Search Results

The Astral 100/150 provides continuous or intermittent ventilatory support for patients weighing more than 5kg (11 lb) who require mechanical ventilation.

The iVAPS mode is intended for patients weighing more than 66lb (30kg).

The Astral device is intended to be used in home, institution/hospital and portable applications for both invasive and non-invasive ventilation.

The Astral ventilator system uses a micro-processor controlled blower, which, along with valves and pressure and flow sensors, achieves pressure, flow and time regulation of air is directed to the patient via one of three ventilator breathing circuit, single circuit with expiratory valve, or single circuit with intentional leak. Supplemental oxygen can be entrained at the main turbine. The device provides both therapeutic alarms (e.g. tidal volume) and technical alarms (e.g. system fault), and a user interface allowing adjustment of clinical parameters and display of monitored clinical data. The Astral can use external AC or DC power supply and contains an integrated battery.

The Astral is capable of providing the following types of ventilatory support:

• -Assist/Control and SIMV with either volume or pressure control
• -Continuous Spontaneous Ventilation in either Pressure Support or CPAP
• -Volume Assurance and Apnea Ventilation

The provided document is a 510(k) premarket notification for a medical device (ventilator). It focuses on demonstrating substantial equivalence to a predicate device rather than presenting a study proving the device meets specific acceptance criteria for AI or a new diagnostic tool.

Therefore, the document does not contain the information requested in your prompt regarding acceptance criteria, device performance derived from a test set, sample sizes, expert involvement, adjudication methods, MRMC studies, standalone performance, ground truth types, training set information, or how ground truth was established for a new AI/diagnostic device.

The document discusses:

• Device Name: Astral 100/150
• Regulation Name: Continuous Ventilator
• Predicate Device: ResMed Astral 100/150 (K133868)
• Reference Device: Respironics Trilogy 200 (K093416)
• Reason for Submission: New device (specifically, the addition of the iVAPS therapy mode).
• Non-Clinical Performance Data: Stated that design and verification activities were performed, including accuracy of ventilation, volume & pressure controls and monitoring, waveform performance, accuracy and repeatability of triggering and cycling, endurance and environmental testing, and alarm verification. It explicitly states, "All tests confirmed the product met the predetermined acceptance criteria." However, it does not list these specific acceptance criteria in a table or provide quantitative performance results against them. It also mentions side-by-side performance testing for the new therapy mode (iVAPS) and electrical changes testing.
• Conclusion: The device is substantially equivalent to the predicate and reference devices based on intended use, technological characteristics, and principles of operation. Clinical testing was not required for this submission.

In summary, this document is a 510(k) submission for a ventilator, focusing on substantial equivalence to a predicate device and not a study validating a new AI/diagnostic device with the specific criteria you've outlined.

Ask a specific question about this device

The AirFit F20 is a non-invasive accessory used for channeling airflow (with or without supplemental oxygen) to a patient from a positive airway pressure (PAP) device such as a continuous pressure (CPAP) or bilevel system.

The AirFit F20 is:
• to be used by patients weighing more than 66 lb (30 kg) for whom positive airway pressure therapy has been prescribed
• intended for single-patient reuse in the home environment and multi-patient reuse in the hospital/institutional environment.

The AirFit F20 is an externally placed vented mask covering the mouth and the nose of the patient. It provides a seal such that pressure from a positive pressure source is directed to the patient's nose and/or mouth. The mask connects via a standard conical connector to a conventional air delivery hose, which in turn connects to the positive pressure source. The mask is held in place with an adjustable headgear that straps the mask to the face. The AirFit F20 mask system comprises four subassemblies: cushion, frame, elbow and headgear. The elbow incorporates the vent array and anti-asphyxia valve safety features. The cushion and headgear are available in various sizes to fit a wide patient population.

AirFit F20 is a prescription device supplied non-sterile.

The provided document is a 510(k) summary for the ResMed AirFit F20, a non-invasive accessory for CPAP/bilevel systems. It focuses on demonstrating substantial equivalence to a predicate device (Quattro Air K123979) rather than presenting a study to prove acceptance criteria for a new, unique device performance. Therefore, many of the requested categories (e.g., sample size for test set, number of experts for ground truth, MRMC study, training set information) are not applicable or not explicitly detailed as one might find in a study specifically designed to establish novel performance claims.

Here's an analysis based on the available information:

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't provide a direct table of specific acceptance criteria values alongside numerical performance results for the AirFit F20. Instead, it states that the device was designed and tested in accordance with ISO 17510-2: Sleep apnoea breathing therapy - Part 2: Masks and application accessories, and that testing confirmed the new device met "predetermined acceptance criteria" and its performance is "substantially equivalent" to the predicate.

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

• Sample Size for Test Set: Not explicitly stated. The testing appears to be primarily bench/non-clinical and biocompatibility. For bench testing of physical characteristics like flow, rebreathing, and resistance, samples would typically consist of a certain number of manufactured units of the AirFit F20. The specific number is not provided.
• Data Provenance: The testing was non-clinical (bench testing) and focused on material and functional performance. It does not involve human patient data in the context of clinical outcomes. The manufacturer, ResMed Ltd., is based in Australia, and the submission was made to the US FDA.

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

• This question is not applicable in the context of this 510(k) submission. The "ground truth" for the non-clinical tests (e.g., CO2 rebreathing, flow resistance) is established by measurement against predefined engineering specifications and international standards (like ISO 17510-2). These are objective physical measurements, not subjective expert interpretations that require "ground truth" establishment by multiple experts with specific qualifications like radiologists.

4. Adjudication Method for the Test Set

• Not applicable. Since the tests are objective physical measurements against standards and predicate performance, there is no need for expert adjudication.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• No. The document explicitly states: "Clinical data was not relied upon to demonstrate substantial equivalence to the predicate device. Bench testing demonstrates that the new AirFit F20 device performs in an equivalent manner and is as safe and as effective as the predicate device." MRMC studies apply to imaging or diagnostic devices where human readers interpret results, which is not the case for this device.

6. Standalone (i.e., algorithm only without human-in-the-loop performance) Performance Study

• Yes, indirectly. The non-clinical data presented (CO2 rebreathing, AAV performance, total mask flow, flow resistance, through impedance, mechanical integrity, biocompatibility) represents testing of the device's inherent physical and functional performance, essentially "standalone" in a bench setting without human interaction influencing the core functional measurements. However, it's not an "algorithm" in the typical sense for AI, but rather the performance of the physical mask.

7. The Type of Ground Truth Used

• The "ground truth" for the non-clinical tests is based on:
  • International Standards: Specifically, ISO 17510-2: Sleep apnoea breathing therapy - Part 2: Masks and application accessories.
  • Engineering Specifications: Predetermined acceptance criteria derived from the standard and design requirements.
  • Predicate Device Performance: Demonstrating substantial equivalence to the performance characteristics of the legally marketed predicate device (Quattro Air (K123979)).

8. The Sample Size for the Training Set

• Not applicable. This device is a physical medical device (mask), not an AI/algorithm-based diagnostic system that requires a "training set" in the machine learning sense.

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

• Not applicable. As above, there is no AI training set for this device.

Ask a specific question about this device

AirView is a web based solution for healthcare specialists intended to:

• assist in the diagnosis of sleep disordered breathing in adult patients through analysis of data recorded by an AirView compatible home sleep device.

• transfer and display machine and therapeutic information that has been transmitted remotely from the patient's therapy device. It is intended to support the standard follow-up care of patients that have been prescribed a compatible ResMed therapy device. AirView also provides remote settings capabilities for non-life support devices only.

AirView is a web application that can transfer, store, analyse, manage, and display machine and therapy data (from ResMed compatible therapy devices) and diagnostic data (from ResMed compatible sleep study devices). The data is transferred from the device either wirelessly through a communications module or with the aid of a data card/USB stick and internet technology to a central database and then displayed on the healthcare professional's computer through a web browser such as Internet Explorer.

The software application enables patient machine and therapy data to be shared across several different user groups for the primary purpose of monitoring patient compliance and home sleep studies. Clinical users and other healthcare specialists can access data with ResMed approved user accounts.

AirView can also be used by the healthcare specialist to remotely change the machine settings of compatible therapy devices. This assists in addressing any clinical issues in a timely manner and providing the necessary patient support. This is restricted to non-life support therapy devices only.

The provided document describes the AirView device, a web-based solution for healthcare specialists. It aims to assist in the diagnosis of sleep-disordered breathing and manage patient therapy data. The submission highlights that the modified AirView device underwent non-clinical testing to demonstrate substantial equivalence to its predicate devices (EasyCare Online (K132371) and ResScan (K140054)). No clinical testing was deemed necessary.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based only on the provided text:

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

The document states that "All tests confirmed the product met the predetermined acceptance criteria". However, the specific quantitative acceptance criteria themselves are not explicitly listed in the provided text. The performance is reported in a descriptive manner, focusing on verification activities.

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

The document mentions "End-to-End testing," "Regression Testing," and "Side-by-Side testing," but it does not specify the sample size for any of these test sets, nor does it provide information about the data provenance (e.g., country of origin, retrospective or prospective nature of the data used in these tests).

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)

The document does not mention the use of experts to establish ground truth for the test set. The testing appears to be focused on technical validation (data transfer, functionality, output comparison) rather than clinical interpretation by human experts.

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

The document does not describe any adjudication method as it does not involve expert consensus or human interpretation for the ground truth.

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

A multi-reader multi-case (MRMC) comparative effectiveness study was not done or described in the provided text. The AirView device's primary function is data management, transfer, and display, and to "assist in the diagnosis of sleep disordered breathing in adult patients through analysis of data recorded by an AirView compatible home sleep device," not necessarily to directly improve human reader performance in interpreting images or complex diagnostic output requiring "readers." The "analysis" of data for diagnosis is performed by the system itself based on recorded sleep data.

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

The testing conducted ("End-to-End testing," "Regression Testing," "Side-by-Side testing") assessed the standalone performance of the algorithm/software in terms of data transfer, functionality, and output comparability. The device "assists in the diagnosis" through this analysis, implying it has a standalone analytical component without a human "in the loop" for that specific analytical function.

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

Given the nature of the testing (data transfer, functional verification, output comparison), the "ground truth" implicitly refers to:

• Correct data transmission: Ensuring the data sent matches the data received.
• Expected software behavior: Verifying that existing functionalities remain unchanged and new functionalities operate as designed.
• Concordance with predicate device output: Comparing the output of the modified AirView with a known, cleared predicate device (ResScan) to ensure they produce comparable results.

There is no mention of expert consensus, pathology, or outcomes data being used for ground truth in these non-clinical tests.

8. The sample size for the training set

The document does not mention a training set or any machine learning model training. The described activities are verification testing, not model development or validation.

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

As no training set is mentioned, this information is not applicable or provided.

Ask a specific question about this device

The Darlinghurst Vented mask is a non-invasive accessory used for channeling airflow to a patient from positive airway pressure (PAP) devices.
The mask is:

• to be used on patients weighing >66 lb (30 kg), for whom non-invasive positive airway pressure therapy has been prescribed
• disposable devices, intended for short-term treatment (up to 7 days) of a single patient, in the hospital environment only.

The Darlinghurst NV-AAV mask is a non-invasive accessory used for channeling airflow to a patient from a positive airway pressure (PAP) device.
The mask is:

• to be used on patients weighing >66 lb (30 kg), for whom non-invasive positive airway pressure ● therapy has been prescribed
• a disposable device, intended for short-term treatment (up to 7 days) of a single patient, in the ● hospital environment only
• intended to be used with breathing circuits or positive pressure ventilation (PPV) devices that provide their own method of venting expired or supplemental gases.

The Darlinghurst masks are externally placed masks covering the mouth and the nose of the patient. They provide a seal such that positive pressure from a positive pressure source is directed to the patient's nose and/or mouth. The masks connect via a standard (female ISO5356-1) conical connector to a conventional air delivery hose between the mask elbow and the positive airway-pressure source.
They are held in place with a common adjustable headgear that straps the mask to the face.
Darlinghurst masks are disposable devices that can be used for a maximum period of 7 days, on a single-patient and in the hospital/institutional environment only.
Both Darlinghurstmask variants are very similar in design and function. The only difference between the Darlinghurst 'Vented' and the Darlinghurst 'NV-AAV' is in the elbow component.
Whilst both variants of the mask include a built-in Anti-Asphyxia Valve (AAV) to allow the patient to continue to breathe fresh air in the event of a positive air-pressure supply failure or impediment,

• . The Darlinghurst Vented mask includes additional built-in diffuse exhaust ports to provide a continuous air leak that flushes out CO2 and prevent it from being rebreathed by the patient
• The Darlinghurst NV-AAV design does not incorporate built-in passive exhaust ● ports. This non-vented variant of the mask requires a separate part of the breathing circuit (e.g. an active exhaust valve in the ventilator or an additional leak valve) to vent the expired air (including CO2).
  All other components of the masks are common to both Darlinghurst variants.
  Darlinghurst masks are intended to be used under the conditions and purposes indicated in the labelling provided with the product.
  Darlinghurst masks are prescription devices, supplied non-sterile.

The provided document describes the FDA 510(k) clearance for the ResMed Darlinghurst Vented and Darlinghurst NV-AAV masks, which are non-invasive accessories for positive airway pressure (PAP) devices.

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

The document presents a table summarizing various bench tests conducted and their corresponding pass/fail results. While explicit acceptance criteria (numerical thresholds) are not fully detailed for each test, the general acceptance criterion is that the device "PASS"es the test, implying it meets predefined performance targets.

The report states that the characteristics listed above ensure that clinicians are able to prescribe the appropriate therapy when using the new device. The CO2 performance data demonstrates re-breathing to be substantially equivalent to the predicates.

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

The document does not explicitly state a specific "sample size" in terms of number of individuals or devices for each test. Instead, it refers to "bench testing" which typically involves testing of representative samples of the device. The data provenance is implied to be from laboratory testing performed by ResMed Ltd, an Australian company, as part of their 510(k) submission. The exact country of origin of the data is not specified beyond the manufacturer's location. The studies are retrospective in the sense that they are conducted on manufactured devices in a laboratory setting to demonstrate compliance.

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

This information is not applicable to this submission. The "ground truth" in this context refers to established technical standards and the performance of predicate devices, which are assessed through objective laboratory measurements rather than expert human interpretation of medical images or conditions. The study is a comparison to a predicate device and relevant industry standards (e.g., ISO 17510-2:2007 for CO2 performance, ISO 10993-1 for biocompatibility).

4. Adjudication method for the test set:

This information is not applicable. Adjudication methods like 2+1 or 3+1 are used in clinical studies where human interpretation or diagnosis is involved. Here, the tests are objective bench tests with pass/fail outcomes against established technical criteria or comparison to a predicate device.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

This information is not applicable. The device is a medical mask and not an AI-powered diagnostic tool. Therefore, no MRMC study or assessment of AI assistance for human readers was conducted or is relevant to this submission.

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

This information is not applicable. The device is a physical medical mask, not an algorithm.

7. The type of ground truth used:

The "ground truth" used for assessing the device's performance relies on several factors:

• Established technical standards: Such as ISO 17510-2:2007 for CO2 re-breathing and ISO 10993-1 for biocompatibility.
• Performance of predicate devices: The Darlinghurst masks were compared against the Hans Rudolph 6600 Series V2 (for Vented) and Hans Rudolph 6700 Series V2 (for NV-AAV). The established performance characteristics of these predicate devices served as a benchmark for substantial equivalence.
• Engineering specifications and design requirements: The "PASS" results indicate that the device met its predefined engineering specifications derived from relevant standards and predicate device performance.

8. The sample size for the training set:

This information is not applicable. This is a 510(k) submission for a physical medical device, not an AI/ML algorithm that requires a training set. The development of the masks likely involved iterative design and testing, but not in the context of "training data."

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

This information is not applicable for the same reasons as point 8.

Ask a specific question about this device

The S9 Greenhills is indicated for the treatment of patients weighing more than 66 lb (30 kg) with obstructive sleep annea (OSA), central and/or mixed apneas, or periodic breathing.

It is intended for home and hospital use.

The hunidifier is intended for single patient use in the home environment and re-use in a hospital/institutional environment.

The S9 Greenhills is similar to the predicate device(s), using a blower based positive pressure system with an integrated heated humidifier and heater controller. The device platform is identical to the S9 VPAP Adapt (K113801) and contains a Micro-processor controlled blower system that generates controlled positive airway pressure between 3-25 cmH2O. The system comprises the flow generator, patient tubing, mask (patient interface) and humidifier.

The S9 Greenhills is a flow generator device designed to provide adaptive servo-ventilation therapy (ASV mode) or (ASVAuto mode) to stabilize a patient's ventilation during sleep. The device continually measures the patient's instantaneous ventilation, and calculates a target ventilation based on to the patient's recent average minute ventilation. It then adjusts the degree of pressure support to servo-control the patilation to at least equal the target ventilation. The same is true for ASVAuto mode except the EPAP is adjusted to address any obstructive apneas detected.

Therapy modes contained in the S9 Greenhills are CPAP, ASV, and ASVAuto and unchanged from the S9 VPAP Adapt (K102586). They are:

• . CPAP mode - the device delivers a continuous positive airway pressure throughout the entire therapy session;
• ASV mode the device automatically adjusts pressure support in response to the . patient's recent average minute ventilation; and
• ASVAuto mode the device automatically adjusts pressure support in response to . the patient's recent average minute ventilation and EPAP level for OSA events.

The functional characteristics of the S9 Greenhills system includes all the clinician and user friendly features of the predicate device which have been verified during usability studies in accordance with IEC 62366 Medical devices - Application of usability engineering to medical devices.

The provided 510(k) summary for the ResMed S9 Greenhills device describes its acceptance criteria and the study conducted to demonstrate its performance. However, it's important to note that this submission focuses on demonstrating substantial equivalence to a predicate device, not on proving overall clinical effectiveness from scratch. Therefore, the "study" is primarily comparative bench testing, and some of the requested information (like human reader performance with/without AI assistance, or expert consensus for ground truth on a large test set) is not applicable or not provided in this type of submission.

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

1. Table of Acceptance Criteria and Reported Device Performance

The submission does not provide a direct table of specific numerical acceptance criteria with corresponding performance metrics like a typical clinical trial report. Instead, it states that "All tests (predicate bench testing) confirmed the product met the predetermined acceptance criteria." and "Side-by-Side bench testing was performed to verify that the S9 Greenhills met the predetermined pass/fail requirements of the S9 Greenhills System Specification when compared to the predicate devices."

The key performance characteristics compared, which inherently define the acceptance criteria for substantial equivalence, are:

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

• Sample Size for Test Set: The document refers to "Side-by-Side bench testing" using "a breathing machine simulates patient breathing patterns." No specific number of simulated patient breathing patterns or cases are quantified.
• Data Provenance: The testing is described as "bench testing" and is therefore synthetic data generated by a breathing machine, not human patient data. There is no country of origin of data or retrospective/prospective designation in the clinical sense, as it is a bench study.

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

This information is not applicable and not provided. The "ground truth" for this bench testing is the expected performance of a well-functioning CPAP/ASV device, primarily benchmarked against the predicate device's known performance characteristics. The tests verify engineering specifications, not clinical diagnoses that would require expert consensus.

4. Adjudication Method for the Test Set

Not applicable. This was a bench test against predetermined engineering specifications and comparison to predicate device performance. No human adjudication of clinical outcomes or images was involved.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

Not applicable. This is a ventilation device, not a diagnostic imaging device using AI to assist human readers. Therefore, an MRMC study comparing AI-assisted vs. non-AI-assisted human reader performance is not relevant to this submission.

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

The device itself is a standalone medical device that delivers therapy based on internal algorithms and sensor inputs. The "bench testing" described evaluates the performance of these algorithms and the device's hardware independently. While not explicitly framed as an "algorithm only" study in the AI context, the bench tests verify the device's automated functioning.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

The "ground truth" for this study is primarily:

• Engineering Specifications: Predetermined pass/fail criteria from the "S9 Greenhills System Specification."
• Predicate Device Performance: The known and established performance of the S9 VPAP Adapt (K113801) is used as the benchmark for comparison, establishing "substantial equivalence." The "breathing machine simulates patient breathing patterns" to test the device's response against expected physiological responses.

8. The Sample Size for the Training Set

Not applicable. This medical device primarily uses control algorithms based on established physiological principles and engineered specifications, not machine learning algorithms that require a distinct "training set" of data in the AI sense.

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

Not applicable, as there is no "training set" in the context of an AI/machine learning algorithm for this device. The device's operating principles and algorithms are based on established medical science for respiratory support.

Ask a specific question about this device

The S9 WANDA VPAP ST is indicated for the treatment of Obstructive Sleep Apnea (OSA) in patients weighing more than 66 lb (30 kg). It is intended for use in the hospital and home.

S9 WANDA VPAP ST System is similar to the predicate device (S9 VPAP ST (K102513)). Key features include: inline power supply; integrated humidifier; tubing; colour LCD; and simple controls. The S9 WANDA VPAP ST contains a Micro-processor controlled blower system that generates Continuous Positive Airway Pressure (CPAP) from 3-25 cmHzO as required to maintain an "air splint" for treatment of OSA. The system comprises the flow generator, patient tubing, mask (patient interface) and humidifier. The S9 WANDA VPAP ST flow generator includes the same therapy modes as the S9 VPAP ST system (K102513) predicate device. These base therapy modes include: CPAP and CPAP with expiratory pressure relief (EPR) modes the device delivers a continuous positive airway pressure throughout the therapy session Bilevel mode the flow generator augments any breath initiated by the patient by detecting the onset of inspiration or expiration and delivering the set Inspiratory Positive Airway Pressure (IPAP) and Expiratory Positive Airway Pressure (EPAP) VAuto mode - the mean air-way pressure (between IPAP and EPAP) will alter based upon breathing events The functional characteristics of the S9 WANDA VPAP ST system includes all the clinician and user friendly features of the predicate device which have been verified during usability studies in accordance with IEC 62366 Medical devices - Application of usability engineering to medical devices.

Acceptance Criteria and Study for S9 WANDA VPAP ST

The submission for the S9 WANDA VPAP ST primarily relied on bench testing to demonstrate substantial equivalence to its predicate device, the S9 VPAP ST (K102513). Therefore, the "acceptance criteria" discussed below primarily refer to the performance standards met during these bench tests, which were deemed sufficient to prove a similar level of safety and effectiveness to the predicate. No clinical studies are mentioned.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a formal "acceptance criteria" table with specific quantitative thresholds for each test. Instead, it states that "All tests confirmed the product met the predetermined acceptance criteria" and that these criteria were "traced to the S9 WANDA VPAP ST System Specification and to the predicate device's performance."

However, the "Characteristics (differences) between predicate and new device" and "Flow Generator comparison" sections provide some comparative performance data, which can be interpreted as demonstrating the device's fulfillment of implied acceptance criteria based on equivalence to the predicate.

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

• Sample Size for Test Set: Not applicable as no human-subject clinical test set was used. The study relied on bench testing using a "breathing machine" and the device itself.
• Data Provenance: The bench testing was performed by ResMed Ltd., an Australian company. The testing is therefore attributed to the manufacturer's internal testing procedures. The data would be considered prospective in relation to the submission, as it was specifically generated for the purpose of demonstrating substantial equivalence.

3. Number of Experts Used to Establish Ground Truth and Qualifications

• Number of Experts: Not applicable. The "ground truth" for the bench testing was established by comparing the S9 WANDA VPAP ST's performance to the "S9 WANDA VPAP ST System Specification" and the "predicate device's performance." These are engineering specifications and previously established performance metrics, not expert human interpretations of data.
• Qualifications of Experts: Not applicable.

4. Adjudication Method for the Test Set

• Adjudication Method: Not applicable. There was no human "test set" requiring adjudication. The assessment was based on objective measurements against engineering specifications and comparison to the predicate device's measured performance during bench testing.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• MRMC Study: No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not performed. The submission explicitly states "Bench testing alone is sufficient to demonstrate Substantial Equivalence."
• Effect Size of Human Readers with/without AI Assistance: Not applicable, as no human-in-the-loop study with AI assistance was conducted.

6. Standalone (Algorithm Only) Performance Study

• Standalone Study: Yes, in a sense. The "bench testing" represents a standalone performance evaluation of the device's algorithms and hardware without a human operator directly influencing its core therapeutic function during the test. The "breathing machine" simulates patient input, and the device's response is objectively measured. This is not "algorithm only" in the modern sense of a software-as-a-medical-device (SaMD) study, but rather the performance of the integrated device's therapeutic functions.

7. Type of Ground Truth Used

• Type of Ground Truth: The ground truth for the bench testing was based on:
  • Engineering Specifications: The S9 WANDA VPAP ST System Specification defined the expected performance.
  • Predicate Device Performance: Direct comparison to the measured performance of the legally marketed S9 VPAP ST (K102513) further served as a "ground truth" for demonstrating equivalence. This is an objective, measured ground truth.

8. Sample Size for the Training Set

• Sample Size for Training Set: Not applicable. This device is a hardware-based medical device with integrated software that controls its mechanical functions (like pressure generation and response to breathing patterns). It does not employ machine learning or AI models that require a separate "training set" of data in the way modern AI/ML devices do. The software development likely involved traditional engineering verification and validation.

9. How Ground Truth for the Training Set Was Established

• How Ground Truth for Training Set Was Established: Not applicable, as there was no training set in the context of machine learning. The device's operational parameters and control logic were developed through engineering design process, adhering to established medical device standards (e.g., IEC 60601-1, IEC 62304) and based on the predicate device's proven functionality.

Ask a specific question about this device

The AirSoft F15 is a noninvasive accessory used for channeling airflow (with or without supplemental oxygen) to a patient from a positive airway pressure (PAP) device such as continuous positive airway pressure (CPAP) or bilevel system.

The AirSoft F15 is:
• to be used by patients (weighing >66 lb (30 kg)) for whom positive airway pressure therapy has been prescribed
• intended for single-patient reuse in the home environment and multipatient reuse in the hospital/institutional environment.

The AirSoft F15 Mask system is an externally placed mask covering the mouth and the nose of the patient. It provides a seal such that positive pressure from a positive pressure source is directed to the patient's nose and/or mouth. It is held in place with an adjustable headgear that straps the mask to the face.
AirSoft F15 can be cleaned by the patient in the home environment and reprocessed by professionals in the hospital/institutional environment.
AirSoft F15 is intended to be used under the conditions and purposes indicated in the labelling provided with the product.
AirSoft F15 is a prescription device supplied non-sterile.

The provided text is a 510(k) summary for the ResMed AirSoft F15, a vented full-face mask. It describes the device, its intended use, and a comparison to predicate devices, focusing on non-clinical performance data to demonstrate substantial equivalence.

Here's the information requested, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state numerical acceptance criteria in a separate section. Instead, the performance evaluations are broadly stated as demonstrating "substantial equivalence" to predicate devices. The key performance areas evaluated and their outcomes are:

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

The document does not specify a separate "test set" and its sample size in the context of clinical trials or human subject testing. The performance data presented appears to be derived from non-clinical bench testing. The data provenance is not explicitly stated beyond being "extensive testing performed." It is implied to be internal testing conducted by ResMed Ltd in Australia ("ResMed Ltd, 1 Elizabeth Macarthur Drive, Bella Vista NSW 2153 Australia"). The data is retrospective in the sense that it was collected and analyzed to support the 510(k) submission.

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

This information is not applicable as the evaluations were primarily non-clinical bench tests and did not involve a test set requiring expert-established ground truth in the context of medical image interpretation or clinical outcomes. The "ground truth" for these engineering tests would be derived from physical measurements and established engineering standards.

4. Adjudication Method for the Test Set

This information is not applicable as the performance evaluations were non-clinical bench tests and did not involve human interpretation or a need for adjudication.

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

No, an MRMC comparative effectiveness study was not done. The document explicitly states: "Use of Full Face masks with CPAP or Bilevel therapy equipment is proven technology and is well accepted by the medical community. So was the case for the predicate devices, bench testing was sufficient to demonstrate substantial equivalence to the predicate devices."

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

This question is not applicable to this device. The ResMed AirSoft F15 is a physical medical device (a mask), not an AI algorithm. Therefore, "standalone" performance in the context of AI is not relevant.

7. The Type of Ground Truth Used

For the non-clinical tests, the "ground truth" was established through:

• Engineering and physical measurements: For pressure-flow characteristics, flow impedance, CO2 washout, mechanical integrity.
• ISO standards and FDA guidance: For biocompatibility evaluations (e.g., ISO 10993-1, FDA guidance #G95-1).
• Validated protocols: For cleaning and reuse validation.

8. The Sample Size for the Training Set

This information is not applicable. The device is a physical mask and does not involve a training set as would be used for an AI algorithm.

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

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

Ask a specific question about this device

The Astral 100/150 provides continuous or intermittent ventilatory support for patients weighing more than 5kg (11 lb) who require mechanical ventilation. The Astral device is intended to be used in home, institution/hospital and portable applications for both invasive and non-invasive ventilation.

The Astral ventilator system uses a micro-processor controlled blower, which, along with valves and pressure and flow sensors, achieves pressure, flow and time regulation of air delivery. Air is directed to the patient via one of three ventilator breathing circuits; double circuit, single circuit with expiratory valve, or single circuit with intentional leak. Supplemental oxygen can be entrained at the inlet to the main turbine. The device provides both therapeutic and technical alarms, and a user interface allowing adjustment of clinical parameters and display of monitored clinical data. The Astral can use external AC or DC power supply and contains an integrated battery.

The Astral is capable of providing the following types of ventilatory support:

• Assist/Control and SIMV with either volume or pressure control
• Continuous Spontaneous Ventilation in either Pressure Support or CPAP
• Volume Assurance and Apnea Ventilation

Acceptance Criteria and Study for Astral 100/150 Ventilator

The provided documentation details the non-clinical performance evaluation of the Astral 100/150 ventilator to establish its substantial equivalence to predicate devices (Respironics Trilogy 200 and Pulmonetic LTV 1200).

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document states that "All tests confirmed the product met the predetermined acceptance criteria." The specific numerical or qualitative values for these criteria are not provided in this summary but are implied to have been met for substantial equivalence.

2. Sample Size and Data Provenance

• Sample Size for Test Set: Not explicitly stated. The document refers to "Design and Verification activities" and "non-clinical side-by-side performance testing" for each therapy mode and supplementary feature. This suggests a comprehensive, but unquantified, series of tests.
• Data Provenance: The study was conducted as part of the device's design and verification by ResMed Corp., in San Diego, CA, USA. This indicates the testing was performed internally by the manufacturer, likely in a controlled laboratory environment. The data would be prospective as it was generated specifically for the 510(k) submission to demonstrate compliance.

3. Number of Experts and Qualifications for Ground Truth

• This information is not applicable as the study was a non-clinical performance evaluation of a medical device (ventilator). Ground truth in this context would refer to the established engineering specifications, performance standards, and the capabilities of the predicate devices, rather than expert interpretation of clinical data. The performance was assessed against these known standards and functional requirements.

4. Adjudication Method for the Test Set

• This information is not applicable. As a non-clinical performance study, there would be no human "adjudication" in the sense of resolving disagreements among experts on clinical findings. Performance was assessed against predefined technical specifications and standards using objective measurements.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• No, a multi-reader multi-case (MRMC) comparative effectiveness study was not performed. The document explicitly states: "Clinical testing was not required." The evaluation was entirely non-clinical and focused on device performance against technical standards and comparison to predicate devices, not on human-in-the-loop performance or clinical outcomes.

6. Standalone (Algorithm Only) Performance Study

• Yes, a standalone performance study was done in the sense that the device's performance was evaluated independently without human intervention during the technical tests. The "Design and Verification activities" and "non-clinical side-by-side performance testing" assessed the device's inherent mechanical and software-driven functionalities (e.g., accuracy of volume/pressure controls, waveform generation, triggering, alarms). This is implicitly a standalone performance evaluation of the device as an engineered system.

7. Type of Ground Truth Used

• The ground truth used was based on established engineering specifications, performance standards, and the known operational characteristics of the predicate devices. The testing confirmed that the Astral device met "predetermined acceptance criteria" and demonstrated "substantially equivalent" performance to the predicates. This encompasses:
  • Applicable FDA guidance documents (e.g., Draft Reviewer Guidance for Ventilators, Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices).
  • International standards (e.g., ASTM F 1246-91, ASTM F 1100-90, ISO 10651-2:2004, IEC 60601-1:2005, IEC 60601-1-2:2007).
  • The performance characteristics and range/accuracy of the predicate devices (Respironics Trilogy 200 and Pulmonetic LTV 1200).

8. Sample Size for the Training Set

• This information is not applicable. The Astral 100/150 is a medical device (ventilator) that relies on micro-processor controlled mechanics and software for its operation. It is not an AI/machine learning algorithm that requires a "training set" in the conventional sense. The "software based pressure, flow and time regulation" is developed through engineering and control system design, not through machine learning from data.

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

• This information is not applicable as there was no AI/machine learning training set. The "ground truth" for the device's design and functional parameters would have been established through established engineering principles, physics, medical requirements for ventilation, and regulatory standards.

Ask a specific question about this device

The S9 Cronulla for Her self-adjusting system is indicated for the treatment of mild to moderate obstructive sleep apnea (OSA) in female patients weighing more than 66 lb (30 kg).

The S9 Cronulla for Her self-adjusting system is intended for home and hospital use.

The 'S9 Cronulla for Her' contains a Micro-processor controlled blower (flow generator) system that generates Continuous Positive Airway Pressure (CPAP) from 4-20 cmHzO as required to maintain an "air splint" for effective treatment of OSA. The system comprises the flow generator, patient tubing (standard, or heated), mask (patient interface) and humidifier. The 'S9 Cronulla for Her' System (S9 Cronulla for Her with HumidAire 5i) retains all the same hardware and performance features of the predicate device. Key features include in-line power supply, HumidAire 5i, tubing (heated and standard options) and colour LCD for better user interface.

The 'S9 Cronulla for Her' flow generator includes three therapy modes. These include:

• CPAP mode - the device delivers a continuous positive airway pressure throughout the entire therapy session
• AutoSet mode the device automatically adjusts pressure in response to inspiratory flow limitation, snore and apnea.
• AutoSet for Her mode -- the device automatically adjusts pressure in response female-specific OSA characteristics.

The functional characteristics of the S9 Cronulla for Her system includes all the clinician and user friendly features of the predicate device which have been verified during usability studies in accordance with IEC 62366 Medical devices - Application of usability engineering to medical devices.

This document describes the regulatory submission for the ResMed S9 Cronulla for Her, a non-continuous ventilator (IPPB) designed for the treatment of mild to moderate obstructive sleep apnea (OSA) in female patients. The submission aims to demonstrate substantial equivalence to a predicate device, the S8 Aspen (K091947), by incorporating a new treatment mode called AutoSet for Her (AfH).

Here's an analysis based on your requested criteria:

1. Table of Acceptance Criteria and Reported Device Performance

The submission does not provide a formal table of specific, quantitative acceptance criteria for the clinical trial, nor does it explicitly list corresponding "reported device performance" against those criteria. Instead, it describes the primary endpoints and outcomes as "met" and generally discusses improvements and lack of significant differences.

However, based on the text, the implicit acceptance criteria for the clinical trial were demonstrating non-inferiority or efficacy in treating female OSA patients, with key outcomes being Apnea-Hypopnea Index (AHI) and Oxygen Desaturation Index (ODI). The non-clinical testing had "predetermined acceptance criteria" for pressure stability, response to apneas, and response to flow limitations and snore, which were reportedly met.

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

• Sample Size: The document does not specify the exact sample size for the clinical trial. It refers to "female OSA patients" without providing a number.
• Data Provenance: The clinical trial was a "single-blind, randomised, cross-over non-inferiority study." It does not explicitly state the country of origin, but ResMed Ltd is based in Australia, and their official contact for the submission is in the US, suggesting a multinational context or at least compliance with international standards. The study design is prospective.

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

This information is not provided in the submission. The clinical trial was a direct comparison of two algorithms in patients, with outcomes (AHI, ODI, sleep parameters) likely derived from polysomnography (PSG) data, which is objectively measured. The "ground truth" here would thus be the objective physiological measurements of OSA, rather than an expert interpretation of, for example, medical images.

4. Adjudication Method for the Test Set

This information is not explicitly provided. Given the nature of objective physiological measurements (AHI, ODI) as primary endpoints in a clinical trial, a complex adjudication method by multiple experts is less common than for subjective assessments or image interpretation. The study was single-blind, randomized, and cross-over.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance

• MRMC Study: No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. This submission describes a clinical trial comparing two algorithms for a medical device (a ventilator), not an AI algorithm assisting human readers in interpreting medical data.

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

Yes, the clinical trial directly compared the performance of two algorithms: the new AutoSet for Her algorithm (AfH) against the standard AutoSet algorithm (predicate device's algorithm). This is a standalone comparison of the algorithms' effectiveness in treating OSA in female patients, without direct human intervention in the algorithm's diagnostic or therapeutic decision-making process. The device operates automatically based on these algorithms.

7. The Type of Ground Truth Used

The ground truth for the clinical trial was objective physiological measurements related to obstructive sleep apnea, specifically:

• Apnea-Hypopnea Index (AHI)
• Oxygen Desaturation Index (ODI)
• Other sleep parameters (e.g., flow limitation, REM sleep percentage, RERAs)

This data is typically derived from polysomnography (PSG), which directly measures these physiological events.

8. The Sample Size for the Training Set

The submission does not specify a "training set" size. The "AutoSet for Her" mode is an additional treatment software mode based on specific OSA characteristics in females. While algorithms are typically developed using data, the document does not detail the development or training process for this particular algorithm beyond stating it's a "modified AutoSet algorithm." The focus of the clinical trial is on validating its performance, not on describing its development data.

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

This information is not provided as the submission focuses on the clinical validation of the device and its new mode, not the detailed development of the algorithm itself. It's implied that the algorithm was designed to respond to "female-specific OSA characteristics," suggesting that development would have been based on clinical understanding and data related to these characteristics, likely derived from sleep studies and medical research.

Ask a specific question about this device

The AirFit™ N10 channels airflow noninvasively to a patient from a positive airway pressure (PAP) device such as a continuous positive airway pressure (CPAP) or bilevel device.
The AirFit™ N10 is:
to be used by patients (> 66 lb/30 kg) for whom positive airway pressure has been prescribed
intended for single-patient re-use in the home environment and multipatient re-use in the hospital / institutional environment.

The AirFit™ N10 is an externally worn mask that provides an air seal, such that air flow from a positive pressure source is directed to the patient's nose. The mask is held in place with an adjustable headgear. It connects to a conventional PAP device air delivery hose via a standard 22mm swivel. The mask may be cleaned with mild soap.
continuous air leak to prevent rebreathing of dead space CO2
AirFit™ N10 is a prescription device supplied non-sterile.

Here's an analysis of the provided text regarding the AirFit™ N10 Traditional 510(k) submission, focusing on the acceptance criteria and the study used to demonstrate equivalence.

It's important to note that this document is a 510(k) summary, which focuses on demonstrating substantial equivalence to predicate devices rather than proving specific device performance against strict, novel acceptance criteria in a clinical study. Therefore, some of the requested information (especially for AI/ML device evaluations like MRMC studies, specific expert qualifications for ground truth, and separate training/test sets with large sample sizes) is not applicable or directly available in this type of submission for a physical medical device.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size for Test Set: Not explicitly stated as a separate "test set" in the context of clinical data for performance evaluation. The evidence is based on bench testing of the device itself, rather than a dataset of patient cases. For the cleaning/disinfection tests, the testing involved a single device (or set of components) undergoing 20 cycles. Biocompatibility tests would involve material samples.
• Data Provenance: The data is from bench testing conducted by ResMed Ltd. The country of origin for the testing itself is not specified but would presumably be associated with the manufacturer's R&D facilities. This is a prospective assessment of the manufactured device.

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

• Not Applicable: This device is a physical mask, and the evaluation is based on objective, quantifiable physical and material properties (CO2 washout, pressure-flow, mechanical integrity, biocompatibility). Clinical "ground truth" established by experts in the typical sense for AI/ML devices is not relevant here. The evaluation relies on established engineering and material science standards.

4. Adjudication Method for the Test Set

• Not Applicable: There was no "adjudication" of expert opinions for a test set as this was not an AI/ML device or a clinical observational study requiring such consensus. The acceptance criteria are based on objective pass/fail thresholds for physical properties.

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

• No: No MRMC comparative effectiveness study was done. This type of study focuses on human reader performance with and without AI assistance, which is irrelevant for a physical CPAP mask.

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

• Not Applicable: This is not an algorithm or software device. The "standalone" performance refers to the device's physical function as outlined in the bench tests.

7. The Type of Ground Truth Used

• For the physical/material tests, the "ground truth" aligns with:
  • Objective Measurement Standards: e.g., defined CO2 levels, pressure differentials, physical integrity thresholds, and chemical properties for biocompatibility.
  • Comparative Equivalence: Demonstrating that the device performs "substantially equivalent" to predicate devices as measured by these objective standards.

8. The Sample Size for the Training Set

• Not Applicable: There is no "training set" in the context of an AI/ML algorithm for this physical device submission. The design and development of the device would involve iterative testing and refinement, but this is distinct from "training data" for a machine learning model.

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

• Not Applicable: As there's no training set for an AI/ML algorithm, this question is not relevant. The "ground truth" during device development (design, prototyping, and early testing) would be based on engineering specifications, user needs, and established medical device standards.

Ask a specific question about this device