Search Results

The myAir app is indicated for patients:

• prescribed with a compatible ResMed Air11 platform device to simulate therapy prior to using their device with their prescribed settings, and to configure their settings to support therapy. It is an optional software accessory to allow patients to acclimate to and operate their therapy device.
• prescribed a NightOwl wearable device to provide the user interface to operate the connected device and aid in the home sleep testing process.

The device is intended for home and hospital use for:

• new and existing patients of ResMed Air10 and Air11 PAP therapy devices and
• new users who are prescribed a compatible NightOwl home sleep test (HST).

myAir is a companion mobile medical application ("app") that serves as a patient self-monitoring, therapy usage tracking, and engagement platform for patients prescribed with compatible ResMed PAP therapy devices and the NightOwl home sleep test (HST) sensors. The app allows the patient to connect via Bluetooth to a compatible hardware device for control of their prescribed PAP or HST device and to allow self-tracking of device usage data. myAir can also be used as a communication pathway using the Bluetooth connection with the compatible device in order to send or receive data. Analysis of patient diagnostic data or display of diagnostic results are not in scope of myAir features.

The myAir subject device for this premarket submission adds device software functions related to starting and stopping therapy, and control of comfort settings (collectively referred to as "device control"). The addition of these device software functions within the myAir subject device is a modification to the K241216 myAir predicate device, in addition to sustaining previously cleared medical device functions.

It appears the provided document is an FDA Clearance Letter for the "myAir" device, specifically a 510(k) summary. This type of document primarily focuses on establishing substantial equivalence to a predicate device, rather than detailing the full scope of acceptance criteria and the comprehensive study results typically found in a clinical study report or a more detailed technical submission.

Based on the provided text, the device "myAir" is a companion mobile medical application. The submission is for a modified device, adding "device software functions related to starting and stopping therapy, and control of comfort settings (collectively referred to as 'device control')".

Therefore, the study detailed is primarily non-clinical verification and validation testing of software functions introduced with these modifications. The document states:

"Non-clinical verification and validation testing completed for device software functions under review introduced with the modifications to the myAir app demonstrated that the device met all intended performance requirements. Testing included:

• Software verification and validation, including non-functional requirements and end-to-end functional testing."

Given this, I cannot provide detailed information about acceptance criteria and study results for clinical performance or human-in-the-loop studies (MRMC, effect size, etc.), as such studies are not described in this 510(k) summary for a software modification. The focus is on the software's functional performance and adherence to guidance documents for software and cybersecurity.

Here's what can be extracted from the provided text according to your request, with a clear indication where information is not available in the document:

Acceptance Criteria and Device Performance for "myAir" (K250624)

The "myAir" device is a mobile application that received FDA 510(k) clearance (K250624) as a modified device, primarily adding "device control functions" (starting/stopping therapy, controlling comfort settings) for compatible ResMed Air11 platform devices. The acceptance criteria and performance detailed below pertain specifically to the non-clinical verification and validation of these new software functions.

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 specified. The document mentions "Software verification and validation, including non-functional requirements and end-to-end functional testing." This typically involves a range of test cases, but the specific number is not disclosed in this summary.
• Data Provenance: The document describes "non-clinical verification and validation testing." This implies internal testing conducted by the manufacturer (ResMed Corp, USA). It does not involve patient data or clinical datasets. Therefore, provenance (country, retrospective/prospective) is not applicable in the typical sense of a clinical study.

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

• Not Applicable/Not specified. For non-clinical software verification and validation, "ground truth" is typically defined by functional requirements specifications and design documents. The testing validates that the software performs according to these pre-defined specifications. Expert human readers or adjudicators are not typically involved in establishing ground truth for this type of testing.

4. Adjudication Method for the Test Set

• Not Applicable/None stated. As the testing is non-clinical software verification, adjudication methods like 2+1 or 3+1 (common in image interpretation studies) are not relevant here. The success or failure of a test case is determined by whether the software performs as specified.

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

• No. An MRMC study was not conducted as part of this submission, based on the provided document. The submission pertains to software functionality and its substantial equivalence, not to comparative effectiveness for human readers.
• Effect Size of Human Readers Improvement with AI vs. Without AI Assistance: Not applicable, as no MRMC study or human reader performance evaluation was described. The "myAir" app is an accessory for device control and patient engagement, not an AI diagnostic tool assisting human readers.

6. If a Standalone (i.e., Algorithm Only Without Human-in-the-Loop Performance) Was Done

• Yes, implicitly. The "non-clinical verification and validation testing" is a form of standalone testing for the software's functional performance. The software is tested to operate its intended device control functions (starting/stopping therapy, comfort settings) without direct human intervention in the execution of those specific software commands once initiated. However, this is not "standalone performance" in the sense of a diagnostic algorithm's accuracy, sensitivity, or specificity. It's about the software performing its programmed tasks correctly.

7. The Type of Ground Truth Used

• Functional Requirements and Design Specifications. For this type of software verification, the "ground truth" is established by the detailed specifications of how the software functions are designed to operate. Test cases are then executed to confirm that the actual software behavior matches these expected behaviors. No clinical ground truth (e.g., pathology, outcomes data, expert consensus on patient conditions) is mentioned as being used for the specific software modifications under review.

8. The Sample Size for the Training Set

• Not Applicable/Not disclosed. Since this is software functional verification and validation for a non-AI/ML application (it controls a medical device and provides user interface), there is no "training set" in the sense of data used to train a machine learning model. The software's logic is developed through traditional programming methods, not data training.

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

• Not Applicable. See point 8. No training set for an AI/ML model is indicated, so no ground truth establishment process for a training set is relevant or described.

Ask a specific question about this device

The Easy Care Tx 2 software is intended to be used with ResMed compatible therapy devices in a clinical environment. EasyCare Tx 2 provides therapy device setting changes and displays real-time data and treatment settings from compatible ResMed therapy devices when used together with the TxLink 2 module.

EasyCare Tx 2 is a personal computer application designed to allow clinicians to monitor real-time data from the ResMed compatible therapy device and adjust the therapy device settings from the control room of the sleep lab.

The device in question is the EasyCare Tx 2, a therapy titration software developed by ResMed Corp. The provided document is a 510(k) Premarket Notification summary to the FDA. The submission seeks to prove substantial equivalence to a predicate device, the EasyCare Tx System (K113780).

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

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of "acceptance criteria" in a quantitative sense as might be seen for diagnostic device performance (e.g., sensitivity, specificity). Instead, it focuses on comparing the technological characteristics and intended use of the EasyCare Tx 2 with its predicate device to demonstrate substantial equivalence. The "performance" here relates to functional capabilities and parameter ranges rather than diagnostic accuracy.

The acceptance criteria here are implicitly met by demonstrating that the EasyCare Tx 2 has similar intended use and technological characteristics to the predicate device, and that any differences do not raise new questions of safety or effectiveness. The "reported device performance" are the parameter ranges and functional capabilities described for EasyCare Tx 2.

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 states: "Non-clinical verification and validation testing completed for EasyCare Tx 2 demonstrated that the device met all intended performance requirements. Testing included: Software verification and validation."

It also mentions: "The verification testing performed with EasyCare Tx 2 was software verification and validation against the non-functional requirements and end-to-end functional testing."

This indicates that the "test set" consisted of various software testing scenarios (unit, integration, system, performance, usability tests) to verify functionality and non-functional requirements. However, no specific sample size (e.g., number of data points, cases, or patients) for a test set is provided, nor is the data provenance (country of origin, retrospective/prospective) for any specific clinical data mentioned. The testing described is primarily software-centric, not based on a dataset of patient outcomes.

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 provided. The testing described is software verification and validation, which typically involves engineering and quality assurance professionals, not clinical experts establishing ground truth in the context of medical image analysis or similar diagnostic tasks.

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

This information is not provided. Given the nature of the software verification and validation, adjudication methods typical for clinical or image-based studies are not relevant here.

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

No MRMC comparative effectiveness study was done. This device is a software application for clinicians to monitor and adjust therapy device settings, not a diagnostic AI intended to assist human readers.

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

The device is a human-in-the-loop software. Its purpose is to allow clinicians to monitor and adjust therapy settings. The "performance" is the software correctly displaying data and applying setting changes, not standalone diagnostic accuracy. The testing performed was "software verification and validation against the non-functional requirements and end-to-end functional testing," indicating validation of its functional integrity, not standalone diagnostic capability.

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

For the software verification and validation, the "ground truth" would be the defined software requirements and expected behavior based on engineering specifications and design documents. For example, if a setting is changed from X to Y, the ground truth is that the software should correctly register and apply that change to the therapy device and display it accurately. It's not a clinical ground truth like pathology or outcome data.

8. The sample size for the training set

This information is not applicable/not provided. The EasyCare Tx 2 is described as therapy titration software, not an AI/ML model that would require a "training set" in the context of learning from data to make predictions or classifications. The software's functionality is based on programming and engineering, not machine learning.

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

This information is not applicable/not provided as there is no mention of a machine learning training set.

Ask a specific question about this device

The myAir app is indicated for patients:
• prescribed with a compatible ResMed Air11 platform device to simulate therapy prior to using their device with their prescribed settings. It is an optional software accessory to allow patients to acclimate to their therapy device.
• prescribed a NightOwl wearable device to provide the user interface to operate the connected device and aid in the home sleep testing process.
The device is intended for home and hospital use for:
• new and existing patients of ResMed Air11 PAP therapy devices and
• new users who are prescribed a compatible NightOwl home sleep test (HST).

myAir is a companion mobile medical application ("app") for self-monitoring use of the compatible devices that serve as a patient Home Sleep Test (HST), pre-therapy, and engagement platform for positive airway pressure (PAP) therapy. The app allows the patient to connect via Bluetooth to a compatible hardware device for temporary control of their prescribed HST or PAP device and to allow self-tracking of device usage data. myAir can also be used as a communication pathway using the Bluetooth connection with the compatible device in order to send or receive data. Analysis of patient diagnostic data or display of diagnostic results are not in scope of myAir features.
The subject device modifies the predicate device by adding interoperability with the NightOwl HST (Stella functions) in addition to sustaining previously cleared medical device function of connecting to the Air 1 platform.

The provided text does not contain detailed information about specific acceptance criteria or a dedicated study proving the device meets those criteria. The document is primarily a 510(k) summary for the myAir app, outlining its substantial equivalence to a predicate device and a reference device. It mentions "non-clinical verification and validation testing" but does not elaborate on the specific tests, acceptance criteria, or results.

Therefore, I cannot provide the requested table or detailed information regarding the study.

However, I can extract the available relevant information:

Acceptance Criteria and Device Performance:

The document states: "Non-clinical verification and validation testing completed for NightOwl HST interoperable (Stella) functions introduced with the modifications to the myAir app demonstrated that the device met all intended performance requirements."

This is a general statement that the device met its intended performance requirements, but no specific acceptance criteria (e.g., accuracy metrics, thresholds for errors) or reported device performance data (e.g., a measured accuracy of X%) are provided in the text.

Regarding the study (based on limited information):

• Sample size used for the test set and data provenance: Not specified. The document only mentions "non-clinical verification and validation testing," implying a test set was used, but details on its size or provenance (country of origin, retrospective/prospective) are absent.
• Number of experts used to establish the ground truth for the test set and their qualifications: Not specified. The information provided is about software testing, not clinical performance evaluation that would typically involve expert ground truth.
• Adjudication method: Not applicable/specified. This type of method is typically used in clinical studies with human assessors, which is not described here.
• Multi-reader multi-case (MRMC) comparative effectiveness study: Not mentioned. The document focuses on software interoperability and functional testing, not comparative clinical effectiveness with human readers.
• Standalone (i.e., algorithm only without human-in-the-loop performance) study: The "non-clinical verification and validation testing" likely includes standalone software testing, but specific details or results are not provided. The myAir app acts as a user interface and data transfer mechanism, not an algorithm for diagnostic analysis or interpretation.
• Type of ground truth used: Not specified. For software functional testing, ground truth would typically be defined by expected system behavior and output under various conditions.
• Sample size for the training set: Not applicable and not specified. The myAir app described here is a companion mobile medical application for control and data transfer, not one that employs machine learning models requiring a training set for diagnostic purposes.
• How the ground truth for the training set was established: Not applicable and not specified.

Summary of what is available from the text:

The document concerns the ResMed myAir app (K241216). It states that non-clinical verification and validation testing was performed for the NightOwl HST interoperable (Stella) functions. This testing "demonstrated that the device met all intended performance requirements." The testing followed FDA guidance documents: "Content of Premarket Submissions for Device Software Functions: June 2023" and "Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions: September 2023."

The core of the submission is to establish Substantial Equivalence because:

• The subject device (myAir) and predicate device (Galapagos, K200565) have the same intended use.
• They have similar technological characteristics and operating principles.
• The subject device adds interoperability with the NightOwl HST (Stella functions) to its existing cleared function of connecting to the Air11 platform.
• The differences do not raise any new questions of safety or effectiveness.
• It is as safe and effective as the predicate devices.

Ask a specific question about this device

The Galapagos app is intended for patients who are prescribed a compatible ResMed S10 platform device to simulate therapy prior to using their device with their prescribed settings. It is an optional software accessory to allow patients to acclimate to their therapy device.

Galapagos is a mobile interface where the patient can control the device through pre-determined, scaled inspiratory pressures to help them adjust to pressure and mask fit prior to starting their prescribed therapy. In addition, Galapagos may also be used as a communication pathway using the mobile Bluetooth connection to the compatible flow generator in order to send and receive data.

The provided text is a 510(k) summary for the device "Galapagos," a mobile application. It details the device's indications for use, its comparison to a predicate device (Monte Carlo), and the testing performed to demonstrate substantial equivalence.

However, the document states: "Clinical tests were not required to demonstrate the safety and effectiveness of Galapagos."

This crucial statement means that the acceptance criteria and study proving the device meets those criteria were not based on clinical performance studies like those typically conducted for AI/ML medical devices (e.g., MRMC studies, standalone performance with reader ground truth). Instead, the assessment for this device relied on non-clinical verification and validation testing to demonstrate that it met its intended performance requirements and was substantially equivalent to a previously cleared predicate device.

Therefore, I cannot provide the information requested in points 1-9 as they pertain to clinical performance studies and AI/ML model validation, which were explicitly not conducted for Galapagos. The acceptance criteria and "proof" of meeting them for Galapagos are primarily based on software verification and validation, and bench testing, rather than human-in-the-loop or standalone AI performance.

The document highlights the following non-clinical testing for Galapagos:

• Software verification and validation
• Predicate testing (which involved bench tests against nonfunctional requirements and end-to-end functional testing, comparing Galapagos to the Monte Carlo device).

The "acceptance criteria" here is therefore the successful completion of these non-clinical tests and the demonstration of substantial equivalence based on differences not impacting safety or efficacy.

To directly address your request based on the provided text, but acknowledging the limitations:

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

   • Acceptance Criteria (Implied from the document): The device must successfully pass software verification and validation, and non-clinical performance bench tests including end-to-end functional testing and predicate testing (demonstrating substantial equivalence to Monte Carlo without raising new questions of safety or efficacy).
   • Reported Device Performance: "Non-clinical verification and validation testing completed for Galapagos demonstrated that the device met all intended performance requirements." And "The predicate testing conducted with Galapagos to the predicate Monte Carlo device (K160836) demonstrate substantial equivalence to the technology and operating principle of the devices."

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective): Not applicable, as clinical data was not used for performance evaluation. The "test set" would refer to the scenarios and inputs used during software/bench testing, the details of which are not provided.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth for clinical performance was not established due to the absence of clinical testing.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable.

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 study was done, as clinical tests were not required. The device is a "mobile interface where the patient can control the device" and an "optional software accessory to allow patients to acclimate to their therapy device," not an AI/ML diagnostic or assistive tool for human readers.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable in the context of typical AI/ML standalone performance studies. Bench and software tests were done, but these are not the same as standalone diagnostic performance of an AI algorithm on patient data.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): Not applicable for clinical ground truth. The "ground truth" for the non-clinical testing would be the expected functional behavior and performance characteristics derived from design specifications and predicate device equivalence.

8. The sample size for the training set: Not applicable, as this device does not appear to be an AI/ML model that learns from a training set of data. It's a software application controlling a medical device.

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

Ask a specific question about this device

The S9 Elouera self-adjusting device is indicated 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).

It is intended for home and hospital use.

The S9 Elouera retains all the same hardware and performance features of the predicate device(s). Key features include in-line power supply, fully integrated humidifier, tubing, colour LCD and simplified controls which provides improved usability. The S9 Elouera contains a Micro-processor controlled blower 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, mask (patient interface) and humidifier.

The S9 Elouera 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.
• t AutoSet for Her mode - the device automatically adjusts pressure in response to female-specific OSA characteristics.

The functional characteristics of the S9 Elouera 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.

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

Acceptance Criteria and Device Performance

Detailed Study Information:

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

• Clinical Testing (AfH Mode): Not explicitly stated how many patients were in the "single-blind, randomized, cross-over non-inferiority study." Given the context of a 510(k) summary, specific sample sizes are often omitted in this section but would be detailed in the full submission.
  • Data Provenance: Not explicitly stated, though ResMed is an Australian company, so studies could be international or domestic to Australia. The submission is to the FDA, implying relevance to the US market. The study design (clinical trial) implies prospective data collection.
• Non-Clinical Testing (CSR Detection):
  • Sample Size: The text mentions "patient script files," with each treated as an "individual scenario." The exact number of these scenarios (test cases for CSR) is not provided.
  • Data Provenance: The text describes the use of "digitised breathing patterns." This suggests a retrospective dataset of breathing patterns, potentially derived from real patient data or generated synthetically to simulate various conditions. The origin of these patterns (e.g., country) is not specified.

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

• Clinical Testing (AfH Mode):
  • Number of Experts: Not specified. Clinical trials typically involve medical professionals (e.g., pulmonologists, sleep specialists) to diagnose OSA, monitor patients, and interpret results, but the experts specifically for ground truth establishment in this context (e.g., AHI/ODI scoring) are not quantified beyond the general conduct of a clinical trial.
  • Qualifications: "Medical professionals" (implied for a clinical trial) are involved in patient assessment and data collection/interpretation.
• Non-Clinical Testing (CSR Detection):
  • Number of Experts: Not specified. The text refers to "human scoring" as the comparator for the CSR detector. This implies one or more human experts scored the breathing patterns.
  • Qualifications: Not specified. These would likely be sleep specialists or trained sleep technologists with expertise in scoring sleep-disordered breathing events, including Cheyne-Stokes Respiration.

4. Adjudication Method for the Test Set:

• Clinical Testing (AfH Mode): Not specified. Standard clinical trial practices for outcomes like AHI and ODI often involve blinded scoring by certified sleep technologists, potentially with adjudication processes for discrepancies, but this is not detailed in the summary.
• Non-Clinical Testing (CSR Detection): Not specified. The text only mentions comparison to "human scoring." It doesn't indicate if multiple human scorers were used or if an adjudication process was in place.

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

• No, an MRMC study was implicitly NOT conducted for the device performance itself.
  • The primary clinical study for the AfH mode was a non-inferiority clinical trial comparing two device algorithms (AfH vs. standard AutoSet) in human patients, not a multi-reader study comparing human performance with and without AI assistance.
  • The CSR detection testing involved bench testing against human scoring as ground truth, but not for assessing the improvement of human readers using the device.
• Effect Size of Human Readers Improvement with AI vs. without AI: Not applicable, as an MRMC comparative effectiveness study involving human readers' performance with AI assistance was not described.

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

• Yes, for the CSR Detection feature, a standalone evaluation was performed.
  • The description of "Side-by-side testing using the same digitised breathing patterns was used. This test executes patient script files. Each patient script file is treated as an individual scenario, which the S9 Elouera reports either: No CSR, CSR, CSR + OSA, OSA. The S9 Elouera CSR detector results are then compared to human scoring where sensitivity and specificity are assessed." This clearly indicates an assessment of the algorithm's performance independent of a human operator, using human scoring as the ground truth.
• For the main therapeutic algorithms (CPAP, AutoSet, AfH), these are inherently "standalone" in their operation. They automatically adjust pressure based on detected events. Their efficacy is evaluated in clinical trials (as described for AfH) where the device alone provides therapy.

7. The Type of Ground Truth Used:

• Clinical Testing (AfH Mode): The ground truth for treatment effectiveness (non-inferiority) was established by patient outcomes data (AHI and ODI) collected during a clinical trial, likely based on polysomnography or other clinically accepted methods of measuring these indices.
• Non-Clinical Testing (CSR Detection): The ground truth for the CSR detection algorithm was established by expert consensus / human scoring of the "digitised breathing patterns."

8. The Sample Size for the Training Set:

• Not provided. The summary focuses on the validation/testing of the device's algorithms. It does not mention the training phase or the size of any training datasets used to develop the AutoSet or AfH algorithms or the CSR detector. This information is typically proprietary to the manufacturer and not always included in 510(k) summaries unless explicitly requested by the FDA for specific types of AI/ML devices depending on their risk and adaptive capabilities.

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

• Not provided. Since the training set size is not mentioned, the method for establishing its ground truth is also absent from the summary.

Ask a specific question about this device

The VPAP Adapt is indicated for the treatment of patients weighing more than 66 lb (30 kg) with obstructive sleep apnea (OSA), central and/or mixed apneas, or periodic breathing. It is intended for home and hospital use.

VPAP Adapt System (VPAP Adapt with H5) is similar to the predicate device(s), using a blower based positive pressure system with an integrated heated humidfier and heater controller. The device platform is identical to the S9 VPAP Adapt (K102586) and contains a Micro-processor controlled blower system that generates controlled positive airway pressure between 3-25 cmHzO as required to maintain an "air splint" for effective treatment of OSA. The system comprises the flow generator, patient interface) and humidifier.

The VPAP Adapt is a flow generator device designed to provide adaptive servo-ventilation therapy (ASV) 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. It then adjusts the degree of pressure support to servo-control the patient's ventilation to at least equal the target ventilation. Therapy modes contained in the VPAP Adapt are CPAP, ASV, and ASVAuto. CPAP and ASV therapy modes come from the S9 VPAP Adapt (K102586).

The functional characteristics of the VPAP Adapt system includes all the clinician and user friendly features of the predicate device.

The provided text is a 510(k) summary for the ResMed VPAP Adapt device, a non-continuous ventilator. The document focuses on demonstrating substantial equivalence to a predicate device rather than providing a detailed study of the device's performance against specific acceptance criteria in a clinical setting.

Based on the information provided, here's a breakdown of the requested points:

Device: VPAP Adapt (Non-continuous ventilator)

1. Table of Acceptance Criteria and Reported Device Performance

The document does not provide a table of clinical acceptance criteria (e.g., AHI reduction, oxygen saturation improvement) with corresponding device performance metrics. Instead, it refers to "predetermined acceptance criteria" for bench testing demonstrating the ASVAuto algorithm's specification and the device's adherence to safety and performance standards.

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

• Test Set Sample Size: Not applicable. The "tests" mentioned are bench tests using "closed-loop and open-loop test scripts from patient models," not human subjects or a clinical test set. Therefore, there's no patient sample size.
• Data Provenance: Not applicable, as no clinical data from human subjects is mentioned for the verification activities. The "patient models" used in bench testing would be simulated data or hardware models.

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

Not applicable. The "ground truth" for the bench tests was based on the device's own specifications and the performance of the predicate device (S9 VPAP Adapt K102586). No human experts were used to establish ground truth for a test set in the clinical sense.

4. Adjudication Method for the Test Set

Not applicable. There was no clinical test set requiring human adjudication.

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

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly mentioned or conducted. The document focuses on demonstrating substantial equivalence through bench testing to a predicate device, not on comparing human reader performance with and without AI assistance.

6. Standalone (Algorithm Only) Performance Study

Yes, in a way. The "Non-Clinical Testing" section describes "extensive bench testing using both closed-loop and open-loop test scripts from patient models designed to verify that the ASVAuto algorithm in the VPAP Adapt performs to specification." This is a form of standalone testing of the algorithm within the device against preset criteria. It's not a clinical standalone study, but an engineering verification.

7. Type of Ground Truth Used for the Testing

The ground truth for the bench testing was the design specification of the ASVAuto algorithm and the performance characteristics of the predicate device (S9 VPAP Adapt K102586). It's based on engineering requirements and existing device performance, not clinical pathology, expert consensus, or outcomes data from human subjects.

8. Sample Size for the Training Set

Not applicable. The document does not describe any machine learning training processes or a "training set" in the context of AI. The device's algorithm appears to be rule-based or pre-programmed, not learned from a dataset.

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

Not applicable, as no training set is mentioned for an AI/machine learning model. The algorithm's behavior is described as "continually measures the patient's instantaneous ventilation, and calculates a target ventilation based on to the patient's recent average. It then adjusts the degree of pressure support to servo-control the patient's ventilation." This implies a deterministic, pre-defined control algorithm, not one developed through machine learning.

Ask a specific question about this device

Ask a specific question about this device

The Mirage Echo channels airflow noninvasively to a patient from a positive airway pressure (PAP) device such as a continuous positive airway pressure (CPAP) or bilevel system. The Mirage Echo is: to be used by adult 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 Mirage Echo provides an interface such that airflow from a positive pressure source is directed to the patient's nose. The mask is held in place with adjustable headgear that straps the mask to the face. Mirage Echo is safe when used under the conditions and purposes intended as indicated in the labeling provided with the product. Mirage Echo is a prescription device supplied non-sterile.

Here's an analysis of the Mirage Echo Traditional 510k, based on the provided text, focusing on acceptance criteria and supporting studies.

Based on the provided information, the 510(k) submission for the Mirage™ Echo nasal mask describes a comparative study against predicate devices (Mirage Micro and Ultra Mirage II Mask) to demonstrate substantial equivalence, rather than a study with explicit, quantitative acceptance criteria for device performance as one might see for an AI algorithm.

The core of the "study" is a set of comparisons and assertions of substantial equivalence, relying on bench testing and the existing clinical acceptance of similar technology.

1. Table of Acceptance Criteria and Reported Device Performance

As this is a traditional 510(k) for a medical device (nasal mask), the "acceptance criteria" are primarily established implicitly by demonstrating substantial equivalence to predicate devices, focusing on safety, performance characteristics, and intended use. The performance is reported as "substantially equivalent" to the predicates.

2. Sample Size for the Test Set and Data Provenance

The provided text does not mention a "test set" in the context of clinical data or patient-specific evaluation. The performance data refers to bench testing. Therefore, information regarding:

• Sample size for the test set
• Data provenance (e.g., country of origin, retrospective/prospective)
  is not applicable as no clinical test set data is described. The submission relies on "bench testing" and comparison of technical specifications.

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

This information is not applicable. Since no clinical test set data is described, there's no mention of experts establishing a ground truth for such a set. The "ground truth" for this type of submission is typically derived from established engineering principles, international standards (e.g., ISO), and the performance of legally marketed predicate devices.

4. Adjudication Method for the Test Set

This information is not applicable. No clinical test set data is described that would require an adjudication method.

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

A MRMC comparative effectiveness study was not done. This type of study is relevant for diagnostic devices where human readers interpret results, potentially with AI assistance. The Mirage Echo is a medical device (nasal mask) for therapy delivery, not a diagnostic tool requiring interpretation.

6. Standalone (Algorithm Only) Performance Study

A standalone performance study was not done, nor would it be relevant for this type of device. The Mirage Echo is a physical medical device, not an AI algorithm.

7. Type of Ground Truth Used

The "ground truth" in this context is established through bench testing results, adherence to international standards (e.g., ISO 10993-1 for biocompatibility, ISO 5356-1:2004 for connectors), engineering specifications, and the established performance and safety profile of legally marketed predicate devices. There is no mention of expert consensus, pathology, or outcomes data being used to establish ground truth for this submission, as it focuses on demonstrating substantial equivalence in physical and functional characteristics.

8. Sample Size for the Training Set

This information is not applicable. The Mirage Echo is a physical medical device, not an AI algorithm that undergoes a "training set" process.

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

This information is not applicable. As it's not an AI algorithm, there is no "training set" or ground truth for such a set.

Ask a specific question about this device

The SomnoTraxx System is intended to augment the standard follow-up care of patients diagnosed with obstructive sleep apnea by providing wireless transmission and display of usage and therapeutic information. It is intended for home use only in conjunction with ResMed S7 Elite and AutoSet Spirit CPAP Systems Positive Airway Pressure flow generators.

SomnoTraxx System is not intended to provide automated treatment decisions nor to be used as a substitute for a competent healthcare professional's judgment.

All patients' medical diagnosis and treatment are to be performed under the supervision and oversight of an appropriate healthcare professional.

The S7 Elite and AutoSet Spirit CPAP Systems are indicated for the treatment of obstructive sleep apnea (OSA) in adult patients.

The S7™ Elite (K013909) and AutoSet® Spirit™ (K013843) CPAP Systems are microprocessor controlled blower-based systems that generate Continuous Positive Airway Pressure (CPAP) from 4-20 cmH2O as required to maintain an "air splint" for effective treatment of Obstructive Sleep Apnea (OSA).

The system includes the flow generator, patient tubing and a mask (patient interface). For additional humidification, several humicifiers, including the integrated HuMDARE 2i, are designed to be compatible with the flow generators. AutoScan software allows viewing of flow-generator stored treatment data via a PC, transmitting the data using a direct connection or a modem.

The SomnoTraxx™ System is designed to be used with ResMed's S7™ Elite and AutoSet Spirit™ CPAP The common raise " yetner retrieval and display of stored information from the flow generators to the clinician, via wireless transmission and web-based access. Access to the data is limited to subscribers of the system. There is no patient access to the system.

The SomnoTraxx™ System is comprised of two distinct components, the ResTrax™ and the Server System. Data are extracted from the flow generator, transmitted via a wireless network, stored in a database, transmitted via the Internet and displayed for review by a healthcare provider. Both components must be present in order for the SomnoTraxx™ System to function.

ResTrax™ ~ResTrax™ is an optional wireless module designed to attach to a ResMed S7™ Elite or AutoSet® Spirit™ flow generator using a docking mechanism allows the device to be electrically connected via the existing 15-pin expansion port located at the rear of the flow generator. When attached, the ResTrax™ can automatically collect usage and therapeutic information stored within the flow generator's memory.

The ResTrax™ sends and receives information utilizing existing messaging networks providing wireless coverage to large portions of the US population.

Server System – The Server System consists of several functional software modules that are designed to retrieve information from flow generators through the ResTrax™ and a wireless messaging network, store the information in a database and provide a secure interface into the system allowing users (not patients) to schedule information retrieval and view the results.

The provided text describes a 510(k) submission for the S7™ Elite and AutoSet® Spirit™ CPAP Systems with the SomnoTraxx™ System. This submission is for a modification to an existing device, specifically adding an accessory (the SomnoTraxx™ System) for wireless data transmission.

However, the document is a regulatory filing that focuses on demonstrating "substantial equivalence" of the modified device to predicate devices, rather than a detailed report of a study designed to prove the device meets specific acceptance criteria in the manner one might find for a novel diagnostic or therapeutic algorithm.

Therefore, much of the requested information regarding detailed acceptance criteria tables, specific performance metrics, sample sizes for test sets, expert ground truth establishment, adjudication methods, MRMC studies, standalone performance, and training set details are not explicitly provided in this type of regulatory document.

Here's what can be extracted and inferred based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not provide a table of specific acceptance criteria (e.g., sensitivity, specificity, accuracy targets) for the SomnoTraxx™ system's data transmission or display functionalities, nor does it present detailed quantitative performance results against such criteria. The "acceptance criteria" here refer more broadly to demonstrating that the modified device (with SomnoTraxx™) still functions safely and effectively, and is "substantially equivalent" to predicate devices.

The key statement regarding performance is:
"Design Verification and Validation were performed on the S7 Elite™ & AutoSet® Spirit™ CPAP Systems with SomnoTraxx™ System, in accordance with the risk analysis and product requirements. All tests with ourned the product meets the acceptance criteria. ResMed has determined that the modified design has oonlined the product mode effectiveness of the device."

This indicates that internal tests were conducted, and the reported device performance is that it "meets the acceptance criteria" and maintains the "effectiveness of the device" (meaning the core CPAP function is not degraded by the addition of SomnoTraxx™ and the SomnoTraxx™ itself performs as intended). No specific numerical performance metrics are given.

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

• Sample Size for Test Set: Not specified. The document refers to "Design Verification and Validation" tests but does not detail the number of units, data points, or patients used in these tests.
• Data Provenance: Not specified explicitly as patient data. The tests would likely involve laboratory or simulated environments to verify the functionality of the wireless transmission and data retrieval. As the SomnoTraxx™ is an accessory for existing CPAP systems for home use in the US, the provenance of eventual usage data would be from US patients in a home setting, but the verification and validation data for the accessory itself are not detailed. These tests are likely retrospective, as they are performed on the designed system before marketing.

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

Not applicable/Not specified. This type of information is typically for diagnostic algorithms where a "ground truth" needs to be established (e.g., presence or absence of a disease). For a system focused on wireless data transmission of usage and therapeutic information, the "truth" is whether the transmitted data accurately reflects the data stored in the CPAP device. This would be verified through technical tests, comparing source data to received data, rather than through expert medical assessment of cases.

4. Adjudication Method

Not applicable/Not specified. Adjudication methods (like 2+1, 3+1) are used for resolving disagreements among multiple experts who establish a ground truth. Since expert consensus on medical findings is not the nature of the "ground truth" for this device, an adjudication method is not relevant.

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

Not applicable. An MRMC study assesses how human readers' performance changes with or without AI assistance. The SomnoTraxx™ system is a data transmission and display system, not an AI-assisted diagnostic or interpretive tool that directly aids human readers in making a diagnosis or interpretation in the clinical sense. It augments follow-up care by providing data, but it does not replace or assist a human in interpreting diagnostic images or complex medical signals.

6. Standalone (Algorithm Only) Performance Study

The SomnoTraxx™ system's core function (wireless transmission and display of data) is inherently "standalone" in that it performs its function without human intervention in the data transmission process itself. However, it is an "augmentation" to human follow-up care. The testing would have focused on the accuracy and reliability of the data transmission and storage, which can be considered its standalone performance. No specific performance metrics like accuracy, reliability percentages, or latency are provided in this summary.

7. Type of Ground Truth Used

For the SomnoTraxx™ system, the "ground truth" would be the actual usage and therapeutic information stored within the S7 Elite or AutoSet Spirit CPAP flow generator's memory. The verification tests would have compared the wirelessly transmitted and displayed data against this source data to ensure fidelity.

8. Sample Size for the Training Set

Not applicable. The SomnoTraxx™ system's functionality (wireless data transmission) is based on engineering design and communication protocols, not on machine learning algorithms that require a "training set" to learn from data.

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

The AUTOSET SPIRIT CPAP System is indicated for the treatment of Obstructive Sleep Apnea (OSA) in adult patients. The optional integrated humidifier (HUMDAIRE® 2[™) is indicated for the humidification and warming of air from the AUTOSET SPIRIT flow generator device. The AUTOSET SPIRIT CPAP System and HUMIDAIRE 2i are for home and hospital use.

The AUTOSET SPIRIT CPAP System is a non-invasive Continuous Positive Airway Pressure (CPAP) system. It includes the following system components:

• Flow generator device,
• . Humidifier
• Mask and air tubing.
• . Clinical Interface (AutoScan) Software.
  The flow generator device incorporates a blower (motor/fan assembly), sensors and processing electronics. The blower supplies pressurized air to the patient via the air tubing and a mask.
  The AUTOSET SPIRIT flow generator has two (2) modes of operation:
• (i) CPAP Mode
  In this mode the flow generator provides a single fixed-pressure as set by the clinician.
• Auto-titrating (AutoSet) Mode (ii)
  In this mode the pressure is automatically set in response to the patient's breathing patterns.
  The AutoScan software allows adjustment of parameter settings and viewing of flow generator-stored treatment data via a PC.

This document describes the AUTOSET SPIRIT CPAP System, a device for treating Obstructive Sleep Apnea (OSA). The information provided is primarily focused on demonstrating "substantial equivalence" to predicate devices, which is a regulatory pathway for medical devices in the US. This type of submission relies on showing that the new device is as safe and effective as a legally marketed predicate device, rather than requiring extensive new clinical trials with pre-defined acceptance criteria based on performance metrics.

Therefore, the requested information regarding acceptance criteria and a study proving the device meets them, as it would apply to a novel device or a device requiring a specific performance study, is not explicitly present in the provided text. The submission focuses on compliance with standards and a comparison to predicate devices, rather than a standalone performance study with specific effectiveness endpoints.

However, I can extract information related to the device description, indications for use, and the regulatory pathway.

Here's an analysis based on the provided text, addressing the points where information is available and indicating where it is not:

Acceptance Criteria and Study for AUTOSET SPIRIT CPAP System

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

• Acceptance Criteria: Not explicitly stated as performance metrics in this regulatory filing. The "acceptance criteria" here are implicitly being "substantially equivalent" to predicate devices and meeting relevant safety and electrical standards.
• Reported Device Performance: No specific performance metrics (e.g., AHI reduction, adherence rates, specific pressure delivery accuracy under varying conditions) are reported in clinical study format in this summary. The performance is implied to be equivalent to the predicate devices.

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

• Sample Size for Test Set: Not applicable. This document does not describe a clinical study with a "test set" of patients for evaluating device effectiveness. The "testing" mentioned refers to compliance with engineering and safety standards, not a patient-based performance study.
• Data Provenance: Not applicable.

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)

• Not applicable. There is no mention of experts establishing ground truth for a clinical test set in this document. The "ground truth" for this submission revolves around technical compliance and equivalence to predicate devices, assessed by regulatory bodies and internal engineering teams.

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

• Not applicable. There is no clinical test set requiring adjudication in this submission.

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 device (CPAP system) is not an AI-based diagnostic tool that relies on "human readers." Therefore, no MRMC study, AI assistance data, or effect size is relevant or mentioned.

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

• Not applicable. This is a medical device for treatment, not an algorithm. The "Auto-titrating (AutoSet) Mode" has an algorithmic component, but its performance is demonstrated through comparison to a predicate device and compliance with standards, not a standalone algorithm study with specific metrics in this document.

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

• For the purpose of this 510(k) submission, the "ground truth" is largely established by:
  • Regulatory Standards: Compliance with established medical device standards (EN 60601-1, ISO 8185, etc.).
  • Predicate Device Performance: The established safety and effectiveness of the ResMed Sullivan AutoSet CPAP System (K980721) and the ResMed Sullivan HumidAire Heated Humidifier (K971260). The new device demonstrates "substantial equivalence" to these.
  • Engineering and Bench Testing: Implicit in the statement "This submission presents the results of this testing, and together with detailed descriptions demonstrate Substantial Equivalence..."

8. The sample size for the training set

• Not applicable. This document does not describe a machine learning algorithm that requires a "training set."

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

• Not applicable. This document does not describe a machine learning algorithm or a training set.

Summary of Device and Approval Process:

The AUTOSET SPIRIT CPAP System is a non-invasive Continuous Positive Airway Pressure (CPAP) system for treating Obstructive Sleep Apnea (OSA) in adults. Its approval via the 510(k) pathway was based on demonstrating "Substantial Equivalence" to two predicate devices: the ResMed Sullivan AutoSet CPAP System (K980721) and the ResMed Sullivan HumidAire Heated Humidifier (K971260). The submission included:

• Detailed descriptions of the device, highlighting shared design features with predicate devices.
• Results from testing against a series of international and FDA-recognized standards for medical electrical equipment, electromagnetic compatibility, enclosure protection, humidifiers, and sleep apnea therapy devices.

The FDA's finding of substantial equivalence (K013843) on July 16, 2002, indicates that the agency determined the AUTOSET SPIRIT CPAP System to be as safe and effective as its predicate devices, based on the provided technical and regulatory compliance information, rather than a new clinical effectiveness study with defined performance acceptance criteria.

Ask a specific question about this device