Search Results

AirFit F20 Mask System:

The AirFit F20 mask has two product variants:

• AirFit F20 mask is intended for single-patent reuse in the home environment.
• AirFit F20 SLM (Sleep Lab Mask) variant is intended for multi-patient reuse in the hospital/institutional environment.

Both masks are intended for patients weighing more than 66lb (30kg), who have been prescribed non-invasive CPAP or bi-level positive airway pressure (PAP) therapy. The Sleep Lab Mask is the only variant that is validated and intended for multi-patient reprocessing and must be reprocesssed if reused between patients.

AirFit F20 NM Mask System:

The AirFit F20 Non Magnetic mask has two product variants:

• The AirFit F20 Non Magnetic variant is intended for single-patient reuse in the home environment.
• The AirFit F20 Non Magnetic SLM (Sleep Lab Mask) variant is intended for multi-patient reuse in the hospital/institutional environment.

This mask is for patients weighing more than 66 lb (30 kg), who have been prescribed non-invasive CPAP or bi-level positive airway pressure (PAP) therapy. The Sleep Lab Mask is the only variant that is validated and intended for multi-patient reprocessing and must be reprocessed if reused between patients.

The AirFit F20 and AirFit F20 NM Mask Systems are both full-face masks intended for use with Continuous Positive Airway Pressure (CPAP) and/or Bi-Level devices. CPAP & Bi-Level devices are used for the treatment of Obstructive Sleep Apnea (OSA) and/or ventilatory support. Both treatments deliver pressurized air from a flow generator to the patient. Such delivery of pressurized air relies on the Patient Interface; commonly known as the mask. Full face masks are a common type of Patient Interface (Mask) and are known to efficaciously support the delivery of pressurized air by providing a seal around the patient's nose and mouth.

The AirFit F20 mask system has two product variants:

• AirFit F20 Mask: This is the home use variant that is intended for single patient re-use.
• AirFit F20 SLM (sleep lab mask): This is the variant that is intended for multi-patient re-use and must be reprocessed if reused between patients using the disinfection guide.

AirFit F20 (K170924) had a "For Her" variant which was cleared with aesthetic colour pops, the AirFit F20 Mask and AirFit F20 SLM also have the same "For Her" variant.

The AirFit F20 NM mask system has two product variants:

• AirFit F20 NM Mask: This is the home use variant that is intended for single patient re-use.
• AirFit F20 NM SLM (sleep lab mask): This is the variant that is intended for multi-patient re-use and must be reprocessed if reused between patients using the disinfection guide.

The AirFit F20 and AirFit F20 NM Mask Systems share a common design architecture as the predicate AirFit F20 (K170924), except that the AirFit F20 NM Mask System has non-magnetic clips.

The AirFit F20 and AirFit F20 NM mask systems are made up of the following four main component assemblies: cushion, elbow, frame, and headgear. The cushion and headgear are available in various sizes to allow for adequate mask fit over the intended patient population.

The AirFit F20 and AirFit F20 NM mask systems are prescription devices supplied non-sterile.

The provided FDA 510(k) clearance letter and associated summary pertain to the AirFit F20 Mask Systems, which are non-continuous ventilators (CPAP/Bi-Level masks). This type of device does not typically involve complex diagnostic algorithms or AI components that would necessitate the study structure outlined in your request (e.g., test sets, ground truth, expert adjudication, MRMC studies, standalone performance for AI).

Instead, the clearance is based on demonstrating substantial equivalence to a predicate device (AirFit F20, K170924) through non-clinical performance and safety testing, adherence to recognized standards, and biocompatibility evaluations.

Therefore, many of the specific questions you've asked cannot be directly answered from this document as they are not relevant to the type of device and clearance process involved.

Here's an attempt to extract the relevant information and address your questions where possible:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a "table of acceptance criteria" with corresponding "reported device performance" in a format typically used for diagnostic algorithm validation. Instead, it compares specific design parameters and performance characteristics of the new devices (AirFit F20 Mask System and AirFit F20 NM Mask System) against the predicate device (AirFit F20, K170924). The "Comments" column often indicates that the performance is "Equivalent" or "Identical," implying that the new devices meet or perform similarly to the established safety and performance profile of the predicate, which serves as the de facto acceptance benchmark.

Here's a summary derived from the comparison table (Pages 9-12 of the provided document):

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

The document states that "Non-clinical verification and validation testing completed for the AirFit F20 and AirFit F20 NM Mask Systems demonstrated that the mask systems met all intended performance requirements." This primarily refers to bench testing and in-vitro studies.

• Sample Size: Not explicitly stated as a number of "cases" or "patients" in the context of diagnostic performance. For physical device performance, testing involves multiple units of the product to ensure consistency and reliability, but specific sample sizes for tests (e.g., number of masks tested for exhaust flow, CO2 rebreathing, resistance) are not detailed in this summary.
• Data Provenance: This is not a clinical study in the typical sense. The data comes from non-clinical bench testing conducted by the manufacturer (ResMed Pty Ltd, Australia, with a US office). It is not retrospective or prospective patient data from a particular country, but rather laboratory test results.

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

This question is not applicable. The device is a medical mask system, not a diagnostic algorithm that requires expert interpretation for a "ground truth." The "ground truth" for performance is established by recognized international standards (e.g., ISO 17510:2015 for mask performance, ISO 10993 for biocompatibility) and engineering specifications. Compliance is measured against these standards, not expert consensus on medical images or diagnoses.

4. Adjudication method for the test set

This question is not applicable for the same reasons as #3. Performance is determined by objective measurements against established standards.

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 question is not applicable. This clearance is for a physical medical device (CPAP/Bi-Level mask), not an AI-powered diagnostic tool. There are no "human readers" or "AI assistance" in the context described for this device.

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

This question is not applicable. This is not an algorithm or AI device.

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

The "ground truth" for this device's performance is based on:

• Compliance with international standards: For physical performance (e.g., CO2 rebreathing, exhaust flow, resistance, AAV pressures, sound) as defined by ISO 17510:2015 and other relevant ISO standards.
• Biocompatibility testing: According to ISO 10993 series and ISO 18562 series.
• Mechanical integrity testing: To ensure durability after various environmental stressors (home cleaning, transport, storage, operation, free fall, reprocessing).
• Cleaning and reprocessing validation: Against standards like ISO 17664-1, ISO 17664-2, ST98, and AAMI TIR12.

Essentially, the ground truth is objective measurement against established engineering and safety standards.

8. The sample size for the training set

This question is not applicable. There is no "training set" as this is not a machine learning or AI algorithm.

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

This question is not applicable for the same reasons as #8.

Ask a specific question about this device

AirFit F30i Mask System
The AirFit F30i mask has two product variants:
· AirFit F30i mask is intended for single-patent reuse in the home environment.
• AirFit F30i SLM (Sleep Lab Mask) variant is intended for multi-patient reuse in the hospital/institutional environment. Both masks are intended for patients weighing more than 66lb (30kg), who have been prescribed non-invasive CPAP or bi-level positive airway pressure (PAP) therapy. The Sleep Lab Mask is the only variant that is validated and intended for multi-patient reprocessing and must be reprocesssed if reused between patients.

AirFit F30i NM Mask System
The AirFit F30i Non Magnetic mask has two product variants:
· The AirFit F30i Non Magnetic variant is intended for single-patient reuse in the home environment.
· The AirFit F30i Non Magnetic SLM (Sleep Lab Mask) variant is intended for multi-patient reuse in the hospital/institutional environment.
This mask is for patients weighing more than 66 lb (30 kg), who have been prescribed non-invasive CPAP or bi-level positive airway pressure (PAP) therapy. The Sleep Lab Mask is the only variant that is validated and intended for multipatient reprocessing and must be reprocessed if reused between patients.

Arcadia Mask System
The Arcadia has two product variants:
· Arcadia mask is intended for single-patient reuse in the home environment.
· Arcadia SLM (Sleep Lab Mask) variant is intended for multi-patient reuse in the hospital/institutional environment.
These masks are intended for patients weighing more than 66 lb (30kg), who have been prescribed non-invasive CPAP or bi-level positive airway pressure (PAP) therapy. The Sleep Lab Mask is the only variant that is validated and intended for multi-patient reprocessing and must be reprocesssed if reused between patients.

The AirFit F30i, AirFit F30i NM and Arcadia mask systems are full-face conduit masks intended for use with Continuous Positive Airway Pressure (CPAP) and/or Bi-Level devices are used for the treatment of Obstructive Sleep Apnea (OSA) and/or non-life supporting ventilatory support. Both treatments deliver pressurized air from a flow generator to the patient. Such delivery of pressurized air relies on the Patient Interface; commonly known as the mask. Full face masks are a common type of Patient Interface (Mask) and are known to efficaciously support the delivery of pressurized air by providing a seal around the patient's nose and mouth.
The AirFit F30i, AirFit F30i NM and Arcadia mask systems each have two product variants:

• . AirFit F30i Mask/ AirFit F30i NM Mask/ Arcadia Mask: This is the home use variant that is intended for single patient re-use.
• . AirFit F30i SLM/ AirFit F30i NM SLM/ Arcadia SLM (sleep lab mask): This is intended for multipatient re-use and must be reprocessed if reused between patients using the disinfection guide
  The AirFit F30i, AirFit F30i NM and Arcadia mask systems are made up of the following four main component assemblies: Cushion, conduit frame, elbow and headgear. The cushion and conduit frame are available in various sizes to allow for adequate mask fit over the intended patient population.
  The AirFit F30i, AirFit F30i NM and Arcadia mask systems are prescription devices supplied non-sterile.

The provided text does not contain detailed information about the acceptance criteria or a specific study that proves the device meets those criteria in the format requested. The document is a 510(k) summary and FDA clearance letter, which outlines the device's substantial equivalence to a predicate device based on various performance and safety tests. However, it does not provide the specific "acceptance criteria" (e.g., minimum sensitivity, specificity, or accuracy thresholds) or the detailed methodology and results of a single study with the requested metrics.

Instead, the document lists several non-clinical data submitted, which include performance and safety tests in accordance with ISO standards and other bench tests. The conclusion states that "Non-clinical verification and validation assessment/testing demonstrated that AirFit F30i NM and Arcadia mask systems met all intended performance requirements." and "Verification confirmed that the new device met the predetermined acceptance criteria and the performance is substantially equivalent to the previously cleared predicate AirFit F30i mask system (K183512)."

Therefore, I can extract the types of tests performed and the comparison to the predicate device, but I cannot fill in the table or answer all sub-questions as the specific numerical acceptance criteria and a single "study" proving it with the requested detail are not present.

Here's what can be extracted based on the provided text, with an explanation for missing information:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are generally qualitative (e.g., "met all intended performance requirements") and tied to ISO standards or established performance of the predicate device. Specific numerical thresholds for acceptance are not explicitly listed in the 510(k) summary, except for some comparative parameters.

Detailed numerical acceptance criteria for each test (e.g., "CO2 rebreathing must be less than X%") are not explicitly provided, but the document confirms that the devices "met all intended performance requirements" and "predetermined acceptance criteria." The performance characteristics are compared to the predicate device, often indicating "Equivalent" or "Identical."

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

• Sample Size: Not specified for any of the tests. The document refers to "non-clinical verification and validation assessment/testing."
• Data Provenance: Not specified. These appear to be laboratory-based bench tests or in-house engineering tests. There is no indication of country of origin for data or if it's retrospective/prospective.

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 as the tests described are non-clinical, bench-top performance and safety evaluations, not typically requiring expert-driven ground truth establishment in the way clinical studies with diagnostic devices might.

4. Adjudication method for the test set

• This information is not applicable for the non-clinical, bench-top tests described.

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

• This information is not applicable. The device is a CPAP mask system, not an AI-assisted diagnostic or interpretive tool. Therefore, MRMC studies involving human readers and AI are not relevant.

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 device (CPAP mask system), not a software algorithm or AI.

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

• For the non-clinical tests described, the "ground truth" is typically defined by established engineering standards (e.g., ISO 17510:2015 parameters, pressure measurements, flow rates, CO2 concentration readings) and reference methods. For biocompatibility and reprocessing, it's based on validated test methods and safety thresholds defined by relevant ISO and AAMI standards.

8. The sample size for the training set

• This information is not applicable. The device is a physical medical device; there is no indication of a "training set" in the context of an algorithm or AI.

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 Oran Park mask is intended for use in the home or hospital/institutional environment on patients weighing more than 661b (30kg), who have been prescribed non-invasive CPAP or bi-level positive airway pressure (PAP) therapy.

Only the Sleep Lab Mask (SLM) variant is intended and validated for multi-patient reuse and must be reprocessed if reused between patients.

The Oran Park Mask is an accessory to deliver air flow and positive air pressure generated by positive airway pressure (PAP) devices such as CPAP or bi-level flow generator systems to the patient's airway, for the treatment of Obstructive Sleep Apnea (OSA) or ventilator support (non-life support). It delivers the treatment pressure from the source device to the patient's upper airway by providing an air seal between the PAP device and under the patient's nose and mouth.

There are 2 variants to the Oran Park Mask:

• . Oran Park Mask (Home Use) Intended for single patient re-use (SPMU) for home use. It is configured with a diffused venting port located on the elbow, known as the QuietAir elbow.
• . Oran Park SLM (Sleep Lab Mask)

Intended for multi-patient re-use (MPMU) and must be reprocessed if reused between patients. It is configured with a non-diffused venting port located on the elbow, known as the Multihole elbow.

The Oran Park mask comprises of 4 sub-assemblies: headgear, frame, cushion and elbow. The venting ports and anti-asphyxia valve are incorporated into the elbow assembly. There are four magnets incorporated in the Oran Park mask – two magnets in the frame assembly and 2 magnets in the lower headgear clips – with a magnetic field strength up to 400 mT. The mask help facilitate attaching and detaching the headgear to the mask frame when regularly fitting the mask for use. The cushion and headgear are available in various sizes to fit a wide patient population. Soft wraps, which are attached to the Oran Park mask frame, are available as an optional accessory for patient's comfort.

The Oran Park mask is a prescription device and is supplied non-sterile.

The Oran Park Mask is a medical device accessory used to deliver airflow and positive air pressure from PAP devices for the treatment of Obstructive Sleep Apnea or ventilator support. The device underwent non-clinical testing to demonstrate its performance and safety, aiming to prove substantial equivalence to the predicate device, AirFit F20 (K153563).

Here's an analysis of the acceptance criteria and the study that proves the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance:

The document presents a comparison table between the predicate device (AirFit F20, K153563) and the subject device (Oran Park Mask System) for various design parameters and features. The "Comments" column often indicates the acceptance criteria for the subject device by stating "Equivalent," "Identical," or referencing compliance with specific ISO standards.

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

The document describes non-clinical verification and validation testing. This type of testing typically involves bench tests on manufactured devices rather than studies on human subjects. Therefore, the concept of "test set" in the context of patient data, sample size of patients, and data provenance (country of origin, retrospective/prospective) is not applicable here. The tests are performed on the device prototypes or production samples in a laboratory setting. No information is provided regarding the number of units tested for each non-clinical test.

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

This information is also not applicable as the study described is non-clinical, involving engineering and performance testing against established standards and predicate device performance, not clinical interpretation requiring expert ground truth establishment.

4. Adjudication Method (2+1, 3+1, none) for the Test Set:

This information is not applicable for the same reasons as points 2 and 3. Non-clinical bench testing does not involve adjudication methods used in clinical studies.

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 is not applicable. The device, an Oran Park Mask, is a physical patient interface for respiratory therapy. It is not an AI-powered diagnostic or assistive tool, so an MRMC study comparing human reader performance with and without AI assistance would not be relevant.

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

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

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

For the non-clinical tests, the "ground truth" or reference for acceptance was primarily:

• International Standards: Specifically ISO 17510:2015 (Medical devices – Sleep apnoea breathing therapy – Masks and application accessories), ISO 10993 series (Biocompatibility), ISO 18562 series (Biocompatibility of breathing gas pathways), ISO 5356-1 (Conical connectors), etc.
• Performance of the Predicate Device: The AirFit F20 (K153563) served as a direct comparison for various parameters to establish substantial equivalence.
• Predetermined Acceptance Criteria: These are likely internal specifications derived from the standards and predicate device performance, ensuring safety and effectiveness.

8. The Sample Size for the Training Set:

This is not applicable as there is no "training set" in the context of non-clinical device testing for a physical mask. Device design and validation follow engineering and regulatory processes, not machine learning training.

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

This is not applicable for the reasons stated in point 8.

Ask a specific question about this device

The Whitsundays Mask System has two product variants:
• Whitsundays mask
· Whitsundays SLM (Sleep Lab Mask)
Both masks are intended for patients weighing more than 66 lb (30 kg), who have been prescribed non-invasive CPAP or bi-level positive airway pressure (PAP) therapy. The Whitsundays mask is intended for single-patient reuse in the home environment and the Whitsundays SLM is intended for multi-patient reuse in the hospital/institutional environment. The Sleep Lab Mask (SLM) is the only variant that is validated and intended for multi-patient reprocessing and must be reprocessed if reused between patients.

The Whitsundays Mask System is an accessory to deliver airflow and positive air pressure generated by positive airway pressure (PAP) devices such as CPAP or bi-level flow generator systems to the patient's airway, for the treatment of Obstructive Sleep Apnea (OSA) or ventilatory support (non-life support). It delivers the treatment pressure from the source to the patient's upper airway by providing an air seal between the PAP device and the bottom of the patient's nose.
The Whitsundays mask system has two product variants:

• Whitsundays mask This is the home use variant that is intended for single patient re-use.
• . Whitsundays SLM (Sleep Lab Mask) This is the SLM variant that is intended for multi-patient re-use and must be reprocessed if reused between patients.
  The Whitsundays Mask System is made up of 4 main component assemblies: nasal cushion, conduit frame, elbow, and headgear. The nasal cushion and conduit frame are available in various sizes to allow for adequate mask fit in the intended patient population.
  The Whitsundays Mask System is a prescription device supplied non- sterile.

The provided text describes the ResMed Whitsundays Mask System and its substantial equivalence to a predicate device, the Scone mask (K180497). The document focuses on non-clinical data and acceptance criteria based on recognized standards.

Here's the breakdown of the acceptance criteria and the study information:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document refers to "non-clinical verification and validation testing" and "bench tests" for performance characteristics. The specific sample sizes for these tests are not provided in the summary.

The data provenance is from bench testing conducted by ResMed Pty Ltd. This is a form of prospective testing, as it involves newly manufactured devices undergoing controlled experiments. The country of origin for the company is Australia.

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

This information is not provided in the document. The studies are primarily engineering and performance tests against recognized standards (e.g., ISO, rather than clinical studies requiring expert ground truth for interpretation like imaging).

4. Adjudication method for the test set

Not applicable. The evaluations are based on quantifiable measurements against established standards (e.g., flow rates, pressure drops, CO2 levels) rather than subjective assessments requiring adjudication.

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 is not applicable. The device is a medical mask and not an AI-powered diagnostic or assistive tool for human readers.

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

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

7. The type of ground truth used

The "ground truth" for the non-clinical tests is established by international standards such as ISO 17510:2015, ISO 18562, ISO 10993, and ISO 17664. These standards define the acceptable performance limits and methodologies for testing. For some parameters like physical dead space, the "ground truth" is the measured value of the predicate device, against which the new device's measurements are compared for equivalence.

8. The sample size for the training set

This is not applicable. The device is a physical medical mask, not a machine learning model that requires a training set.

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

This is not applicable for the same reason as above.

Ask a specific question about this device

The S10 Kirra is indicated to provide CPAP and Bi-level therapy for the treatment of obstructive sleep apnea (OSA) in patients (female patients with mild to moderate OSA when using AfH treatment mode) weighing more than 66 lb (30 kg). ASV and ASVAuto modes are also indicated for the treatment of central and/or mixed apneas, or periodic breathing. It is intended for home and hospital use.

The S10 Kirra is a prescription only Positive Airway Pressure (PAP) ventilator device intended to treat individuals that are diagnosed with sleep apnea conditions. The S10 Kirra uses a micro-processor controlled blower, along with pressure and flow sensors, to achieve pressure, flow and time regulation of air delivery. It includes optional humidification, with air delivery to the patient via heated or non-heated breathing circuits. The device provides both therapeutic (e.g. tidal volume) and technical data (e.g. system fault), and a user interface allowing adjustment of device parameters. The device uses an external AC power supply, and allows the addition of low flow supplemental oxygen.

The provided text describes the S10 Kirra, a non-continuous ventilator, and its substantial equivalence to predicate devices, but it does not contain the detailed information necessary to answer all parts of your request about acceptance criteria and a specific study proving the device meets them.

The document focuses on demonstrating substantial equivalence to previously cleared predicate devices (S9 Greenhills, S9 Wanda, S9 Elouera), rather than detailing a new study with acceptance criteria for a novel device.

Here's a breakdown of what can be extracted and what is missing:

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

The document states:
"Verification confirmed the S10 Kirra met the predetermined acceptance criteria as defined in the relevant compliance standards and as defined in the system verification protocols."

However, it does not provide a table listing specific acceptance criteria values and the reported performance for each criterion. It broadly mentions areas of testing:

• Pressure performance
• Breath events (flow limitations, snore, apneas)
• Response to periodic breathing
• Humidification

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

This information is not available in the provided text. The document refers to "verification bench testing" and "comparative predicate testing" but does not specify sample sizes for test sets or data provenance (country of origin, retrospective/prospective).

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 available. The document focuses on bench testing and comparison to predicate devices, not human expert evaluations for ground truth.

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

This information is not available. Adjudication methods are typically relevant for studies involving human interpretation or subjective assessments, which are not detailed 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

The document explicitly states:
"Clinical performance data is not required as the subject device uses established therapeutic technology and bench testing is sufficient to demonstrate substantial equivalence."

Therefore, no MRMC comparative effectiveness study was done as the device relies on established technology, and its performance was evaluated through non-clinical bench testing.

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

The entire non-clinical data section describes performance of the device itself (hardware and software), which can be considered a standalone performance assessment in a bench testing environment. The listed performance areas (pressure, breath events, humidification) are intrinsic to the device's function.

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

For the non-clinical bench testing, the "ground truth" would be established by engineering specifications, compliance standards, and the performance characteristics of the predicate devices. The tests evaluate if the S10 Kirra performs according to these pre-defined, measurable engineering and physiological parameters. It is not based on expert consensus, pathology, or outcomes data in the way these terms are typically used for clinical evaluations.

8. The sample size for the training set

This information is not applicable/available. The S10 Kirra is a medical device (ventilator) with microprocessor control, not an AI/machine learning algorithm that requires a "training set" in the computational sense. The device's "training" involves design, engineering, and calibration to meet its specifications, rather than data-driven model training.

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

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

Ask a specific question about this device