The user interface keeps settings in memory. The user may change settings with a simple and secure setting sequence. A bellows contains breathing gasses to be delivered to the patient. Positive End Expiratory Pressure (PEEP) is regulated electronically. Positive pressure is maintained in the breathing system so that any leakage that occurs is outward. An RS-232 serial digital communications port connects to and communicates with external devices.

Ventilator modes for the device include Volume Control (VCV) Mode, Pressure Control (PCV) Mode (Optional), Synchronized Intermittent Mandatory Ventilation with Pressure Control Ventilation -Volume Guaranteed (SIMV/PCV-VG) Mode, Synchronized Intermittent Mandatory Ventilation with Pressure Support Ventilation (SIMV/PSV) Mode, Pressure Support with Apnea Backup (PSVPro) Mode (Optional), Synchronized Intermittent Mandatory Ventilation with Pressure Control (SIMV-PC) Mode (Optional), Pressure Control Ventilation- Volume Guaranteed (PCV-VG) mode (Optional), and Continuous Positive Airway Pressure/ Pressure Support Ventilation (CPAP-PSV).

Ventilator parameters and measurements are displayed on the system display unit.

The system display unit is mounted to an arm on the top shelf of the Aisys CS2. The arm is counter balanced and capable of moving vertically and/or horizontally, and tilting the display, enabling the user to position the display to the most advantageous viewing position. The arm length is limited such that the display position is always within the footprint of the Aisys CS2 frame. The arm also supports the mounting of additional display units for a variety of patient monitors.

Several frame configurations are available, including one that allows for the physical integration of the GE Monitors (cleared Carescape B850 via K092027 and B650 cleared on K102239). This configuration also provides cable management solutions such that the necessary connections from the monitor display unit to the monitor are hidden within the Aisys CS2 frame. An additional option allows the monitor to be linked to the power supply of the Aisys CS2 such that when the Aisys CS2 is turned on, the monitor is also turned on. Additional configurations allow for the mounting of various patient monitors on the top shelf of the Aisys CS2.

This document is a 510(k) premarket notification for the Aisys CS2 anesthesia system (version 11). It primarily focuses on demonstrating substantial equivalence to a predicate device (Aisys CS2 version 10) through non-clinical testing. Therefore, it does not contain the detailed information about acceptance criteria and a study that proves the device meets those criteria in the way typically found for a diagnostic or AI-driven device.

Based on the provided text, here's a breakdown of what is and is not available:

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

No explicit table of acceptance criteria and reported device performance in terms of diagnostic metrics (e.g., sensitivity, specificity, AUC) is provided. This is because the submission is for an anesthesia system, and the "performance" is related to its functional capabilities and compliance with safety standards, rather than a diagnostic accuracy.

The document lists various verification tests and what they verify. For example:

• Privacy and Security: Verifies functionality including an option to disable viewing patient identifiable information.
• Duplicate Interface Detection: Verifies functionality including that the system continues communication with its clients even if a duplicate IP condition is detected.
• Ethernet Interface: Verifies functionality including that the system supports 100Mbps speed and full duplex settings.
• Network Hazard Mitigation: Verifies that the system has no open ports except for specific clients.
• Network Requirements: Verifies that the system supports clock synchronization with a network device.
• Sapphire and HL7: Verifies communication protocols.
• Address Resolution Protocol Requirements: Verifies correct system subnet mask functionality.
• Respiratory Gas Monitors: Verifies all requirements related to Respiratory Gas Monitors, including functionality of the Sample Gas Return option.
• Monitoring Only Mode: Verifies functionality including O2 being administered through the auxiliary O2 port when the mode is enabled.
• System Hazard Mitigations: Verifies functionality including that the system performs as intended during a recovery state.
• Materials Testing: Includes Volatile Organic Compounds, Particulate Matter Testing, Bacterial Filter Efficiency Testing, Viral Filter Efficiency Testing.
• Reprocessing Instructions Validation Testing
• Verification testing for electrical safety and electromagnetic compatibility: Compliance to AAMI / ANSI ES60601-1:2005/(R)2012, IEC 60601-1-2: 2014, and ISO 80601-2-13: 2011.

For each of these, the implicit "acceptance criterion" is that the system successfully performs or complies with the stated function or standard. The "reported device performance" is the conclusion that these tests were passed and the system is safe and effective.

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 / not provided for this type of submission. This device is an anesthesia machine, not typically tested with "test sets" of patient data in the same way an AI diagnostic device would be. The testing described is functional and safety verification.

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 / not provided. There is no "ground truth" establishment in the context of diagnostic accuracy for this device. Ground truth is usually relevant for AI/ML models being validated against expert-labeled data.

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

This information is not applicable / not provided. Adjudication methods are used to resolve discrepancies in expert labeling for ground truth, which is not relevant here.

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 / not provided. This is an anesthesia machine, not an AI-assisted diagnostic tool for human "readers" (e.g., radiologists interpreting images). An MRMC study would not be relevant for its evaluation.

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

This information is not applicable / not provided. This is an anesthesia machine. While it contains software, it is not a standalone AI algorithm in the diagnostic sense. It is a system intended for use by trained medical professionals. The software updates mentioned are for standards compliance and usability enhancements, not for independent diagnostic decisions.

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

This information is not applicable / not provided. As explained, there is no "ground truth" akin to diagnostic accuracy for this device. The "ground truth" for its performance is its ability to meet engineering specifications, safety standards, and functional requirements.

8. The sample size for the training set

This information is not applicable / not provided. This device is not an AI/ML model that would have a "training set" of data in the typical sense. The software updates are developed and verified through standard software engineering practices.

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

This information is not applicable / not provided. As there is no training set for an AI/ML model, the concept of establishing ground truth for it does not apply.

In summary, the provided document is a 510(k) summary for an anesthesia system. The "study" proving it meets acceptance criteria consists of a comprehensive set of non-clinical verification and validation tests covering:

• Software validation (including enhancements like EcoFlow improvements, Monitory Only mode, Network Connectivity, Privacy and Security, etc.)
• Compliance with electrical safety, EMC, and specific medical device standards (e.g., IEC 60601-1, ISO 80601-2-13).
• Materials testing.
• Risk analysis and design reviews.

The acceptance criteria are implicitly that the system functions as intended, meets its specifications, and complies with all relevant safety and performance standards. The "study" is the extensive report of these non-clinical tests, and the conclusion is that the modified device is substantially equivalent to its predicate. Clinical testing was not deemed necessary for the changes introduced in version 11.

Ask a specific question about this device

The CARESCAPE R860 ventilator is designed to provide mechanical ventilation or support to neonatal, pediatric, and adult patients weighing 0.25 kg and above. The CARESCAPE R860 ventilator is a microprocessor based, electronically controlled, pneumatically driven ventilator that includes integrated monitoring of FiO2, airway pressure, flow, and volume.
Additional respiratory gas monitoring capabilities are supported through the use of optional GE patient monitoring modules.
Not all features are available for all patient types or product configurations.
The CARESCAPE R860 ventilator is not a pulmonary function calculation device.
The system is designed for facility use, including within-facility transport, and should only be used under the orders of a clinician.

The CARESCAPE R860 is a flexible, adaptable, intuitive critical care ventilator. Touchscreen capability allows the user to quickly and easily access patient information and procedures. A wide selection of performance options gives the user full control of the system configuration. The CARESCAPE R860 features patient monitoring, patient ventilation, and the capability of interfacing with central information management systems.
The CARESCAPE R860 is designed to provide mechanical ventilation for adult, pediatric and neonatal patient types weighing 0.25 kg and above, and having degrees of pulmonary impairment varying from minor to severe.
The CARESCAPE R860 introduces a new user interface with touch screen capabilities. Icons represent configurable views of past (historical trends), present (patient status), and possible future patient needs through clinical decision support, including Spontaneous Breathing Trial to evaluate a patient's ability to breath spontaneously for a limited, specified duration of time.
This ventilator comes with standard ventilation modes as well as purchasable ventilation modes and clinical decision support features.
Standard ventilation modes:

• A/C VC (Assist Control Volume Control) .
• A/C PC (Assist Control Pressure Control) .
• A/C PRVC (Assist Control Pressure Regulated Volume Control)
• SIMV VC (Synchronized Intermittent Mandatory Ventilation Volume Control) ●
• SIMV PC (Synchronized Intermittent Mandatory Ventilation Pressure Control)
• CPAP/PS (Continuous Positive Airway Pressure/Pressure Support)
• SBT (Spontaneous Breathing Trial) .
  Purchasable ventilation modes:
• . nCPAP (nasal Continuous Positive Airway Pressure)
• . SIMV PRVC (Synchronized Intermittent Mandatory Ventilation Pressure Regulated Volume Control)
• . BiLevel
• . BiLevel VG (BiLevel airway pressure ventilation Volume Guaranteed)
• VS (Volume Support) ●
• NIV (Non-Invasive Ventilation) .
• . APRV (Airway Pressure Release Ventilation)
  Additional features:
• . FRC (Functional Residual Capacity)
• . SpiroDynamics
  The CARESCAPE R860 is based on the Engström Carestation feature set and contains similar performance characteristics to the Engström family of ventilators.
  The CARESCAPE R860 is a microprocessor-based, pneumatically controlled, data driven ventilator which includes integrated FiO2, airway pressure, spirometry and volume monitoring and an Aerogen Aeroneb nebulizer control board. The ventilator consists of two main components: the display and the ventilator unit. The display allows the user to interface with the system through a resistive touch screen and Trim Knob with keys. The CARESCAPE R860 also includes an optional module bay which allows the integration of various Datex-Ohmeda patient monitoring modules with the ventilator.
  The user interface for control of nebulization is provided via the ventilator display unit. The standard nebulizer board is provided with the CARESCAPE R860. Users have the option to configure the system to use an external pneumatic nebulizer in place of the standard nebulizer.
  Optional accessories common to the CARESCAPE R860 and the predicate Engström family of ventilators include a trolley/cart, integrated air compressor, support arm, humidifier and water trap mounting brackets. Additional optional accessories include airway modules, intratracheal pressure sensor, auxiliary electrical outlets, adjustable mounting rail, nebulizer and components, and module bay.
  The optional medical air compressor is intended for use as an accessory to provide a dry, filtered, breathable compressed air supply. The compressor is installed in the base of the ventilator cart. The compressor is powered from AC mains only. A source of compressed oxygen is required to be connected to ventilator equipped with the optional compressor. The use of an integrated air compressor was first cleared on the predicate Engström Carestation and Engström Pro in K050597.
  Optional functionality includes integrated respiratory gas monitoring, capabilities to measure SpiroDynamics via a GE supplied intratracheal pressure sensor in patients using sized 6.5 tracheal tubes and larger, and calculation of functional residual capacity of mechanically ventilated patients using Nitrogen Wash In/Wash Out method. The integrated respiratory gas monitoring is provided via the Datex-Ohmeda Gas Modules, E-CO, E-COV, E-COVX, E-CAiO, E-CAiOV, E-CAiOVX (K051092), E-MiniC module (K052582), or E-sCO, E-sCOV, E-sCAiO, E-sCAiOV (K123195) which are physically integrated into the CARESCAPE R860, receive electronic power from the CARESCAPE R860 and communicate measured values to the CARESCAPE R860 for display on the system display unit.

This document, a 510(k) Pre-market Notification, describes the CARESCAPE R860 ventilator and asserts its substantial equivalence to a predicate device, the Engström Carestation.

Based on the provided text, the CARESCAPE R860 device is a ventilator, not an AI/ML powered device designed to meet specific performance criteria based on an AI model's output. Therefore, many of the requested criteria regarding AI model evaluation (like sample sizes for test sets, number of experts for ground truth, adjudication methods, MRMC studies, standalone performance, training set details, or type of ground truth) are not applicable (N/A) in this context.

The document primarily focuses on demonstrating the device's adherence to regulatory standards and its functional equivalence to a previously cleared device through non-clinical testing.

Here's the information extracted and filled out based on your request:

1. Table of Acceptance Criteria and Reported Device Performance

Given that this is a ventilator and not an AI/ML diagnostic or predictive device, the "acceptance criteria" are related to compliance with medical device standards and functional equivalence to a predicate, rather than specific performance metrics like sensitivity or specificity for an AI model.

2. 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: N/A (No specific "test set" in the context of AI/ML evaluation is mentioned. The testing involved functional verification and validation of a medical device against engineering specifications and regulatory standards.)
• Data Provenance: N/A (The testing performed is non-clinical, involving the device itself rather than patient data.)

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)

• Number of Experts: N/A
• Qualifications of Experts: N/A
  • Explanation: Ground truth in this context refers to the correct functioning of the ventilator according to engineering specifications and regulatory standards. This is typically established through engineering and quality assurance processes, not by expert medical review of output data.

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

• Adjudication Method: N/A

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 Done: No.
• Effect Size: N/A
  • Explanation: This is not an AI-assisted diagnostic device, so MRMC studies are not relevant.

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

• Standalone Performance: N/A
  • Explanation: This device is a ventilator, performing mechanical functions. While it has software, it's not an AI algorithm in the sense of making diagnostic or treatment recommendations that would have a standalone performance evaluated against a ground truth. Its "performance" is its ability to deliver ventilation parameters accurately and safely.

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

• Type of Ground Truth: Engineering specifications, regulatory standards (e.g., ISO 80601-2-12 for medical ventilators), and performance characteristics of the predicate device (Engström Carestation). The "ground truth" is the established correct mechanical and software operation within specified tolerances.

8. The sample size for the training set

• Sample Size for Training Set: N/A (No AI model training involved.)

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

• How Ground Truth Established: N/A (No AI model training involved.)

Ask a specific question about this device

The GE Datex-Ohmeda Engström Carestation and Engström Pro are designed to provide mechanical ventilation for adults and pediatrics weighing 5kg and above having degrees of pulmonary impairment varying from minor to severe. Optional Neonatal capabilities on Engström Carestation and Engström Pro expand the patient range to 0.25 kg.

The GE Datex-Ohmeda Engström Carestation and Engström Pro are microprocessor based, electronically controlled, pneumatically driven ventilators that include integrated FiO2, airway pressure, spirometry, and volume monitoring. Options include an Aerogen Aeroneb nebulizer, data capture accessory, and an integrated air compressor. Options available on Engström Carestation only include integrated respiratory gas monitoring capabilities via various Datex-Ohmeda patient monitoring modules listed in the product labeling, capabilities to measure SpiroDynamics via an intratracheal pressure sensor in patients using sized 6.5 tracheal tubes and larger, and calculation of functional residual capacity of mechanically ventilated patients using Nitrogen Wash In/Wash Out method.

Not all features are available with all patient populations.

The Engström Carestation is not a pulmonary function calculation device.

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

The GE Datex-Ohmeda Engström Carestation and Engström Pro are flexible, and intuitive, critical care ventilators. A wide selection of performance options gives the user full control of the system configuration. The Engström Carestation and Engström Pro feature patient monitoring, patient ventilation, and the capability of interfacing with central information management systems.

Both the GE Datex-Ohmeda Engström Carestation and Engström Pro are designed to provide mechanical ventilation for adults and pediatrics weighing 5kg and above having degrees of pulmonary impairment varying from minor to severe. Optional Neonatal capabilities allow the Engström Carestation and Engström Pro to be used with patients weighing 0.25 kg and above.

The modes of ventilation currently available include:

1. Volume Controlled (VCV)
2. Pressure Controlled (PCV)
3. Pressure Controlled, Volume Guaranteed (PCV-VG)
4. Synchronized Intermittent Mandatory Ventilation, Volume Controlled (SIMV-VC)
5. Synchronized Intermittent Mandatory Ventilation, Pressure Controlled (SIMV-PC)
6. Synchronized Intermittent Mandatory Ventilation, Pressure Controlled Volume Guarantee (SIMV-PCVG)
7. Bi-level Airway Pressure Ventilation
8. Constant Positive Airway Pressure Support Ventilation (CPAP/PSV)
9. Apnea backup (available in SIMV-VC, SIMV-PC, SIMV-PCVG/BiLevel-VG, BiLevel, CPAP/PSV, and VG-PS)
10. Non-invasive ventilation (NIV), not available in neonatal mode
11. Infant Nasal CPAP (nCPAP), only available in neonatal mode
12. Volume Guarantee. Pressure Support (VG-PS), only available in neonatal mode

The GE Datex-Ohmeda Engström Carestation and Engström Pro are microprocessor based, electronically controlled, pneumatically driven ventilators that include integrated FiO2, airway pressure, spirometry and volume monitoring and an Aerogen Aeroneb Pro nebulizer control board.

The ventilator consists of two main components: a display and a ventilator unit. The display allows the user to interface with the system and control settings through use of soft keys on the display, a com wheel, and a resistive touch screen. The Engström Carestation also includes a module bay that allows the integration of various Datex-Ohmeda patient monitoring modules with the ventilator.

The user interface for control of nebulization is provided via the ventilator display unit. The standard nebulizer board is provided with both the Engström Carestation and Engström Pro variants. Users have the option to configure the system to use an external pneumatic nebulizer in place of the standard nebulizer.

The optional medical air compressor is intended for use as an accessory to provide a dry, filtered, breathable compressed air supply. The compressor is installed in the base of the ventilator cart. The compressor is powered from AC mains only. A source of compressed oxygen is required to be connected to Engström Carestation/Engström Pro equipped with the optional compressor. The use of an integrated air compressor was first cleared in K050597.

Optional accessories common to both Engström Carestation and Engström Pro include a trolley/cart, integrated air compressor, support arm, humidifier and water trap mounting brackets, and a data capture accessory. Additional optional accessories specific to the Engström Carestation include airway modules, intratracheal pressure sensor, auxiliary electrical outlets, and module bay. Optional functionality specific to the Engström Carestation includes integrated respiratory gas monitoring, capabilities to measure SpiroDynamics via a GE supplied intratracheal pressure sensor in patients using sized 6.5 tracheal tubes and larger, and calculation of functional residual capacity of mechanically ventilated patients using Nitrogen Wash In/Wash Out method. The integrated respiratory gas monitoring is provided via the Datex-Ohmeda Gas Modules, M-C. M-COV. M-COVX, M-CaiO, M-CAiOV, M-CAiOVX, rev 3.2 software and higher (K001814), E-CO, E-COV, E-COVX, E-CAiO, E-CAiOV, E-CAiOVX (K051092), or M-Mini-CO2 Module (K023454) or E-MiniC module (K052582) which are physically integrated into the Engström Carestation, receive electronic power from the Engström Carestation and communicate measured values to the Engström Carestation for display on the system display unit.

Here's an analysis of the provided text regarding the acceptance criteria and study for the GE Datex-Ohmeda Engström Carestation and Engström Pro ventilators.

This 510(k) submission (K140575) is primarily for the addition of an alternate integrated air compressor (EVair) to the existing GE Datex-Ohmeda Engström Carestation and Engström Pro ventilators, which were previously cleared under K111116. The submission states "There have been no changes to the intended use or fundamental scientific technology." and "The addition of the alternate compressor, EVair, does not affect the safe or effective use of the ventilator as the compressor interfaces with the ventilator in the same manner, and performs in an equivalent manner. There is no change to the Engstrom performance as a result of this change." Consequently, the acceptance criteria and studies focus specifically on the new compressor and its functional equivalence, rather than a broad re-evaluation of the entire ventilator system.

1. Table of Acceptance Criteria and Reported Device Performance

Given the nature of this 510(k) (adding an alternate component), the acceptance criteria are framed around functional equivalence and safety of the new EVair compressor compared to the predicate EVair03.

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

The provided document describes nonclinical testing only.

• Sample Size: The document does not specify a quantitative "sample size" in terms of units tested for the compressor, nor does it refer to patient data. Testing appears to be on developmental units of the EVair compressor integrated with the Engström ventilators.
• Data Provenance: The testing was "nonclinical," meaning it did not involve human patients. It was conducted by the manufacturer, Datex-Ohmeda, Inc. (GE Healthcare). There is no mention of country of origin for specific test data, but the company is based in Madison, WI, USA. The testing is prospective in the sense that it evaluates a newly designed component (EVair compressor) before its market release.

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

• The concept of "ground truth established by experts" is not directly applicable here as this is a nonclinical engineering and functional equivalence study for a medical device component.
• The ground truth for this type of evaluation is typically defined by engineering specifications, regulatory standards (e.g., ISO, IEC for medical electrical equipment), and the performance characteristics of the legally marketed predicate device.
• The "experts" involved would be the manufacturer's engineers, quality assurance personnel, and regulatory specialists who designed, tested, and evaluated the device against these objective criteria. Their qualifications would stem from their professional expertise in medical device development, testing, and regulatory requirements.

4. Adjudication Method for the Test Set

• Adjudication methods like "2+1" or "3+1" are typically used in clinical studies involving human observers (e.g., radiologists interpreting images) where consensus or a tie-breaking mechanism is needed to establish a "true" label.
• This submission describes nonclinical engineering testing. Therefore, such adjudication methods are not applicable. The results of the tests (e.g., pressure measurements, acoustic levels, vibration, thermal performance, software function) are objective, quantitative data compared against predefined specifications and predicate performance.

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

• No, an MRMC comparative effectiveness study was not done.
• MRMC studies are clinical studies designed to evaluate the diagnostic performance of human readers, often comparing performance with and without an AI-assisted device.
• This 510(k) submission is for an alternate component (air compressor) of a ventilator, not a diagnostic AI device. The submission explicitly states: "The modifications made to the Engström ventilator did not require clinical testing."

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

• This question is framed for AI/algorithm-based devices. The Engström Carestation and Engström Pro are physical medical devices (ventilators) with microprocessor control, not standalone AI algorithms.
• The "standalone performance" of the EVair compressor itself was evaluated during its design and verification to meet engineering specifications (acoustics, vibration, thermal dissipation) and then its integrated performance with the ventilator system was verified. This can be considered the equivalent of a "standalone" functional test for the component.

7. The Type of Ground Truth Used

• For this nonclinical submission, the ground truth is based on:
  • Engineering Specifications: Detailed technical requirements for component performance (e.g., pressure ranges, flow rates, alarm thresholds, acoustic limits, vibration levels, thermal profiles).
  • Regulatory Standards: Compliance with relevant national and international standards for medical devices, particularly continuous ventilators (e.g., 21 CFR 868.5895, ISO, IEC standards).
  • Predicate Device Performance: The demonstrated safe and effective performance of the previously cleared predicate device (Engstrom Ventilator K111116 and its EVair03 compressor). The new EVair compressor was evaluated against the functional performance of the EVair03.

8. The Sample Size for the Training Set

• This question is relevant for machine learning or AI models.
• Not applicable. This submission is for a physical medical device and its component, not an AI model requiring a training set.

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

• Not applicable, as there is no training set for an AI model in this submission.

Ask a specific question about this device

The GE Datex-Ohmeda Aisys CS2 Anesthesia System is intended to provide general inhalation anesthesia and ventilatory support to a wide range of patients (neonatal, pediatric, adult). The device is intended for volume or pressure control ventilation.

The GE Datex-Ohmeda Aisys CS2 is intended to provide general inhalation anesthesia and ventilatory support to a wide range of patients (neonatal, pediatric, adult). It represents one of the systems in a long line of products based on the Datex-Ohmeda Excel, Aestiva, Aespire, Aisys, and Avance Anesthesia Systems. It is to be used only by trained and qualified medical professionals. The Aisys CS2 supplies set flows of medical gases to the breathing system using electronic gas mixing. Interfaces to control the system include the touch screen, keypad and rotary controller on the main display unit. Selected gas flows are displayed as electronic flow indicators on the system display unit. The Aisys is equipped with a pneumatic back-up O2 delivery system and traditional flow tube, as well. A large selection of frames, gases, and vaporizer cassettes are available to give the user control of the system configuration. The Aisys CS systems are also available in pendant models. The system shall support a maximum of two-cylinder supply connections mounted inboard on the machine and supported by cylinder yokes. All models have O2. The Aisys CS comes with up to two optional gases (air, N2O). Safety features and devices within the Aisys are designed to decrease the risk of hypoxic mixtures and complete power or sudden gas supply failures. The Aisys CS system is available with optional integrated respiratory gas monitoring. When supplied as an option, the integrated respiratory gas monitoring is provided via the Datex-Ohmeda M-Gas Module (M-CAiO and M-CAiOV software revision 3.2 and above cleared via K001814) and E-Gas Module (E-CAiOVX software revision 4.5 and above cleared via K051092). CARESCAPE Modules are also available for Aisys CS' (EsCAiO, E-sCAiOV cleared via K123195). The above modules can be physically integrated into the Anesthesia device, receive electronic power from the said device and communicate measured values to the said device for display on the system display unit. The anesthetic agent delivery for the Aisys CS2 is controlled via an anesthesia computer through user input from the central display. The vaporization technology is based upon the electronic vaporizer cleared as part of the Datex-Ohmeda Anesthesia Delivery Unit (ADU) cleared via K973985. An Aladin cassette (also cleared as part of K973895) or Aladin, is inserted into the active cassette bay. The cassette holds the agent to be delivered - Halothane. Enflurane. Isoflurane. Desflurane or Sevoflurane. Agent is delivered as a percent volume/volume. The Aisys is designed to allow only one active cassette at a time. Per the user input into the main display, valves within the active cassette bay will open and allow agent to be delivered. The agent is mixed with gas from the FGC unit. After mixing, the combination of gases and agent is delivered to the breathing system and then onto the patient. The Datex-Ohmeda 7900 Anesthesia Ventilator is used in the Aisys Anesthesia System. It is a microprocessor based, electronically controlled, pneumatically driven ventilator that provides patient ventilation during surgical procedures. The 7900 ventilator is equipped with a built-in monitoring system for inspired oxygen, airway pressure and exhaled volume. Sensors in the breathing circuit are used to control and monitor patient ventilation as well as measure inspired oxygen concentration. This allows for the compensation of compression losses, fresh gas contribution and small leakage in the breathing absorber, bellows and system. User setting and microprocessor calculations control breathing patterns. The user interface keeps settings in memory. The user may change settings with a simple and secure setting sequence. A bellows contains breathing gasses to be delivered to the patient. Positive End Expiratory Pressure (PEEP) is regulated electronically. Positive pressure is maintained in the breathing system so that any leakage that occurs is outward. An RS-232 serial digital communications port connects to and communicates with external devices. Ventilator modes for the device include Volume Mode, Pressure Control Mode, Pressure Support with Apnea Backup Mode (Optional) and Synchronized Intermittent Mandatory Ventilation (SIMV) Mode (Optional) and Continuous Positive Airway Pressure / Pressure Support Ventilation (CPAP/PSV) Mode (Optional). Aisys CS2 also supports optional Pressure Control Ventilation - Volume Guarantee mode with spontaneous breath pressure support (SIMV PCV-VG) mode (Optional). Ventilator parameters and measurements are displayed on the system display unit. The system display unit is mounted to an arm on the top shelf of the Aisys CS. The arm is counter balanced and capable of moving vertically and/or horizontally, and also tilting the display, enabling the user to position the display to the most advantageous viewing position. The arm length is limited such that the display position is always within the footprint of the Aisys CS2 frame. The arm also supports the mounting of additional display units for a variety of patient monitors. Several frame configurations are available, including one that allows for the physical integration of the GE Monitors (cleared Carescape B850 via K092027 and B650 cleared on K102239). This configuration also provides cable management solutions such that the necessary connections from the monitor display unit to the monitor are hidden within the Aisys CS frame. An additional option allows the monitor to be linked to the power supply of the Aisys CS2 such that when the Aisys CS2 is turned on, the monitor is also turned on. Additional configurations allow for the mounting of various patient monitors on the top shelf of the Aisys CS.

The provided text is for a 510(k) Premarket Notification for the GE Datex-Ohmeda Aisys CS2 Anesthesia System. This document describes a new version of an already marketed device and focuses on demonstrating substantial equivalence to the predicate device (GE Datex-Ohmeda Aisys, K110213).

Therefore, the document does not contain the kind of acceptance criteria, study details (like sample sizes, expert qualifications, adjudication methods), or performance metrics associated with a de novo device or a groundbreaking algorithmic performance study. Instead, the focus is on verification and validation of changes relative to a predicate device.

Here's an analysis based on the information available in the provided text, and explicit statements about what is not available due to the nature of this submission:

Acceptance Criteria and Device Performance

The document does not specify quantitative acceptance criteria or numerical performance metrics in the way one would for an AI/algorithm-driven diagnostic device. Instead, the acceptance is based on demonstrating that the updated device continues to meet its specifications and performs as safely and effectively as the predicate device.

The study that "proves" the device meets acceptance criteria is a series of non-clinical tests.

1. Table of acceptance criteria and the reported device performance:

Study Details

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

• Test Set Sample Size: Not applicable/not specified in the context of this 510(k) submission. There isn't a "test set" in the sense of a medical image or patient data set used for algorithmic evaluation. The testing involved various engineering and software validation tests.
• Data Provenance: Not applicable. The testing was non-clinical (e.g., in-house verification and validation).

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

• Number of Experts: Not applicable. Ground truth, in the context of an anesthesia machine, would refer to its functional correctness, safety, and performance according to engineering specifications and regulatory standards, not expert interpretation of medical data.
• Qualifications of Experts: Not applicable. The "ground truth" was established by engineering specifications, regulatory standards, and internal quality assurance processes.

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

• Adjudication Method: Not applicable. This concept is typically relevant for studies involving human interpretation or clinical endpoints, not for the engineering verification and validation of an anesthesia system.

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

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 anesthesia system as a "standalone algorithm" performance. The device's performance was evaluated through non-clinical verification and validation testing of its hardware and software functions (e.g., gas mixing, ventilation modes, display accuracy, safety features).

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

• Type of Ground Truth: The ground truth for this device's evaluation was based on engineering specifications, regulatory standards compliance, and internal quality assurance requirements. This includes:
  • Functional requirements (e.g., gas flow rates, ventilation parameters).
  • Safety requirements (e.g., hypoxic mixture prevention, alarm accuracy).
  • Performance requirements (e.g., display accuracy, response times).
  • Compliance with voluntary standards.

8. The sample size for the training set:

• Training Set Sample Size: Not applicable. This device is an anesthesia system developed through traditional engineering and software development processes, not an AI/machine learning model that requires a "training set" of data.

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

• Ground Truth for Training Set: Not applicable. There is no "training set" in the context of this device's development.

Ask a specific question about this device

The GE Datex-Ohmeda Avance CS2 Anesthesia System is intended to provide general inhalation anesthesia and ventilatory support to a wide range of patients (neonatal, pediatric, adult). The device is intended for volume or pressure control ventilation.

The GE Datex-Ohmeda Avance CS2 anesthesia machines are intended to provide general inhalation anesthesia and ventilatory support to a wide range of patients (neonatal, pediatric, adult). They represent one of the systems in a long line of products based on the Datex-Ohmeda Excel. Aestiva, and Aespire Anesthesia Systems. Avance systems are to be used only by trained and qualified medical professionals trained in the administration of general anesthesia.

The Avance and Avance CS2 anesthesia systems supply set flows of medical gases to the breathing system using electronic gas mixing. Gas flows are selected by the user using the electronic controls on the main display unit and then displayed as electronic flow meters on the system display unit. The Avance systems are equipped with a pneumatic back-up O2 delivery system and traditional flow tube, as well. A large selection of frames options including central brake or individual caster brakes, gases, and vaporizers are available to give the user control of the system configuration. The Avance systems are also available in pendant models. Avance systems are available with two or three gases, up to three vaporizer positions and up to three cvlinder connections. All models have O2. The Avance systems come with up to two optional gases (air, N2O).

The Avance systems accept Tec 6 Plus and Tec 7 vaporizers on a Selectatec manifold. Safety features and devices within the Avance systems are designed to decrease the risk of hypoxic mixtures, agent mixtures and complete power or sudden gas supply failures. The Avance systems are available with optional integrated respiratory gas monitoring. When supplied as an option, the integrated respiratory gas monitoring is provided via the GE Compact Gas Airway Modules Series: M-Gas Module (M-CAiO and M-CAiOV software revision 3.2 and above cleared via K001814) and E-Gas Compact Gas Airway Module (E-CAiOVX software revision 3.2 and above cleared via K051092) which can be physically integrated into the Avance, receive electronic power from the Avance and communicate measured values to the Avance for display on the system display unit. In addition to M-Gas and E-gas modules, the Avance CS- can utilize the GE CARESCAPE Respiratory Module (E-sCAiO, E-sCAiOV cleared via K123195).

The Datex-Ohmeda 7900 Anesthesia Ventilator is used in the Avance Anesthesia Systems. It is a microprocessor based, electronically controlled, pneumatically driven ventilator that provides patient ventilation during surgical procedures. The 7900 ventilator is equipped with a built-in monitoring system for inspired oxygen, airway pressure and exhaled volume. Sensors in the breathing circuit are used to control and monitor patient ventilation as well as measure inspired oxygen concentration. This allows for the compensation of compression losses, fresh gas contribution and small leakage in the breathing absorber. bellows and system. User setting and microprocessor calculations control breathing patterns. The user interface keeps settings in memory. The user may change settings with a simple setting sequence. A bellows contains breathing gasses to be delivered to the patient. Positive End Expiratory Pressure (PEEP) is regulated electronically. Positive pressure is maintained in the breathing system so that any leakage that occurs is outward. An RS-232 serial digital communications port connects to and communicates with external devices. Ventilator modes for the device include Volume Control Ventilation (VCV), Pressure Control Ventilation (PCV) (optional), Synchronized Intermittent Mandatory Ventilation/Pressure Support (SIMV/PSV) (optional), Pressure Support Ventilation (PSVPro) (optional), Synchronized Intermittent Mandatory Ventilation-Pressure Control (SIMV-PC) (optional), Pressure Control Ventilation-Volume Guaranteed (PCV-VG) (optional), Constant Positive Airway Pressure/Pressure Support Ventilation (CPAP/PSV), Pressure Control Ventilation-Volume Guaranteed with Pressure Support Ventilation (SIMV PCV-VG) (optional), and Volume Control Ventilation Mode for Cardiac Bypass Mode (optional). Ventilator parameters and measurements are displayed on the system display unit.

Several frame configurations are available, including one that allows for the physical integration of the GE Monitor Series (cleared Carescape B850 via K092027 and B650 cleared on K102239). These configurations also provide cable management solutions such that the necessary connections from the monitor display unit to the monitor are hidden within the Avance frame. Additional configurations allow for the mounting of various patient monitors on the top shelf of the Avance.

The provided text is a 510(k) summary for the GE Datex-Ohmeda Avance CS2 Anesthesia System. It details the device's description, intended use, and a comparison to a predicate device. However, it explicitly states that no clinical testing was required or conducted for the modifications made to this version of the device.

Therefore, the document does not contain the information requested in your prompt regarding acceptance criteria and the study that proves the device meets them, as these are typically derived from clinical or comprehensive performance studies which were not performed in this case.

Specifically, the document states:

• "The modifications made to the GE Datex-Ohmeda Avance CS2 did not require clinical testing. The functionality of the modified features was completely evaluated by performing nonclinical tests of design verification and validation testing."

Without a clinical study or a study specifically designed to establish performance against acceptance criteria, I cannot fill out the requested table or provide details on sample sizes, expert involvement, ground truth establishment, or comparative effectiveness.

The only "testing" mentioned is nonclinical verification and validation testing, which includes:

• Risk Analysis
• Requirements Reviews
• Design Reviews
• Testing on unit level (Module verification)
• Integration testing (System verification)
• Performance testing (Verification)
• Safety testing (Verification)
• Simulated use testing (Validation)

This nonclinical testing served to confirm that the changes made (primarily updated labeling to include the use of an optional CARESCAPE respiratory module) did not alter the fundamental scientific technology or indications for use, and that the device remained substantially equivalent to its predicate.

Ask a specific question about this device

The GE Datex-Ohmeda Avance CS2 Anesthesia System is intended to provide general inhalation anesthesia and ventilatory support to a wide range of patients (neonatal, pediatric, adult). The device is intended for volume or pressure control ventilation.

The GE Datex-Ohmeda Avance and Avance CS anesthesia machines are intended to provide general inhalation anesthesia and ventilatory support to a wide range of patients (neonatal, pediatric, adult). They represent one of the systems in a long line of products based on the Datex-Ohmeda Excel, Aestiva, and Aespire Anesthesia Systems. Avance systems are to be used only by trained and qualified medical professionals trained in the administration of general anesthesia.

The Avance and Avance CS2 anesthesia systems supply set flows of medical gases to the breathing system using electronic gas mixing. Gas flows are selected by the user using the electronic controls on the main display unit and then displayed as electronic flow meters on the system display unit. The Avance systems are equipped with a pneumatic back-up O2 delivery system and traditional flow tube, as well. A large selection of frames options including central brake or individual caster brakes, gases, and vaporizers are available to give the user control of the system configuration. The Avance systems are also available in pendant models. Avance systems are available with two or three gases, up to three vaporizer positions and up to three cylinder connections. All models have O2. The Avance systems come with up to two optional gases (air, N2O).

The Avance systems accept Tec 6 Plus and Tec 7 vaporizers on a Selectatec manifold. Safety features and devices within the Avance systems are designed to decrease the risk of hypoxic mixtures, agent mixtures and complete power or sudden gas supply failures. The Avance systems are available with optional integrated respiratory gas monitoring. When supplied as an option, the integrated respiratory gas monitoring is provided via the GE Compact Gas Airway Modules Series: M-Gas Module (M-CAiO and M-CAiOV software revision 3.2 and above cleared via K001814) and E-Gas Compact Gas Airway Module (E-CAiOVX software revision 3.2 and above cleared via K051092) which can be physically integrated into the Avance, receive electronic power from the Avance and communicate measured values to the Avance for display on the system display unit.

The Datex-Ohmeda 7900 Anesthesia Ventilator is used in the Avance Anesthesia Systems. It is a microprocessor based, electronically controlled, pneumatically driven ventilator that provides patient ventilation during surgical procedures. The 7900 ventilator is equipped with a built-in monitoring system for inspired oxygen, airway pressure and exhaled volume. Sensors in the breathing circuit are used to control and monitor patient ventilation as well as measure inspired oxygen concentration. This allows for the compensation of compression losses, fresh gas contribution and small leakage in the breathing absorber, bellows and system. User setting and microprocessor calculations control breathing patterns. The user interface keeps settings in memory. The user may change settings with a simple setting sequence. A bellows contains breathing gasses to be delivered to the patient. Positive End Expiratory Pressure (PEEP) is regulated electronically. Positive pressure is maintained in the breathing system so that any leakage that occurs is outward. An RS-232 serial digital communications port connects to and communicates with external devices. Ventilator modes for the device include Volume Control Ventilation (VCV), Pressure Control Ventilation (PCV) (optional), Synchronized Intermittent Mandatory Ventilation/Pressure Support (SIMV/PSV) (optional), Pressure Support Ventilation (PSVPro) (optional), Synchronized Intermittent Mandatory Ventilation-Pressure Control (SIMV-PC) (optional), Pressure Control Ventilation-Volume Guaranteed (PCV-VG) (optional), Constant Positive Airway Pressure/Pressure Support Ventilation (CPAP/PSV), Pressure Control Ventilation-Volume Guaranteed with Pressure Support Ventilation (SIMV PCV-VG) (optional), and Volume Control Ventilation Mode for Cardiac Bypass Mode (optional). Ventilator parameters and measurements are displayed on the system display unit.

Several frame configurations are available, including one that allows for the physical integration of the GE Monitor Series(most recently cleared Carescape B850 via K092027 and B650 cleared on K102239). These configurations also provide cable management solutions such that the necessary connections from the monitor display unit to the monitor are hidden within the Avance frame. Additional configurations allow for the mounting of various patient monitors on the top shelf of the Avance.

Here's an analysis of the provided text regarding acceptance criteria and supporting studies for the GE Datex-Ohmeda Avance CS2 Anesthesia System:

Based on the provided document, the application is for a 510(k) premarket notification, which focuses on demonstrating substantial equivalence to a predicate device rather than undergoing new clinical trials for efficacy. Therefore, much of the information typically requested for acceptance criteria and a deep dive into study design for novel devices is not present or not applicable in this context.

The document explicitly states: "The modifications made to the GE Datex-Ohmeda Avance to create the GE Datex-Ohmeda Avance CS2 did not require clinical testing. The functionality of the modified features was completely evaluated by performing nonclinical tests of design verification and validation testing."

This immediately tells us that there was no standalone clinical study with human patients to prove device performance against specific acceptance criteria in the way one might expect for a new, high-risk device.

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

1. Table of Acceptance Criteria and the Reported Device Performance

Given the nature of a 510(k) for an updated device, the "acceptance criteria" are primarily related to meeting specifications, voluntary standards, and demonstrating that the new features do not negatively impact safety and effectiveness compared to the predicate device. There isn't a table of specific clinical performance metrics (e.g., accuracy of a diagnostic feature, rates of successful treatment) with corresponding target values and achieved results reported in this summary.

Acceptance Criteria (Implied from 510(k) process and text):

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

• Test Set Sample Size: Not applicable in the context of human clinical data for this specific device. The testing involved "nonclinical tests of design verification and validation testing," including unit-level testing, integration testing, performance testing, safety testing, and simulated use testing. These are not typically quantified with "sample sizes" in the same way as human subject studies; rather, they involve testing various components, configurations, and scenarios.
• Data Provenance: Not applicable as no clinical data from patients was used. The data provenance would be from internal engineering and quality testing (e.g., lab test data, simulated environment data).

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

• Not applicable. Since no clinical testing was performed and no ground truth was established from patient data, there's no mention of experts establishing a ground truth for a test set in a diagnostic or outcome-based scenario. The "ground truth" for nonclinical testing would be engineering specifications and functional requirements.

4. Adjudication Method for the Test Set

• Not applicable. There was no clinical test set requiring adjudication in the context of human data. Adjudication methods (like 2+1, 3+1) are typically used for resolving disagreements among human readers/experts in interpreting clinical data.

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 device is an anesthesia system, not an AI-powered diagnostic or assistive tool for human readers. Therefore, an MRMC comparative effectiveness study involving human readers and AI assistance would not be relevant and was not performed.

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

• Not applicable. This is an anesthesia machine, not an algorithm-only device. Its performance is inherent in its hardware, software, and integrated components, designed to operate with a medical professional as the "human in the loop" administering anesthesia.

7. The Type of Ground Truth Used

• For Nonclinical Testing: The ground truth would be based on engineering specifications, design requirements, and established performance benchmarks derived from the predicate device and relevant industry standards.
• For Substantial Equivalence: The ultimate "ground truth" for the 510(k) process is the safety and effectiveness profile of the predicate device (GE Datex-Ohmeda Avance, K112722). The new device must demonstrate it meets this same standard.

8. The Sample Size for the Training Set

• Not applicable. Given the device type and the absence of clinical studies, there is no mention of a "training set" in the context of machine learning. The testing performed (verification and validation) is based on engineering principles and quality assurance, not statistical training sets.

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

• Not applicable, as there was no machine learning training set mentioned.

Ask a specific question about this device

The GE Datex-Ohmeda Avance Anesthesia System is intended to provide general inhalation anesthesia and ventilatory support to a wide range of patients (neonatal, pediatric, adult). The device is intended for volume or pressure control ventilation.

The GE Datex-Ohmeda Avance is intended to provide general inhalation anesthesia and ventilatory support to a wide range of patients (neonatal, pediatric, adult). It represents one of the systems in a long line of products based on the Datex-Ohmeda Excel, Aestiva, and Aespire Anesthesia Systems. It is to be used only by trained and qualified medical professionals in the administration of general anesthesia. The Datex-Ohmeda Avance Anesthesia System supplies set flows of medical gases to the breathing system using electronic gas mixing. Gas flows are selected by the user using the keypad and rotary controller on the main display unit and then displayed as electronic flow meters on the system display unit. The Avance is equipped with a pneumatic back-up O2 delivery system and traditional flow tube, as well. A large selection of frames options, gases, and vaporizers are available to give the user control of the system configuration. The Avance is also available in wall-mount and pendant models. It is available with two or three gases, up to two vaporizer positions and up to three cylinder connections. All models have O2. The Avance comes with up to two optional gases (air, N2O). The Avance systems accept Tec 4, Tec 5, Tec 6, and Tec 7 vaporizers on a Selectatec manifold. Safety features and devices within the Avance are designed to decrease the risk of hypoxic mixtures, agent mixtures and complete power or sudden gas supply failures. The Avance system is available with optional integrated respiratory gas monitoring. When supplied as an option, the integrated respiratory gas monitoring is provided via the Datex-Ohmeda M-Gas Module (M-CAiO and M-CAiOV software revision 3.2 and above cleared via K001814) and E-Gas Module (E-CAiOVX software revision 4.5 and above cleared via K051092) which can be physically integrated into the Avance, receive electronic power from the Avance and communicate measured values to the Avance for display on the system display unit. The Datex-Ohmeda 7900 Anesthesia Ventilator is used in the Avance Anesthesia System. It is a microprocessor based, electronically controlled, pneumatically driven ventilator that provides patient ventilation during surgical procedures. The 7900 ventilator is equipped with a built-in monitoring system for inspired oxygen, airway pressure and exhaled volume. Sensors in the breathing circuit are used to control and monitor patient ventilation as well as measure inspired oxygen concentration. This allows for the compensation of compression losses, fresh gas contribution and small leakage in the breathing absorber, bellows and system. User setting and microprocessor calculations control breathing patterns. The user interface keeps settings in memory. The user may change settings with a simple and secure setting sequence. A bellows contains breathing gasses to be delivered to the patient. Positive End Expiratory Pressure (PEEP) is regulated electronically. Positive pressure is maintained in the breathing system so that any leakage that occurs is outward. An RS-232 serial digital communications port connects to and communicates with external devices. Ventilator modes for the device include Volume Control Ventilation (VCV), Pressure Control Ventilation (PCV) (optional), Synchronized Intermittent Mandatory Ventilation/Pressure, Support (SIMV/PSV) (optional), Pressure Support Ventilation (PSVPro) (optional), Synchronized Intermittent Mandatory Ventilation-Pressure Control (SIMV-PC) (optional), Pressure Control Ventilation-Volume Guaranteed (PCV-VG) (optional), Constant Positive Airway Pressure/Pressure Support Ventilation (CPAP/PSV), and Volume Control Ventilation Mode for Cardiac Bypass Mode. Ventilator parameters and measurements are displayed on the system display unit. Several frame configurations are available, including one that allows for the physical integration of the GE Monitors (most recently cleared Carescape B850 via K092027 and B650 cleared on K102239). This configuration also provides cable management solutions such that the necessary connections from the monitor display unit to the monitor are hidden within the Avance frame. Additional configurations allow for the mounting of various patient monitors on the top shelf of the Avance.

The provided text is a 510(k) Premarket Notification summary for the GE Datex-Ohmeda Avance Anesthesia System. This document focuses on demonstrating substantial equivalence to previously cleared predicate devices, rather than establishing de novo acceptance criteria and performing a study to prove they are met.

Therefore, the requested information categories concerning acceptance criteria and study design are not directly applicable or present in this type of regulatory submission. The document explicitly states: "The modifications made to the GE Datex-Ohmeda Avance did not require clinical testing."

However, I can extract information related to the non-clinical testing that was performed to support the substantial equivalence claim, which serves as a form of acceptance in the context of a 510(k) submission.

Here's a breakdown of the available information, addressing as many of your points as possible:

Acceptance Criteria and Reported Device Performance

Since this is a 510(k) submission for an updated device, the "acceptance criteria" are implicitly tied to demonstrating that the updated device performs equivalently or better than the predicate devices and meets its own verified specifications. The document does not provide a table for specific performance metrics and their acceptance ranges. Instead, it describes a robust non-clinical testing approach.

Study Details (Non-Clinical)

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

   • Test Set Sample Size: Not specified as a number of "samples" in the clinical sense. The testing involved various modules, integrated systems, and simulated use of the device.
   • Data Provenance: Not explicitly stated (e.g., country of origin, retrospective/prospective). However, the testing was conducted internally by the manufacturer (Datex-Ohmeda Inc.) as part of their development process. It is by nature "prospective" in the sense that the tests were designed and executed to evaluate the new device's modifications.

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

   • Number of Experts: Not specified. This type of non-clinical engineering validation typically involves internal engineers, quality assurance personnel, and potentially subject matter experts who understand anesthesia systems.
   • Qualifications of Experts: Not specified, but implied to be qualified technical and engineering personnel involved in the device's design, development, and testing at Datex-Ohmeda.

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

   • Adjudication Method: Not applicable. This concept pertains to clinical studies where independent reviewers agree on ground truth. In non-clinical engineering testing, "adjudication" is managed through formal test protocols, defect tracking, and review processes by the development and quality teams.

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:

   • MRMC Study: No. This is not an AI-assisted diagnostic device, but an anesthesia system. Therefore, MRMC studies are not relevant. This document explicitly states: "The modifications made to the GE Datex-Ohmeda Avance did not require clinical testing."

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

   • Standalone Performance: The non-clinical testing evaluates the device's inherent performance characteristics, including its software logic and hardware functionality, in a standalone manner (i.e., its ability to perform its functions as designed without direct human intervention in the moment of testing, though human users operate the system during its intended use). The testing verifies that the "algorithm only" (software) performs as specified.

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

   • Ground Truth: For non-clinical engineering validation, the "ground truth" is defined by the device's design specifications, industry standards, and regulatory requirements. The device is tested against these predefined criteria to ensure it performs as intended and safely.

7. The sample size for the training set:

   • Training Set Sample Size: Not applicable. This is not an AI/machine learning device that requires a training set.

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

   • Ground Truth for Training Set: Not applicable, as there is no training set for an AI/ML model.

In summary: The GE Datex-Ohmeda Avance Anesthesia System underwent a non-clinical verification and validation process. The "acceptance criteria" were met through demonstrating compliance with design specifications, software validation, risk analysis, and adherence to voluntary standards. No clinical studies were deemed necessary due to the nature of the modifications and the substantial equivalence claim.

Ask a specific question about this device

The GE Datex-Ohmeda Engström family of ventilators (Engström Carestation and Engström Pro) are designed to provide mechanical ventilation for adults and pediatrics weighing 5kg and above having degrees of pulmonary impairment varying from minor to severe. Optional Neonatal capabilities on Engström family expand the patient range to 0.25 kg.

The GE Datex-Ohmeda Engström family of ventilators are microprocessor based, electronically controlled, pneumatically driven ventilators that include integrated FiO2, airway pressure, spirometry and volume monitoring. Options include an Aerogen Aeroneb nebulizer, data capture accessory and an integrated air compressor. Options available on Engström Carestation only include integrated respiratory gas monitoring capabilities via various Datex-Ohmeda patient monitoring modules listed in the product labeling, capabilities to measure SpiroDynamics via an intratracheal pressure sensor in patients using sized 6.5 tracheal tubes and larger, and calculation of functional residual capacity of mechanically ventilated patients using Nitrogen Wash In/Wash Out method.

Not all features are available with all patient populations.

The Engström Carestation is not a pulmonary function calculation device.

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

The GE Datex-Ohmeda Engström family of ventilators (Engström Carestation and Engström Pro) are flexible, adaptable, and intuitive critical care ventilators. A wide selection of performance options gives the user full control of the system configuration. The Engström Carestation is a complete system featuring patient monitoring, patient ventilation, and the capability of interfacing with central information management systems. The Engström Pro is a defeatured variant of the Engström Carestation.

Both the GE Datex-Ohmeda Engström Carestation and Engström Pro are designed to provide mechanical ventilation for adults and pediatrics weighing 5kg and above having degrees of pulmonary impairment varying from minor to severe. Optional Neonatal capabilities expand its patient range to 0.25 kg.

The modes of ventilation currently available include:

1. Volume Controlled (VCV)
2. Pressure Controlled (PCV)
3. Pressure Controlled, Volume Guaranteed (PCV-VG)
4. Synchronized Intermittent Mandatory Ventilation, Volume Controlled (SIMV-VC)
5. Synchronized Intermittent Mandatory Ventilation, Pressure Controlled (SIMV-PC)
6. Synchronized Intermittent Mandatory Ventilation, Pressure Controlled Volume Guarantee (SIMV-PCVG)
7. Bi-level Airway Pressure Ventilation
8. Constant Positive Airway Pressure/Pressure Support Ventilation (CPAP/PSV)
9. Apnea backup (available in SIMV-VC, SIMV-PC, SIMV-PCVG/BiLevel-VG, BiLevel, CPAP/PSV, and VG-PS)
10. Non-invasive ventilation (NIV), not available in neonatal mode
11. Infant Nasal CPAP (nCPAP), only available in neonatal mode
12. Volume Guarantee, Pressure Support (VG-PS), only available in neonatal mode

The GE Datex-Ohmeda Engström Carestation and Engström Pro are microprocessor based, electronically controlled, pneumatically driven ventilators that include integrated FiO2, airway pressure, spirometry and volume monitoring and an Aerogen Aeroneb Pro nebulizer control board.

The ventilator consists of two main components: a display and a ventilator unit. The display allows the user to interface with the system and control settings through use of soft keys on the display, a com wheel, and a resistive touch screen. The ventilator unit controls electrical power, nebulization, and pneumatic gas flow to and from the patient. The Engstrom Carestation also includes a module bay that allows the integration of various Datex-Ohmeda patient monitoring modules with the ventilator.

The user interface for control of nebulization is provided via the ventilator display unit. The Aerogen Aeroneb Pro Nebulizer board (K021175) is provided standard with the unit. Nebulizers are options for both the Engström Carestation and Engström Pro. Users have the option to configure the system to use an external pneumatic nebulizer in place of the Aerogen.

Optional accessories common to both Engström Carestation and Engström Pro include a trolley/cart, integrated air compressor, support arm, humidifier and water trap mounting brackets, and a data capture accessory. The GE Datex-Ohmeda EV Air Compressor is intended for use as an accessory to provide a dry, filtered, breathable compressed air supply. The compressor has no alarm functions. The Engström Carestation or Engström Pro provides all alarm functions and reactions to a failure of the compressed gas supply. The compressor is installed in the base of the ventilator cart. The compressor is powered from AC mains only. A source of compressed oxygen is required to be connected to Engström Carestation/Engström Pro equipped with the optional compressor. The compressor was cleared in K041775.

Additional optional accessories specific to the Engström Carestation include airway modules, intratracheal pressure sensor, auxiliary electrical outlets, and module bay. Optional functionality specific to the Engström Carestation includes integrated respiratory gas monitoring, capabilities to measure SpiroDynamics via a GE supplied intratracheal pressure sensor in patients using sized 6.5 tracheal tubes and larger, and calculation of functional residual capacity of mechanically ventilated patients using Nitrogen Wash In/Wash Out method. The integrated respiratory gas monitoring is provided via the Datex-Ohmeda Gas Modules, M-C, M-CO, M-COV, M-COV, M-COVX, M-CaiO, M-CAiOV, M-CAiOVX, rev 3.2 software and higher (K001814), E-CO, E-COV, E-COVX, E-CAiO, E-CAiOV, E-CAiOVX (K051092), or M-Mini-CO2 Module (K023454) or E-MiniC module (K052582) which are physically integrated into the Engström Carestation, receive electronic power from the Engstrom Carestation and communicate measured values to the Engström Carestation for display on the system display unit.

The provided text describes a 510(k) premarket notification for the GE Datex-Ohmeda Engström Ventilator family (Engström Carestation and Engström Pro). This submission is for an updated version of an existing device, primarily involving software changes.

Here's an analysis of the acceptance criteria and study information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The submission does not explicitly provide a table of acceptance criteria with specific performance metrics (e.g., accuracy, sensitivity, specificity) for the device's functions. Instead, it focuses on demonstrating substantial equivalence to a predicate device through non-clinical testing and verification.

However, the general acceptance criteria for this type of submission are implied through the testing methods described:

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

• Sample Size for Test Set: Not explicitly stated. The text mentions "Testing on unit level," "Integration testing," "Performance Testing (Verification)," and "Safety Testing (Verification)" but does not specify the number of devices or scenarios used for these tests.
• Data Provenance: The testing appears to be conducted in-house by GE Healthcare/Datex-Ohmeda Inc. as part of their development and verification process. The data is retrospective in the sense that it's based on internal testing conducted on the device prior to submission, rather than prospective clinical trials. There is no mention of data origin by country.

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

Not applicable. This submission is for a ventilator, and the testing described is primarily engineering verification and validation against technical specifications and predicate device performance. It does not involve interpretation of medical images or diagnostic outputs that would require clinical expert "ground truth" establishment in the way a diagnostic AI device would. "Simulated Use/User Requirements Testing (Validation)" was performed, implying user involvement, but the number and qualifications of these users/experts are not specified, nor is their role in establishing a "ground truth" defined in the typical diagnostic context.

4. Adjudication Method for the Test Set

Not applicable. As noted above, the testing is against technical specifications and predicate device performance, not against expert-adjudicated ground truth.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size

No MRMC comparative effectiveness study was done. The text explicitly states: "The modifications made to the Engstrom ventilator did not require clinical testing."

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

The device itself is a standalone medical device (a ventilator), not an algorithm intended for diagnostic interpretation. The software updates were evaluated for their standalone functionality as part of the ventilator system. The non-clinical tests verified and validated the "safety and functionality" of the ventilator with the software changes.

7. The Type of Ground Truth Used

The "ground truth" for this device's performance is its adherence to:

• Technical Specifications: The device's design specifications for ventilation parameters, safety features, alarm conditions, etc.
• Predicate Device Performance: The established safety and effectiveness of the previously cleared Engstrom Ventilator (K093886) and Hamilton G5 Ventilator (K070513).
• Applicable Standards: Compliance with relevant medical device standards (e.g., electrical safety, electromagnetic compatibility).

8. The Sample Size for the Training Set

Not applicable. This document describes a medical device (ventilator) with software updates, not an AI/ML algorithm that requires a "training set" in the machine learning sense. The software updates were based on "customer feedback" and "minor changes to bring the product in line with current specifications," but this is not equivalent to a supervised learning training process.

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

Not applicable, as there was no AI/ML training set in the context described by the question.

Ask a specific question about this device