Search Results

Intended to reduce or alleviate snoring, mild to moderate Obstructive Sleep Apnea (OSA) while sleeping in adults.

AIO Breathe consists of two separate intraoral trays (upper, lower) that are customized to fit over all the teeth. The device is manufactured at AIOMEGA facilities using additive manufacturing with Stereolithography (SLA) 3D printing technology that builds the device from biocompatible resins. The customized trays are fabricated based on intraoral scans provided by the dentist and the dentist's prescription.

AIO Breathe features right and left protrusive flanges on the buccal sides of the upper tray. These flanges engage with corresponding right and left vertical flanges featured on the buccal sides of the lower tray. This engagement repositions the jaw to reflect the dentist's prescribed anterior mandibular advancement.

Additionally, mandibular plateaus, as prescribed by the dentist, featured on the right, and left occlusal cranial surfaces of lower tray, guide the mandible downward, thus opening the anterior airway. The plateaus and flanges allow vertical opening of the jaw (jaw is not fixed in a single position) and work together to maintain advancement in open and closed mouth positions. This design feature allows more room and creates traction for the tongue to migrate forward. The resulting mechanical protrusion acts to increase the patient's pharyngeal space, improving their ability to exchange air, thereby reducing the tendency to snore and alleviating signs of obstructive sleep apnea.

The provided text is a 510(k) summary for the AIO Breathe device, an intraoral device intended to reduce or alleviate snoring and mild to moderate Obstructive Sleep Apnea (OSA). Crucially, the document explicitly states: "No clinical studies were conducted on AIO Breathe."

Therefore, I cannot provide information regarding acceptance criteria or a study proving the device meets those criteria, as no such study was conducted according to this document. The submission relies on substantial equivalence to a predicate device (Slow Wave DS8 K191320), not on a direct clinical study of AIO Breathe's performance.

If there were a clinical study described, the following information would be extracted and organized as requested:

1. Table of acceptance criteria and reported device performance: This would list specific metrics (e.g., AHI reduction, snoring reduction percentage) with their predefined acceptance thresholds and the results achieved by the AIO Breathe device in the study.

2. Sample size used for the test set and the data provenance: This would state the number of patients/participants in the study and whether the data was collected specifically for this study (prospective) or from existing records (retrospective), and the country of origin.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: This would detail how many independent experts were involved in evaluating patient outcomes and their professional backgrounds (e.g., Board-certified sleep physicians with X years of experience).

4. Adjudication method for the test set: This would describe how discrepancies among experts were resolved (e.g., a third expert reviewed discordant cases).

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done: This would state if human readers were part of the study, and if so, how their performance was measured with and without AI assistance, including the effect size. (Likely not applicable for a physical intraoral device).

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: This would indicate if the device's performance was evaluated purely by itself, without human intervention in its function or interpretation. (Likely not applicable for a physical intraoral device).

7. The type of ground truth used: This would specify the gold standard against which the device's performance was measured (e.g., polysomnography results, patient-reported outcomes).

8. The sample size for the training set: If machine learning was involved in the device's design or functionality, this would state the size of the dataset used to train any algorithms. (Likely not applicable for this type of device).

9. How the ground truth for the training set was established: This would describe the method used to label or categorize the data in the training set for any machine learning components. (Likely not applicable for this type of device).

In summary, based on the provided document, no clinical studies were performed on the AIO Breathe device, and therefore, no acceptance criteria or study results demonstrating its performance are available within this text. The clearance is based on its substantial equivalence to an existing predicate device.

Ask a specific question about this device

The Breathe+ is intended for use as a Positive Expiratory Pressure Device to help prevent or reverse atelectasis in adult patients needing PEP therapy. Intended for single-patient, multi-use in a hospital or home care setting.

The subject device provides PEP only. The subject device is an oral device that provides positive expiratory airway pressures to enhance expiratory muscle strength while preventing and reversing atelectasis. Furthermore, the device is hands-free.

The provided submission for the Breathe+ device, a Positive Expiratory Pressure (PEP) device, does not contain a typical study that proves the device meets specific acceptance criteria in the manner of a clinical trial or algorithm performance study. Instead, it focuses on bench testing and a comparison to predicate and reference devices to demonstrate substantial equivalence for FDA clearance.

Therefore, the following information will be drawn from the provided text regarding the bench testing that was performed for the device. The document does not describe a clinical study with an AI component or expert ground truth adjudication.

Acceptance Criteria and Reported Device Performance (Bench Testing)

Note: The exact acceptance thresholds for "repeatability and accuracy" are not explicitly stated in the document, but the discussion concludes "The device performance was tested and does not raise any new concerns of safety or effectiveness."

Study Details (Bench Testing)

1. Sample size used for the test set and the data provenance: Unspecified number of "final, finished samples" of the Breathe+ device. The data provenance is internal testing performed by PEEP Medical, LLC. It is prospective testing on newly manufactured devices.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. This was bench testing of a physical device's mechanical performance, not an AI or diagnostic study requiring expert ground truth.

3. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable. This was mechanical bench testing.

4. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance: Not applicable. No MRMC study was performed as this is a mechanical medical device, not an AI diagnostic tool.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. This is a mechanical medical device, not an algorithm.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc): The ground truth for the bench testing was based on direct physical measurements of the device's performance, such as pressure readings (cmH2O) at various flow rates (lpm) using calibrated equipment.

7. The sample size for the training set: Not applicable. This refers to bench testing of a physical device.

8. How the ground truth for the training set was established: Not applicable.

Ask a specific question about this device

The device is intended for the spot measurement of respiration rate of an adult patient in a home or clinical setting. It is not a vital signs monitor or an apnea monitor. It should not be used on patients that exhibit uncontrolled limb movement.

Not Found

The provided text does not contain detailed information about the acceptance criteria, the specific study that proves the device meets the acceptance criteria, or the various aspects of the study design such as sample size, data provenance, expert qualifications, or adjudication methods.

The document is an FDA 510(k) clearance letter for the "Breathe Easy Mobile Respiratory Monitor (MRM)," indicating that the device has been found substantially equivalent to a legally marketed predicate device. It defines the "Indications for Use" for the device, stating it's for "spot measurement of respiration rate of an adult patient in a home or clinical setting. It is not a vital signs monitor or an apnea monitor. It should not be used on patients that exhibit uncontrolled limb movement."

However, it does not provide the specific data requested in your prompt regarding acceptance criteria, performance metrics, or study methodology. This type of detailed technical data is typically found in the 510(k) submission summary or associated technical documentation, which is not included in the provided text.

Ask a specific question about this device

The BreatheSuite MDI Device is an electronic device intended for single-patient use of patients 5 years of age and older. It assists patients in recording and monitoring the actuations and technique of prescribed metered dose inhaler (MDI) usage. The BreatheSuite System is composed of the disposable, battery powered, portable BreatheSuite MDI Device and a mobile application.

The BreatheSuite MDI Device is an accessory designed to work with an MDI by attaching to the top of the canister of the inhaler. The BreatheSuite MDI Device does not interfere with regular MDI usage and can be reattached with ease. The BreatheSuite MDI Device does not actuate the inhaler but rather gathers information based on manual MDI usage.

The BreatheSuite MDI Device measures the parameters of MDI use and records them for review by the patient. The BreatheSuite application records, stores, and transmits usage events from the BreatheSuite MDI Device to a remote storage system. Furthermore, BreatheSuite MDI reminds the patient of important steps of MDI use through visual feedback in the BreatheSuite application.

The output of the BreatheSuite System is not intended to diagnose or replace a diagnosis provided by a licensed physician. The BreatheSuite system is not intended for use as a MDI medication dose counter, nor is it intended to indicate the quantity of medication remaining in an MDI. The BreatheSuite MDI Device is not intended to replace a physician's advice or inhaler labels; patients are expected to always follow their doctor's advice and inhaler labels.

The BreatheSuite System can be used both indoors as well as in home and work settings.

The BreatheSuite System may also be used in clinical trials where researchers need to know information about use of a MDI Medication(s) by a participant.

The BreatheSuite MDI Device is a Metered Dose Inhaler (MDI) accessory that monitors inhaler usage and inhaler technique metrics.

The BreatheSuite MDI Device mounts on top of an MDI to measure when and how patients use their inhalers. The device uses internal sensors to record parameters of MDI use and technique including date and time of usage; MDI shaking duration; coordination between MDI actuation and the start of inhalation; and inhalation duration.

By pairing with the BreatheSuite app via Bluetooth Low Energy (BLE) communications, the user receives reports on each inhaler dosage and on their inhalation technique. The user may share their use and technique information with their physicians and/or healthcare providers.

This document, an FDA 510(k) summary for the BreatheSuite MDI Device (K203155), does not describe a study involving an AI/algorithm to improve human reader performance or a standalone algorithm-only performance study. Instead, it focuses on demonstrating the substantial equivalence of the BreatheSuite MDI Device (a hardware accessory for Metered Dose Inhalers) to a predicate device, primarily through non-clinical performance testing.

Therefore, many of the requested details about acceptance criteria for AI and the study proving it are not present in this document.

However, I can extract the acceptance criteria and study information related to the BreatheSuite MDI Device's hardware performance and its comparison to the predicate device.

Acceptance Criteria and Device Performance (for the hardware device)

Based on the "9. Non-Clinical Performance Testing" and "13. Conclusion - Statement of Substantial Equivalence" sections, here's a table summarizing the acceptance criteria (inferred from the testing performed to show equivalence) and the reported device performance:

• ISO 10993-1:2009 (biocompatibility)
• ISO 10993-5:2009 (cytotoxicity)
• ISO 10993-10:2010 (sensitization and intracutaneous irritation). |
  | Electrical Safety: Device must comply with general and home-use electrical safety standards. | The device complies with:
• IEC 60601-1:2012 (general safety)
• IEC 60601-1-11:2015 (home-use safety). |
  | Electromagnetic Compatibility (EMC): Device must comply with EMC standards. | The device complies with:
• IEC 60601-1-2:2014 Ed 4.0
• FCC Part 15 Subpart B & ICES-003:2019 (electromagnetic compatibility). Information was provided according to FDA guidance. |
  | Software Functionality: Software components should be verified and validated for correct functionality and cybersecurity. | Software verification and validation testing was conducted to ensure correct functionality for the BreatheSuite MDI software release, for all software components. Documentation was provided as recommended by FDA guidances. "Software verification demonstrates that the device should perform as intended in the specified use conditions, and equivalently to the predicate for common software functions." |
  | Delivered Dose Uniformity (DDU) & Aerosol Particle Size Distribution (APSD): The device should not adversely affect drug delivery. | DDU and APSD testing confirmed that the addition of the BreatheSuite MDI Device does not have an effect on medication delivery for compatible MDIs. "Inhaler usage parameters are measured with sufficient accuracy for monitoring inhaler use, and the addition of the new sensors does not adversely affect use of the inhaler." |
  | Battery Performance (Shelf Life): Battery shelf life should be substantially equivalent to the predicate. | Battery performance (Shelf Life) testing confirmed substantial equivalence to the shelf life of the predicate. |
  | MDI Compatibility: Compatibility with MDIs should be equivalent to the predicate. | MDI Compatibility testing confirmed substantial equivalence to the predicate in terms of compatible MDIs. |
  | Dose Counting: The device should not inhibit the dose counter on compatible MDIs. | Dose counting testing confirmed the BreatheSuite MDI Device does not inhibit the dose counter on any compatible metered dose inhaler. |
  | Depression Force: The device should not change the actuation force of compatible MDIs. | Depression Force Testing confirmed the BreatheSuite MDI Device does not change the force required to actuate any compatible metered dose inhaler. |
  | Device Fit and Label Obscuration: The device should not permanently obscure the MDI label. | Device Fit and Label Obscuration testing confirmed the BreatheSuite MDI Device does not permanently obscure the MDI label. |
  | Technique Measurement: The device should obtain and record correct technique information (shaking, orientation timing, inhalation duration). | Technique Measurement testing confirmed the BreatheSuite MDI Device obtains and records correct technique information including inhaler shaking, orientation timing and inhalation duration for all compatible MDIs according to requirements. |
  | Usability: The device should be safely and effectively usable, with critical tasks evaluated. | Usability evaluation was carried out to evaluate use scenarios and critical tasks, and established validity of the results obtained from testing carried out in accordance with FDA guidance. "The usability evaluation indicates there are no issues for successful use with the compatible inhaler." |
  | OTC Validation: For Over-The-Counter use, the device and labeling should provide necessary information and not introduce new safety concerns. | Validation testing confirmed the device and its provided OTC labeling provided all necessary information to support over-the-counter use. Hazard Analysis for OTC identified no new safety concerns related to patient interaction with the system (obtaining, learning, registering, installing, using, reviewing data, support). |

Here's the information regarding the study design based on the provided text:

• 1. A table of acceptance criteria and the reported device performance: (See table above)

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

  • The document states "Non-clinical testing and evaluation of the BreatheSuite MDI has been completed..." and lists various tests (Biocompatibility, Electrical Safety, EMC, Software V&V, Performance Testing, Usability).
  • Specific sample sizes for each test are NOT provided in this summary. For example, it does not state how many devices were tested for DDU, or how many users were in the usability study.
  • Data Provenance: The studies were non-clinical, likely conducted in laboratories by the manufacturer or external labs. No information is provided about the country of origin of testing data, or if it was retrospective/prospective studies on patient data as it's a hardware device performance study, not a clinical data study of an AI.

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

  • Not applicable in the context of this 510(k) summary. This document describes performance testing of a physical device and its software's functionality, not an AI interpreting medical images or clinical data. Ground truth for the tests (e.g., whether DDU is affected, if a button registered a press) would be established by the test protocols and instrument readings, not expert consensus on medical interpretation.

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

  • Not applicable. This is not a study involving human interpretation or adjudication of outputs.

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

  • No, an MRMC comparative effectiveness study was not done. This 510(k) is for a hardware device accessory to an MDI, not an AI diagnostic tool that assists human readers.

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

  • While the device has software and "technique measurement" capabilities, the 510(k) does not present these as a standalone AI algorithm that would typically undergo such a performance evaluation (e.g., an algorithm diagnosing a condition). The "standalone" performance here refers to the device's ability to accurately capture defined parameters (shaking, orientation, inhalation duration), which was validated through "Technique Measurement testing." The summary conclusion states: "Inhaler usage parameters are measured with sufficient accuracy for monitoring inhaler use."

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

  • For the physical device and its software functionality, the "ground truth" would be established by:
    • Standardized test methods and calibrated equipment: For tests like DDU, APSD, electrical safety, EMC, depression force, etc., the "ground truth" is derived from measurements against established metrological standards and limits.
    • Design requirements/specifications: For software verification and validation, the ground truth is whether the software performs according to its documented requirements.
    • Observed behavior: For usability, the ground truth relates to successful completion of tasks and identification of use errors, which are observed and evaluated against predefined criteria.

• 8. The sample size for the training set:

  • Not applicable. There is no mention of a "training set" in the context of machine learning/AI for this device. The software "learns" from sensors, not a large training dataset.

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

  • Not applicable, as there is no mention of a training set for an AI/ML model.

Ask a specific question about this device

The Breathe Technologies Life2000™ Ventilation System is intended to provide continuous or intermittent ventilatory support for the care of individuals who require mechanical ventilation.

The Life2000 Ventilation System consists of the Life2000 Ventilator and the Life2000 Compressor.

The System is intended for use by qualified, trained personnel under the direction of a physician. Specifically, the System is applicable for adult patients who require the following types of ventilatory support:

• · Positive Pressure Ventilation, delivered invasively (via ET tube) or non-invasively (via mask).
• · Assist/Control mode of ventilation.

The System is suitable for use in home and institutional settings and is not intended for ambulance or air transportation.

The Breathe Technologies Life2000 Ventilation System includes a portable, battery powered, continuous ventilator that was cleared in K141943 along with the Breathe Pillows Interface, Universal Connector and various other dedicated accessories.

In this submission, the Life2000 Ventilation System is expanding with the inclusion of additional components, including the Life2000 Compressor, a portable air compressor. This Life2000 Compressor provides a primary source of compressed air for the Life2000 Ventilator, in addition to the previously cleared gas sources of facility in-wall compressed gas (air & oxygen) and tanks of compressed medical gas. The Life2000 Compressor provides a dedicated docking station for the Life2000 Ventilator.

The Ventilator administers the physician-prescribed volume to the patient via the previously cleared Breathe Technologies Universal Connector which connects into the patient's tracheostomy tube, endotracheal tube, or any off the shelf non-invasive mask. It can also be used with the previously cleared Breathe Technologies Pillows Interface (K141943), a type of nasal mask.

This submission includes new versions of the Pillows Interface, labeled as the Breathe Pillows Entrainment Interface, that have an inlet for supplemental oxygen. It also includes labeling for the use of third party supplemental Oxygen Adapters for use with the Universal Connector. These inlets or Adapters allow the physician to administer supplemental oxygen into the patient circuit or interface.

Here's a breakdown of the acceptance criteria and study information based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document describes a Breathe Technologies Life2000™ Ventilation System seeking 510(k) clearance, intending to demonstrate substantial equivalence to its predicate device (the previous version of the Life2000 Ventilation System, K141943) and a reference device (Siemens Compressor Mini, K023354). The acceptance criteria are largely implied by compliance with various medical device standards and through bench testing and human factors validation. The "device performance" is primarily assessed against the predicate and reference devices, demonstrating functional equivalence and safety.

Since specific quantitative acceptance criteria with numerical targets and direct performance comparisons are not explicitly laid out in a table in the provided text, I will infer them from the comparisons made to the predicate and reference devices, and the standards listed.

Inferred Acceptance Criteria and Reported Device Performance:

2. Sample Sizes and Data Provenance

• Test Set (Human Factors Validation - HFV): "over 100 participants"

  • Data Provenance: Not explicitly stated, but the context of an FDA submission for a US company (Breathe Technologies, Irvine, CA) suggests the data is likely from the USA and would be prospective as it involves active testing with participants for validation.
  • Test Set (Bench Testing): Not explicitly stated, but typically involves a number of units sufficient to demonstrate design validation and compliance with standards.

• Training Set: Not mentioned in the provided text. The document describes a 510(k) submission, which primarily focuses on demonstrating substantial equivalence to a predicate device through testing and comparison, rather than developing a new algorithm/AI from a training set.

3. Number of Experts and their Qualifications (for Ground Truth)

• Human Factors Validation: No explicit mention of experts establishing a "ground truth" for the test set in the traditional sense (e.g., radiologists interpreting images). The HFV tests evaluated user performance against usability objectives (safe and effective use).
  • The study involved diverse user groups: Patients, Caregivers, Respiratory Therapists, and Physicians and Critical Care Nurses. Their performance in using the device constituted the primary evaluation in the HFV. Their "qualifications" are implied by their roles as end-users of the device.

4. Adjudication Method (for Test Set)

• The document does not describe an adjudication method in the context of expert consensus, as it is not an interpretative study. The Human Factors Validation (HFV) tests assessed user performance directly.

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

• No, an MRMC comparative effectiveness study was not done. The document describes a substantial equivalence submission for a physical medical device (ventilator system), not an AI/software device requiring human reader interpretation or assistance. Therefore, there is no discussion of AI assistance or its effect size on human readers.

6. Standalone Performance Study (Algorithm Only)

• Not applicable. This is a hardware medical device (ventilator system and accessories), not an algorithm or AI. Standalone performance for this device would refer to its functional performance as a ventilator (volume, pressure, alarms, etc.), which was tested through bench testing and compliance with various standards, as listed. The "algorithm" in this context would be the device's control software, which is implicitly validated through the functional and performance testing.

7. Type of Ground Truth Used

• For Human Factors Validation: The ground truth was implicitly the observed safe and effective use of the device by representative users (patients, caregivers, respiratory therapists, physicians, and critical care nurses) in simulated environments, as evaluated against predefined usability goals and error detection.
• For Bench Testing and Compliance: The ground truth was established by approved engineering specifications, international/national standards, and regulatory guidelines (e.g., ISO 10993-1, FDA Draft Reviewer Guide for Ventilators, ASTM F1246-91, AAMI/ANSI 60601-1, IEC 60601-1-2, ISO 80601-2-12, ISO 80601-2-72, IEC 62133, IEC 62366, FDA Guidance Documents). The device's performance was measured against these objective criteria.

8. Sample Size for the Training Set

• Not applicable / Not mentioned. The document does not describe a machine learning algorithm or AI component that would require a distinct training set. The submission focuses on validating hardware components and their integrated system.

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

• Not applicable. As no training set for an AI/algorithm is mentioned, the method for establishing its ground truth is not discussed.

Ask a specific question about this device

The Breathe Technologies Life2000 Ventilation System is intended to provide continuous or intermittent ventilatory support for the care of individuals who require mechanical ventilation. The ventilator is intended for use by qualified, trained personnel under the direction of a physician. Specifically, the ventilator is applicable for adult patients who require the following types of ventilatory support: - Positive Pressure Ventilation, delivered invasively (via ET tube) or non-invasively (via mask). - Assist/Control mode of ventilation. The ventilator is suitable for use in home and institutional settings.

The Breathe Technologies Life2000 Ventilation System is a portable, battery powered, critical care ventilator. The Ventilator administers the physician-prescribed volume to the patient via the attached Breathe Technologies Patient Universal Connector which connects into the patient's tracheostomy tube, endotracheal tube, or any off the shelf non-invasive mask. It can also be used with the Breath Technologies NIOV Pillows Interface, a type of nasal mask. The ventilator is small and light enough to be worn on a patient's belt, or slung over their shoulder. It is connected to a separate, third party, gas supply. The Ventilator is intended for Institutional or Home Use. It is not intended for use during emergency/medical transportation.

The Breathe Technologies Life2000 Ventilation System is a portable, battery-powered critical care ventilator for adult patients requiring continuous or intermittent ventilatory support.

Here's an analysis of its acceptance criteria and supporting studies:

1. Table of Acceptance Criteria and Reported Device Performance

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

   • The document does not specify sample sizes for specific performance tests (e.g., comparative waveform testing, human factors).
   • The document does not explicitly state the country of origin of the data or whether the studies were retrospective or prospective, beyond general statements of compliance with international and US standards.

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 identifies general "qualified, trained personnel under the direction of a physician" as the intended operators for the device. However, it does not specify the number or qualifications of experts used to establish ground truth or conduct specific performance assessments for the testing mentioned (e.g., comparative waveform testing, human factors).

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

   • The document does not specify any adjudication methods for the test sets.

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

   • No MRMC comparative effectiveness study is mentioned, as this device is a mechanical ventilator, not an AI-assisted diagnostic tool. The "comparative effectiveness" studies mentioned are related to device performance compared to a predicate, not human reader performance.

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

   • This is not applicable to a mechanical ventilator device. The device's performance is inherently standalone in its function, but its operation always involves a human user (qualified personnel under a physician's direction).

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

   • For the "Summary of Supporting Data," the ground truth for device performance is established through compliance with recognized standards such as ISO 10993-1, FDA Draft Reviewer Guide for Ventilators, ASTM F1246-91, IEC 60601-1, IEC 60601-1-2, and ISO 80601-2-12. This implies engineering and clinical performance metrics defined by these standards serve as the "ground truth" for the device's functional and safety capabilities.
   • Specific tests mentioned like "Ventilator Cleaning validation," "Risk characterization of VOC's," "Static Analysis Tool verification of software," "Comparative Waveform Testing," and "Human Factors and Usability Testing" would have their own defined ground truths based on established protocols for those types of evaluations (e.g., cleanliness standards, toxicology limits, software quality metrics, physiological waveform accuracy, human-computer interaction success rates).

8. The sample size for the training set

   • This is not applicable for a mechanical ventilator. Training sets are typically associated with machine learning or AI models, which are not described as integral to this device's function.

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

   • This is not applicable for a mechanical ventilator.

Ask a specific question about this device

The NIOV Ventilator, with accessories; is a volume assist ventilator intended to aid adult patients with respiratory insufficiency. It is designed for patients that are capable of spontaneously breathing a minimum tidel volume of 3.5 ml/kg of predicted body weight. The device is designed for continuous applications such as patient ambulation, physical therapy, respiratory therapy, and other rehabilitation efforts in an institutional or home care environment. The device is intended for operation by trained personnel, patients or their caregivers under the direction of a physician.

The Breathe Technologies NIOV Ventilator System is a battery powered, wearable, volume ventilator that augments the patient's spontaneous breathing. The NIOV Ventilator administers this physician-prescribed volume to the patient via the attached Breathe Technologies Patient Circuit (BT-PC) which inserts into the patient's tracheostomy tube, or via the Breath Technologies NIOV Pillows Interface, a type of nasal mask. The ventilator is small and light enough to be worn on a patient's belt, or slung over their shoulder. It is connected to a separate, third party, air or oxygen gas supply. The Ventilator is cleared for Institutional or Home Use.

The provided text describes the Breathe Technologies NIOV Ventilation System and its substantial equivalence to a predicate device, but it does not contain the specific information required to answer all parts of your request regarding acceptance criteria and a study proving those criteria.

Specifically, the text is a 510(k) summary, which focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than presenting detailed study results against specific, quantified acceptance criteria.

However, I can extract what is available:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state acceptance criteria in a quantified, pass/fail manner. Instead, it refers to compliance with recognized standards and guidelines. The "reported device performance" is a general statement of compliance.

The study that proves the device meets the (implied) acceptance criteria:

The study referenced is "bench testing of the device" and "Software Design and Validation process."

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

The document does not specify a "test set" sample size in the context of clinical or performance data for the device itself. It mentions "bench testing," which implies laboratory-based tests on the device, but details on the number of units tested or specific scenarios are not provided. There is no mention of data provenance like country of origin or whether it was 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 provided. The bench testing and software validation would likely rely on engineering and technical expertise to establish "ground truth" (i.e., correct device function or output), but no details on expert numbers or qualifications are given.

4. Adjudication method for the test set

This information is not provided.

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

No such study is mentioned. The device is a ventilator, not an AI-powered diagnostic imaging tool that would typically involve human readers.

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

This concept is not relevant to a mechanical ventilator like the Breathe Technologies NIOV. The device itself operates "standalone" in the sense that it performs its function (ventilation) without direct human intervention in each breath cycle, but it is operated by trained personnel, patients, or caregivers. The document indicates that "bench testing of the device" demonstrated its operation.

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

For the bench testing and software validation, the ground truth would likely be based on:

• Engineering specifications and design requirements.
• Measurements against calibrated standards for parameters like volume, pressure, flow, and timing.
• Expected behavior defined by the referenced industry standards (e.g., ASTM, IEC).

8. The sample size for the training set

This information is not provided. The device relies on embedded software and control algorithms, but the document does not discuss machine learning or "training sets" in the context of AI.

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

Not applicable, as no training set for AI is mentioned.

Ask a specific question about this device

The continuous positive airway pressure (CPAP) System is indicated for the treatment of obstructive sleep apnea (OSA) in patients > 661b (30 kg). The Breathe CPAP System is intended for single-patient re-use in the home environment.

The Breathe Technologies™ CPAP system is an AC powered Continuous Positive Airway Pressure (CPAP) device that delivers a physician prescribed pressure during the inspiratory phase and expiratory phases to help maintain airway patency during sleep for patients with obstructive sleep apnea (OSA). The Breathe CPAP System consists of a programmable, microprocessor controlled, flow generator (i.e., blower) and a Nasal Pillows Mask. The flow generator generates CPAP from room air to the patient and transmits it via the attached Nasal Pillows Mask. The end of the patient circuit is a nasal pillows interface which is worn on the nose. The nasal interface is held in place with standard headgear.

The provided text is a 510(k) summary for a CPAP system and does not contain information about acceptance criteria or a study proving the device meets acceptance criteria.

The document states that the device is "substantially equivalent" to a predicate device based on its intended use, indications for use, technology, design, materials, physician or patient use, and energy source. It also mentions that "the testing described below demonstrates that the differences in the devices do not raise any unresolved issues of safety or efficacy." However, the actual testing details, acceptance criteria, and specific performance results are not provided in the extracted text.

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study that proves the device meets them, nor can I provide the requested information about sample sizes, ground truth establishment, or comparative effectiveness studies. The primary focus of this document is establishing substantial equivalence to a predicate device and adherence to general medical device standards.

Ask a specific question about this device

The Breathe Technologies™ Ventilator, with accessories, is a volume assist ventilator intended to aid adult patients with respiratory insufficiency. It is designed for patients who are capable of spontaneously breathing a minimum tidal volume of 3.5cc/kg of predicted body weight. The device is designed for continuous applications such as patient ambulation, physical therapy, occupational therapy, respiratory therapy, and other rehabilitation efforts in an institutional or home care environment. The device is intended for operation by trained personnel, patients, or caregivers under the direction of a physician.

The Breathe Technologies Ventilator with Accessories (BT-V2S) is a small, wearable, ventilator that interfaces with proprietary nasal and tracheostomy breathing circuits.

The provided text describes the Breathe Technologies Ventilator (BT-V2S) and its accessories, and a 510(k) submission for expanded indication to include use in the Home Care Environment. The information focuses on demonstrating substantial equivalence to a predicate device and does not contain detailed acceptance criteria or a study design in the way you've outlined for a typical AI/software device.

Specifically, the document discusses general standards and guidelines the device complies with, and "Human Factors Studies" to demonstrate proper operation by intended users. It does not provide quantitative performance metrics, sample sizes, ground truth establishment, or expert-based evaluations in the context of an AI/algorithm-driven device.

Therefore, many of the requested fields cannot be directly extracted from the provided text. I will fill in the available information and indicate where data is not present.

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

The document does not specify quantitative acceptance criteria or performance metrics directly from a study in the format typically seen for AI/diagnostic devices. Instead, it states that the device is compliant with various industry standards and guidelines, and that "Human Factors Studies" demonstrated proper operation.

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

The document mentions "three Human Factors Studies" but does not provide sample sizes for these studies or their data provenance (e.g., country of origin, retrospective/prospective nature), beyond stating "The first study was with clinicians, and the second was with respiratory therapy patients."

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

Not applicable. This device is a mechanical ventilator, and the studies mentioned are Human Factors studies focused on usability and proper operation, not diagnostic accuracy requiring expert ground truth in the traditional sense of medical image analysis. The "experts" would likely be the clinicians and patients participating in the Human Factors studies.

4. Adjudication method for the test set

Not applicable. Adjudication methods are typically relevant for establishing ground truth in diagnostic studies, which is not the type of study described 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

Not applicable. This is not an AI-driven device, and no MRMC study is mentioned.

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

Not applicable. This is not an AI-driven device.

7. The type of ground truth used

For the Human Factors studies, the "ground truth" was likely defined by observational data and user feedback demonstrating the ability of users (clinicians, patients, caregivers) to safely and effectively operate the device according to its instructions and design, and to identify and address any usability issues. This is not a pathology or outcomes data ground truth in the diagnostic sense.

8. The sample size for the training set

Not applicable. There is no mention of a "training set" as this is not an AI/machine learning device. The "training" here refers to the actual training of users on how to operate the device.

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

Not applicable. See point 8.

Ask a specific question about this device

The Breathe Technologies Ventilator (BT-V2S), with Accessories, is a volume assist ventilator intended to aid adult patients with respiratory insufficiency. It is designed for patients, with or without a tracheostomy, that are capable of spontaneously breathing a minimum tidal volume of 3.5cc/kg of predicted body weight. The device is designed for continuous applications such as patient ambulation, physical therapy, occupational therapy, respiratory therapy, and other rehabilitation efforts in an institutional environment. The device is intended for operation by trained personnel under the direction of a physician.

This application is being filed to allow a new breathing circuit for the Breathe Technologies Ventilator (BT-V2). The Ventilator is fundamentally unchanged. The only difference between the predicate and application submissions is that the application requests clearance to market the BT-NT nasal interface with the BT-V2S ventilator.

The BT-NT is a nasal mask style patient circuit which attaches to the patients nose. It connects to the BT-V2S ventilator.

The BT-NT is approximately 12cm wide and 2cm thick at its thickest point under the patient's nose. These dimensions do not include the 231 cm dual tubing that connects to the Ventilator. It is composed of various plastics.

The provided document is a 510(k) Summary for a medical device modification (BT-V2S Ventilator and accessories). It states that the device is substantially equivalent to a predicate device, meaning it does not claim to offer superior performance or new functionalities that require extensive studies to prove acceptance criteria. Instead, the focus is on demonstrating that the modification (a new nasal interface breathing circuit, BT-NT) does not introduce new safety or efficacy concerns and that the device remains compliant with existing standards.

Therefore, the document does not contain the information requested in points 1-9 regarding the acceptance criteria, sample sizes, ground truth establishment, or expert involvement for a study proving device performance against specific acceptance criteria in the way one would expect for a novel AI/Diagnostic device.

Here's a breakdown of what is available and why most of the requested information is absent:

Explanation of Missing Information:

This document describes a "Special 510(k): Device Modification" for a ventilator. The core claim is "substantial equivalence" to a predicate device (BT-V2). This means the manufacturer is asserting that the modified device is as safe and effective as the previously cleared device, not that it is a new device with novel performance claims requiring rigorous clinical trials or AI performance evaluations. The modification here is specifically a "new breathing circuit for the Breathe Technologies Ventilator (BT-V2S)."

Therefore, the study performed is primarily bench testing and biocompatibility to prove that the modification does not negatively impact the existing performance and safety of the ventilator. This is fundamentally different from a study to establish novel performance metrics for AI or diagnostic accuracy where many of your questions would be highly relevant.

Information from the Document (and limitations):

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

   • Acceptance Criteria (Implied): Compliance with
     • ISO 10993 (Biocompatibility)
     • FDA Draft Reviewer Guide for Ventilators (July 1995)
     • ASTM F1100 90 (1997), Standard Specification for Ventilators Intended for Use in Critical Care
     • IEC 60601 1 (1988), Amendment 1 (1991-11), Amendment 2 (1995): Medical electrical equipment - General Requirements for Safety
     • IEC 60601 2- 12 (2001-10): Medical electrical equipment - Particular requirements for the safety of lung ventilators - Critical care ventilators.
   • Reported Device Performance:
     • Biocompatibility data demonstrates that the device is in compliance with ISO 10993.
     • Bench testing, including a lung model, has demonstrated that the BT-V2S remains in compliance with the expectations of the medical community, the product labeling, and the listed Standards and Guidances.
     • The document states: "The testing described below demonstrates that the differences in the devices do not raise any unresolved issues of safety or efficacy."

2. Sample size used for the test set and the data provenance: Not applicable. The "study" was bench testing (likely involving physical units of the ventilator and the new breathing circuit). There is no "test set" in the context of patient data, nor is there data provenance (e.g., country of origin, retrospective/prospective) for a bench test.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth, in this context, refers to the compliance with established engineering and medical device standards, which are evaluated by accredited labs and engineers, not typically by clinical experts establishing diagnostic "ground truth."

4. Adjudication method for the test set: Not applicable. There is no "adjudication" in the sense of resolving disagreements among experts on a test set. Compliance is determined by objective measurements against specified standard thresholds.

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 a ventilator, not an AI-powered diagnostic tool, and no MRMC study was performed or needed for this type of modification.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. This is not an algorithm-only device.

7. The type of ground truth used: "Ground truth" was compliance with established engineering and medical device standards (ISO, ASTM, IEC) and the "expectations of the medical community" for ventilator performance, as verified through bench testing.

8. The sample size for the training set: Not applicable. This is not an AI/machine learning device that requires a training set.

9. How the ground truth for the training set was established: Not applicable, as there is no training set for this type of device.

Ask a specific question about this device