Search Results

The Dream Wear Silicone Pillows Mask is intended to provide an interface for application of CPAP or bi-level therapy to patients. The mask is for single patient use in the home or multi-patient use in the hospital/institutional environment. The mask is to be used on patients (>66lbs/30kg) for whom CPAP or bi-level therapy has been prescribed.

The DreamWear Silicone Pillows Mask consists of a nasal pillows cushion, a silicone mask frame, an elbow with swivel and exhalation ports, headgear with arm extenders, and optional fabric sleeves. The nasal pillows cushion tips seal at the entrance to the nillows cushion base sits under the nares, and comes in four sizes (small, medium, medium wide, large).

Exhalation ports are incorporated into the mask. The built-in exhalation ports are molded into the front of the cushion as well as the top of the elbow. The mask exhalation ports for the DreamWear Silicone Pillows Mask were incorporated in both components, rather than only one of these components, to optimize diffusion, noise, comfort of breathing and CO2 inside the mask. The exhalation openings are used to flush exhaled CO2 out of the circuit. The fabric headgear is attached through the slots on the left and right headgear arms, which in turn are inserted into the slots on the sides of the frame to support the mask fit. The headgear can be adjusted with the hook and loop tabs. The elbow is inserted to the top of the frame. The fabric headgear goes over the mask frame and around the patient's head. The headgear comes in one size and includes adjustment sliders to allow for a large or small fitting on the patient's head. Fabric sleeves (optional) are also provided to provide additional comfort if desired.

The mask design is intended to remove movement restrictions during sleep with the air inlet on the top of the head and air movement through both sides of the frame and cushion for therapy delivery to the patient's nose. The tubing frame is intentionally designed such that one side can collapse when the patient is lying on their side, while therapy is delivered to the cushion through the open side of the frame. The frame is available in three sizes (small, medium, and large) The mask was tested and verified to ensure performance is maintained according to its specifications.

The mask elbow can rotate freely through 360 degrees and has a 22mm quick disconnect swivel that is used to connect the conventional air delivery hose between the mask and pressure source. The 22mm quick disconnect swivel can also rotate freely through 360 degrees and be easily removed from the elbow.

The mask is designed in such a way that they can be easily disassembled for cleaning or replacement purposes. The mask components may be cleaned by the patient in the home (single patient use) or disinfected by the professional in the hospital/institutional environment (multi-patient use).

The key benefits of this device to the patient are:

• Ease of use ●
• . Comfort
• Fewer movement restrictions ●
• Easy disassemblv .

The provided text describes the regulatory clearance for a medical device, the DreamWear Silicone Pillows Mask, and compares it to a predicate device, the TI Nasal Mask. However, it does not describe an AI model or a study proving that an AI-driven device meets acceptance criteria.

The document details the device's design, intended use, and various performance characteristics through non-clinical laboratory testing, not a clinical study involving human readers or AI.

Therefore, I cannot provide the requested information about acceptance criteria and studies for an AI device based on this input. The document explicitly states:

• Clinical Tests: "Clinical tests were not required to demonstrate the safety and effectiveness of the DreamWear Silicone Pillows Mask. All risks have been sufficiently mitigated and product functionality has been adequately assessed by non-clinical tests." (page 13)

This product is a physical medical device (a CPAP mask), not an AI-powered diagnostic tool. The performance metrics discussed (e.g., pressure drop, sound levels, CO2 rebreathing, leaks) are physical or mechanical properties of the mask itself, verified through laboratory tests (non-clinical tests), not cognitive performance metrics of an AI.

Ask a specific question about this device

This mask is intended to provide an interface for application of CPAP or bi-level therapy to patients. The mask is for single patient use in the home and multi-patient use in the hospital/institutional environment. The mask is to be used on patients > 7 years old (>40 lbs) for whom CPAP or bi-level therapy has been prescribed.

The Magneto Nasal Mask includes two cushion type options: a nasal, cradle cushion and nasal, pillows cushion. The nasal cradle cushion seals around the bottom of the patient's nose, and comes in five sizes (extra small, medium wide, large). The nasal pillows cushion tips seal at the entrance to the nares. The pillows cushion base sits under the nares, and comes in five sizes (extra small, small, medium wide, large). Both of the cushion design options contain enclosed magnets.

The mask frame also contains enclosed magnets, and connects to the mask cushion magnetically for easy and secure assembly by the user. The mask frame comes in one size and connects to the tubing with a snap fit, which allows the frame attached to the tubing.

The fabric headqear goes over the top of the mask frame and around the patient's head. The headgear comes in one size and includes adjustment sliders to allow for a large or small fitting on the patient's head.

The mask includes 10 mm tubing. The 10 mm tubing contains built-in exhalation at the top of the tube where the tubing connects to the mask frame. The tubing also includes an ISO 5356-1 compliant, 22 mm male conical swivel. The tubing swivel connects directly to ISO 5356-1 compliant, 22 mm female connections used on therapy device tubing. The tubing swivel detaches from the mask tubing, via a quick disconnect feature. The tubing connects to 12 mm connections when the tubing swivel is detached.

The provided document is a 510(k) Premarket Notification from the FDA for a medical device called the "Magneto Nasal Mask." It describes the device, its intended use, and compares it to a predicate device to demonstrate substantial equivalence.

This document does not contain the acceptance criteria or a study proving the device meets acceptance criteria in the format typically required for performance studies of AI/ML-driven medical devices. The Magneto Nasal Mask is a physical medical device (a mask for CPAP/bi-level therapy), not an AI/ML software device.

Therefore, many of the requested categories in the prompt (sample size for test set, data provenance, number of experts, adjudication method, MRMC study, standalone performance, training set details) are not applicable to the information provided in this 510(k) summary for a physical medical device.

However, I can extract the closest analogous information regarding performance testing and acceptance criteria for this physical device.

Acceptance Criteria and Reported Device Performance

The "acceptance criteria" for this physical device are primarily based on demonstrating equivalence to the predicate device and meeting relevant international standards for safety and performance. The "reported device performance" refers to the measurements taken for the Magneto Nasal Mask compared to the predicate.

Note: The acceptance criteria are largely implied by compliance with standards (e.g., ISO 17510 for masks, ISO 10993 for biocompatibility) and demonstrating that differences from the predicate do not raise new questions of safety and effectiveness. Specific numerical "acceptance criteria" are not explicitly stated as pass/fail thresholds in this summary for most metrics, but rather performance values are presented for comparison.

Study Proving Device Meets Acceptance Criteria:

A series of non-clinical tests were performed to verify the safety and effectiveness of the device and demonstrate substantial equivalence to the predicate device. These tests assessed various physical and performance characteristics of the mask.

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

• Test Set Sample Size: Not explicitly stated in terms of number of masks or specific test replicates for each performance metric, but the tests were conducted on the "Magneto Nasal Mask."
• Data Provenance: The tests were performed by the manufacturer, Respironics, Inc., to verify the device modifications. This is retrospective testing done on manufactured devices. The country of origin of the data is implicitly the USA, where Respironics is based and where the FDA submission occurred.

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

Not applicable. This is a physical medical device, not an AI/ML software. "Ground truth" in the AI/ML sense (e.g., expert annotation of images) is not used. Performance is assessed through objective physical and functional measurements against standards and predicate device data.

4. Adjudication method for the test set

Not applicable. This is a physical medical device, not an AI/ML software. Performance is measured objectively according to specified test protocols for physical devices.

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

Not applicable. This is a physical medical device, not an AI/ML software. No human readers or AI assistance are involved in interpreting its output.

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

Not applicable. This is a physical medical device, not an AI/ML software.

7. The type of ground truth used

The "ground truth" for this medical device is established by:

• International standards (e.g., ISO 17510 for mask performance, ISO 10993 for biocompatibility).
• Performance data of the legally marketed predicate device (Simple T Youth Nasal Mask, K140268).
• Engineering specifications and safety requirements for medical devices.
• The tests themselves produce objective physical measurements.

8. The sample size for the training set

Not applicable. This is a physical medical device, not an AI/ML software. It does not use a "training set" in the context of machine learning.

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

Not applicable. This is a physical medical device, not an AI/ML software.

Ask a specific question about this device

Sleepware G3 is a software application used for analysis (automatic and manual scoring), display, retrieval, summarization, report generation, and networking of data received from monitoring devices used to categorize sleep related events that help aid in the diagnosis of sleep-related disorders. It is indicated for use with adults (18 and older) and infant patients (one year old or less) in a clinical environment by or on the order of a physician.

The optional Somnolyzer scoring algorithms are for use with adults (18 and older) to generate an output that is ready for review and interpretation by a physician. Cardio-Respiratory Sleep Staging (CReSS) is an additionality of Somnolyzer which uses standard Home Sleep Apnea Test HSAT signals (in the absence of EEG signals) to infer sleep stage.

Sleepware G3 software is a polysomnography scoring application, used by trained clinical professionals, for managing data from sleep diagnostic devices using a personal computer. Sleepware G3 is able to configure sleep diagnostic device parameters, transfer data stored in sleep diagnostic device memory to the personal host computer, process and auto-score data to display graphical and statistical analyses, provide aid to clinical professionals for evaluating the physiological data waveforms relevant to sleep monitoring, and create unique patient reports.

Sleepware G3 includes an optional Somnolyzer plug-in. The auto-scoring algorithms of the Somnolyzer Inside software can be used in addition to, or in the place of, the auto-scoring algorithms that are included in Sleepware G3.

Sleepware G3, remains unchanged in function and fundamental scientific technology from Sleepware G3 which was cleared under K142988.

Here's a breakdown of the acceptance criteria and the study proving the device meets those criteria, based on the provided text:

Acceptance Criteria and Reported Device Performance

The acceptance criteria for the Somnolyzer scoring algorithms are based on demonstrating non-inferiority to manual expert scoring. The reported device performance indicates that all primary and secondary endpoints were met.

Detailed Study Information:

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

   • Test Set Sample Size: A total of 1,204 polysomnography (PSG) and home sleep apnea test (HSAT) files were used in the five clinical studies.
   • Data Provenance: The document does not explicitly state the country of origin. The studies are described as using a "large, diverse sample... collected via a number of different platforms," suggesting diverse sources but not specifying geographical location. The studies were likely retrospective, as they involved validating algorithms against existing manual scoring, but this is not explicitly stated.

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

   • Number of Experts: Not explicitly stated how many individual experts were used across all studies. However, the non-inferiority margin for comparisons was "set at the lower-margin of the agreement observed across expert technologists." This implies multiple experts were involved in defining the range of agreement for ground truth.
   • Qualifications of Experts: The experts are referred to as Registered Polysomnographic Technologists (RPSGT). This indicates their professional qualification in sleep study scoring.

3. Adjudication method for the test set:

   • The document implies a form of consensus or agreement among experts was utilized to set the non-inferiority margin, but it does not explicitly describe a specific adjudication method like 2+1 or 3+1 for individual cases within the test set. The focus is on comparing the algorithm's performance against the established range of agreement among experts.

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:

   • No, an MRMC comparative effectiveness study was not the primary focus described. The study design primarily involved a standalone evaluation of the AI algorithm (Somnolyzer) against human expert scoring, demonstrating its non-inferiority.
   • The document states that Somnolyzer's output is "ready for review and interpretation by a physician," implying it assists human readers by providing a pre-scored output. However, it does not quantify the improvement in human reader performance with AI assistance versus without AI assistance.

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

   • Yes, a standalone evaluation was performed. The clinical studies "validated the Somnolyzer and CReSS algorithms against manual scoring." The non-inferiority claims ("Somnolyzer scoring... is non-inferior to manual expert scoring") directly refer to the algorithm's performance without human intervention in the scoring process.

6. The type of ground truth used:

   • The ground truth was expert consensus scoring. The document states that the algorithms were validated "against manual scoring" by "expert technologists" (RPSGTs). The non-inferiority margin was based on "the agreement observed across expert technologists."

7. The sample size for the training set:

   • The document does not provide information on the training set sample size. The provided text focuses solely on the clinical performance testing for validation.

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

   • As the training set information is not provided, the method for establishing its ground truth is also not described in the document.

Ask a specific question about this device

Care Orchestrator is intended to support clinicians by tracking data on patients who are prescribed compatible therapy devices in accordance with the intended use of those therapy devices. Care Orchestrator provides remote patient data collection & viewing and is intended to be used by healthcare representatives (e.g., Physicians, Clinicians, Durable Medical Equipment providers) in conjunction with compatible non-life support therapy devices to adjust prescription and/ or performance settings. In addition, Care Orchestrator can be used for analysis (automatic and manual scoring), display, retrieval, summarization, and report generation of data received from compatible monitoring devices used to categorize sleep-related events that help aid in the diagnosis of sleep-related disorders. The Home Sleep Testing function of Care Orchestrator is indicated for Adult use only. Care Orchestrator allows read-only access to patients. Care Orchestrator is intended to be used in hospital, institutional, provider, and home care settings.

Care Orchestrator is a cloud-based software platform that allows entities including physicians, other professional home and clinical staff, and durable medical equipment providers in a patient's therapy lifecycle the ability to manage patients and referrals, control access to patient information and therapy data, enhance patient compliance management workflow, and gain efficiencies in the overall patient therapy workflow. Care Orchestrator also provides a method for sleep data acquired from a supported home sleep test (HST) devices to be imported, scored and reviewed by a qualified user. The HST function of Care Orchestrator is for adult use only.

The intent of the Care Orchestrator sleep diagnostic functionality is to provide a capability that allows users to analyze, score, review and generate clinical reports for HST acquisitions (i.e. sleep studies) from within a web browser. Users can upload acquisitions to Care Orchestrator and perform these actions all from within the browserbased Care Orchestrator Client application.

Care Orchestrator software has undergone no significant changes since in K181053. The addition of the Home Sleep Testing features, subject of this submission, add a sub-set of Home Sleep Testing functionality.

The provided document is a 510(k) summary for the "Care Orchestrator with Home Sleep Testing" device. It outlines the device's indications for use, its comparison to a predicate device, and a brief statement about performance data. However, it does not contain a detailed study proving the device meets specific acceptance criteria, nor does it provide a table of acceptance criteria with reported device performance.

The document states:

• "Software verification and validation testing was conducted and documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices."
• "Software verification and validation included software code reviews, automated testing, bench verification testing and labeling review."

This indicates that general software V&V activities were performed, but the specific details requested in your prompt (acceptance criteria table, sample sizes, ground truth establishment, MRMC studies, etc.) are not included in this summary.

Therefore, many of your questions cannot be answered from the provided text.

Here's a breakdown of what can be inferred or directly stated, and what information is missing:

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

• Missing from the document. The document states that software verification and validation testing was done, but it does not provide a table of specific acceptance criteria or quantitative performance metrics for those criteria.

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

• Missing from the document. The summary mentions "bench verification testing" but does not detail the sample size of the test set, the nature of the data (e.g., patient data, synthetic data), its origin, or whether it was retrospective or prospective.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• Missing from the document. The document does not specify if experts were used to establish ground truth for a test set, nor their number or qualifications.

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

• Missing from the document. There is no information provided regarding any adjudication methods for a test set.

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

• Missing from the document. The document does not mention any MRMC comparative effectiveness studies. The device's function involves automatic and manual scoring to aid in the diagnosis of sleep-related disorders, but how it impacts human reader performance through such studies is not discussed.

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

• Partially addressed. The device performs "analysis (automatic and manual scoring)". The "automatic scoring" component implies standalone algorithmic functionality. However, the document does not provide specific performance metrics for this standalone component.

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

• Missing from the document. The type of ground truth used for any validation of the automatic scoring algorithm is not specified.

8. The sample size for the training set

• Missing from the document. This document focuses on the regulatory submission and does not disclose details about the training set size for any machine learning components.

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

• Missing from the document. Similar to the test set, the method for establishing ground truth for any potential training set is not provided.

Ask a specific question about this device

The DreamStation 2 CPAP/DreamStation 2 Auto CPAP system delivers positive airway for the treatment of Obstructive Sleep Apnea in spontaneously breathing patients weighing over 30 kg (66 lbs). It is for use in the home or hospital/institutional environment.

The DreamStation 2 System uses a microprocessor-controlled blower to treat patients with Obstructive Sleep Apnea (OSA). There are 2 models: DreamStation 2 and DreamStation 2 Advanced. Both aforementioned models will be available in two therapy modes: CPAP only and Auto CPAP. With CPAP therapy, the device provides a continuous positive airway pressure throughout the entire therapy session. With Auto CPAP therapy, the device provides a positive airway pressure that automatically adjusts to the patient's needs as various breathing events are detected, such as apneas and hypopneas. In addition to the therapy modes, the DreamStation 2 System provides several optional features to aid with patient comfort. These patient comfort features include: Ramp Plus, adjustable pressure relief (FLEX), EZ-Start, Opti-Start, and humidification (adaptive and adaptive with heated tube). Note: some of the features are only available in the DreamStation 2 Advanced model. The DreamStation 2 device also features integrated Bluetooth and cellular technology for the transfer of patient management data between the therapy device and Respironics proprietary compliance software, Care Orchestrator.

This document describes the 510(k) premarket notification for the DreamStation 2 System, a noncontinuous ventilator (CPAP system) for treating Obstructive Sleep Apnea. It does not contain information about a study proving the device meets acceptance criteria from clinical trials involving human subjects, nor does it provide a table of acceptance criteria and reported device performance from such a study.

The document primarily focuses on demonstrating substantial equivalence to predicate devices through non-clinical performance testing, software testing, biocompatibility testing, general safety and electrical compatibility testing, and human factors/usability testing.

Therefore, I cannot fulfill the request for information regarding clinical acceptance criteria, study details, sample sizes, expert ground truth, MRMC studies, standalone performance, or training set specifics, as this information is not present in the provided text.

The document explicitly states: "Clinical tests were not required to demonstrate the safety and effectiveness of the DreamStation 2 System. Safety and efficacy of the DreamStation 2 System has been established via nonclinical tests."

The only "acceptance criteria" presented are related to technical specifications (e.g., pressure accuracy) and compliance with various international standards, which is then demonstrated through the completion of non-clinical testing.

Here's a breakdown of what is available in the document regarding performance and testing:

1. Table of Acceptance Criteria and Reported Device Performance:

The document provides a comparison of technical characteristics between the DreamStation 2 System and its predicate devices in Table 5-1 (pages 5-6) and Table 5-2 (page 8). While it doesn't explicitly state "acceptance criteria" for clinical outcomes, it does list performance specifications for pressure accuracy and notes whether the subject device's performance is "Same" or "Similar" to the predicates.

Note: The "Acceptance Criteria" column is inferred from the document's claim of "Same" or "Similar" performance to the predicates, which is the basis for substantial equivalence. The document does not specify exact acceptance criteria values for new features, but rather demonstrates that the new device meets or exceeds the performance of existing legally marketed predicate devices for similar functionality.

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

• Not Applicable. The document explicitly states that clinical tests were not required. The testing performed was non-clinical. Therefore, no "test set" of patient data or data provenance information is provided.

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

• Not Applicable. As no clinical "test set" was used, there was no need for experts to establish ground truth in a clinical context. Product requirement and specification experts within the company would have been involved in defining the non-clinical testing parameters.

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

• Not Applicable. This refers to clinical data adjudication, which was not performed.

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. No MRMC study involving human readers or AI assistance was performed or described. This device is a CPAP system, not an AI-driven diagnostic tool.

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

• Not Applicable. This refers to AI algorithm performance. The DreamStation 2 System is a hardware device for delivering airway pressure, not primarily an AI algorithm. Its software is for controlling the device and managing patient data, not for making diagnostic or treatment recommendations independently in an "algorithm only" sense beyond its intended function.

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

• Not Applicable (for clinical ground truth). For the non-clinical and software testing, the "ground truth" would be the device's technical specifications, design requirements, and adherence to recognized international standards (e.g., ISO, IEC).

8. The sample size for the training set:

• Not Applicable. No clinical training set was used or described.

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

• Not Applicable. No clinical training set was used or described.

Summary of the Study that Proves the Device Meets the (Non-Clinical) Acceptance Criteria:

The DreamStation 2 System demonstrated that it meets acceptance criteria through a series of non-clinical performance tests which include:

• Performance Testing: To address device requirements, risk mitigations, show substantial equivalence, and assure safety and efficacy. (Details not provided in terms of specific tests, but performance characteristics like pressure accuracy are compared to predicates).
• Software Testing: Developed according to IEC 62304:2015 ("Medical Device Software - Software Life Cycle Processes"). Software verification and validation were performed based on product requirements, following FDA Guidance "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices." The software was deemed to have a "Moderate" level of concern.
• Biocompatibility Testing: Conducted in accordance with FDA Guidance and international standards ISO 10993-1:2018 and ISO 18562-1:2017, proving the device to be biocompatible.
• General Safety, Electrical Safety, and Electromagnetic Compatibility (EMC) Testing: The system complies with AAMI/ANSI/ES 60601-1:2005/A1:2012, IEC 60601-1-2:2014, IEC 60601-1-6:2013, IEC 60601-1-11:2015, ISO 80601-2-61: 2011, ISO 80601-2-70: 2015, and ISO 80601-2-74: 2017.
• Human Factors/Usability Testing: Aligned with IEC 62366-1: 2015 and FDA guidance "Applying Human Factors and Usability Engineering to Medical Devices." A human factors validation study indicated safe and effective operation by intended users with acceptable residual risk.

The conclusion drawn from these non-clinical tests is that the DreamStation 2 System is substantially equivalent to its predicate devices, and that modifications do not raise new questions of safety and effectiveness. Clinical tests were not deemed necessary.

Ask a specific question about this device

The SomnaPatch™ is a single use physiologic recorder intended to collect and record data for use by clinical software used in polysomnography and sleep disorder studies by providing the information required for calculation of the apnea-hypopnea index. It is intended for adult use and can be used in a hospital, clinic, or patient home.

The SomnaPatch Home Sleep Test is a single-use disposable physiologic recorder used as an aid in the diagnosis of sleep related breathing disorders. The SomnaPatch device is affixed to the face of the user and is designed to continuously be worn overnight, up to approximately 10-hours. Once activated, the device records and stores patient data for the wear period. After the wear period, the device is returned to the healthcare professional, where the data is downloaded and processed by the SomnaPatch Data Processing Software. The processed data can be viewed by a healthcare professional and analyzed either manually or by third-party sleep data viewing and scoring software. The SomnaPatch device is not involved in the data management performed by the host or third-party data viewing or scoring software.

The forehead patch contains three sensors (Pressure Sensor, Accelerometer, and Optical SpO2), wherein their outputs' are recorded to a secure MicroSD card. The SomnaPatch Data Processing Software installed on a PC downloads the recorded data from the secure MicroSD card to derive 4 channels (nasal pressure, oxygen saturation (SpO2), pulse rate, and head position) of data in EDF format.

Here's an analysis of the provided text to extract information about the SomnaPatch device's acceptance criteria and the study proving it, structured as requested:

Acceptance Criteria and Device Performance for SomnaPatch

The document primarily focuses on demonstrating substantial equivalence to a predicate device (Alice PDx) rather than explicitly stating pre-defined acceptance criteria with precise numerical targets for clinical accuracy. However, based on the clinical study summarized and the comparison section, we can infer the performance considered acceptable.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size (Clinical Study for AHI accuracy): 178 participants
• Data Provenance (Clinical Study for AHI accuracy): Multi-center, open-label study (country of origin not explicitly stated, but submission is to US FDA, implying relevance to US market). The study involved a "within-subject comparison" against overnight polysomnography (PSG) in a laboratory setting. This indicates a prospective study design for data collection against the gold standard.
• Sample Size (Clinical Testing for SpO2 signal): Not explicitly stated, but refers to "arterial blood samples drawn under hypoxic conditions over the SaO2 range of 70-100%."
• Data Provenance (Clinical Testing for SpO2 signal): Partnered with University of California San Francisco (UCSF) Hypoxia Research Laboratory. This is likely a prospective clinical study.

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

The document does not explicitly state the number or specific qualifications of experts used to establish the ground truth for scoring the AHI from the gold standard PSG, beyond referring to "in-lab polysomnography (PSG)" being the gold standard. For the SpO2 testing, the ground truth was "arterial blood samples," which is an objective physiological measure, not dependent on expert interpretation.

4. Adjudication Method for the Test Set

The document does not describe the adjudication method for the test set regarding AHI scoring or any other clinical readouts. It mentions "in-lab polysomnography (PSG)" as the gold standard, implying that the AHI from PSG was considered definitive.

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 involving human readers with and without AI assistance was not conducted or described. The clinical study focused on the device's standalone accuracy in estimating AHI compared to PSG, not on assisting human readers.

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

Yes, a standalone performance evaluation was conducted. The clinical study described for AHI accuracy directly assessed the SomnaPatch device's ability to estimate AHI compared to the gold standard PSG. The SpO2 accuracy validation was also a standalone assessment against arterial blood samples. The device processes data via software to derive channels and calculate AHI, which is then viewed and analyzed by a healthcare professional. The core evaluation is the device's accuracy in producing this data, which is a standalone performance metric.

7. The Type of Ground Truth Used

• For AHI Accuracy: Overnight polysomnography (PSG) in a laboratory setting (clinical gold standard).
• For SpO2 Accuracy: Arterial blood samples (objective physiological measurement).
• For Sensor Performance (Pressure): Hypopneas and apneas generated using ASL scripts, then viewed in Sleepware G3. This appears to be a simulated, controlled environment ground truth rather than real patient data for this specific sensor comparison.

8. The Sample Size for the Training Set

The document does not specify a sample size for a training set. The device appears to be a physiological recorder that provides raw/processed data channels (like nasal pressure, SpO2) and then relies on clinical software or healthcare professionals to calculate AHI. There's no indication that the device itself uses a trainable algorithm in the sense of deep learning or machine learning that would require a distinct training set for its core function of recording and deriving these physiological channels.

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

Since no training set is mentioned in the context of a trainable algorithm (see point 8), this information is not applicable and therefore not provided in the document. The device's function is data collection and processing based on sensor readings.

Ask a specific question about this device

The Care Cycle Connect software application is intended for use with Trilogy Series ventilators by both caregivers and clinicians. The application pairs with the Trilogy device via a Bluetooth connection. The application provides the caregiver remote patient monitoring, and alarm surveillance. Alarm surveillance consists of both an audible tone and a visible alert if an alarm condition exists. The application provides the clinician with the ability to view, collect and store patient ventilator usage data. Care Cycle Connect also provides educational information on ventilator use to both caregivers and clinicians. It is intended to be used in the home, and hospital/ institutional settings. The Care Cycle connect application is intended to supplement and not replace any part of the current device monitoring procedures.

The Care Cycle Connect application is an accessory to a continuous ventilator (product code MOD). Care Cycle Connect is intended for use with the Trilogy Series of Ventilators cleared by the US FDA under K083526, K093416, K093905, and K111610. Care Cycle Connect (CCC) is a mobile software application designed to provide features and functions related to respiratory care in the home, hospital and institutional healthcare settings. The application provides the caregiver remote patient monitoring and alarm surveillance. The CCC application has been designed with two users in mind, the caregiver and the clinician. The functionality of the application is tailored to the different needs of these users and is configured when the application is installed. At the initial start-up of the application, users are asked to choose either careqiver (for patients and their in-home caregivers) or clinician mode. Functionality is based on the configuration selected. Once this choice is made, users cannot switch back and forth between the two configurations. The primary users expected to interact with Care Cycle Connect in the context of patient care in the home (the main use scenario) are caregivers and respiratory therapists (clinicians). CCC may also be used if the patient is in a hospital or institutional environment (sub-acute care facility). Caregivers are not expected to use CCC in a hospital or institutional setting. Care Cycle Connect provides constant feedback to the caregiver while the app is connected to the ventilator. This feedback is displayed via the Manometer Display feature within the application. This constant display provides data on the patient's use of the ventilator, ensuring that the ventilator is providing therapy. Care Cycle Connect will also provide educational information on the use of the ventilator to the caregiver or clinician, independent of being connected to the ventilator. The respiratory therapist will use the app when connected to a patient ventilator while on a home visit to gather ventilator data. It provides an interface for keeping patient information. When the app is not connected to the patient ventilator, the clinician can review stored data, such as appointments, journal, and vent check records. In the hospital or institutional environment. CCC may be used by clinicians to schedule and perform vent checks, which would be completed in the patient's room. Care Cycle Connect is an application that can be loaded onto an Apple device (iPad) that uses iOS 8.0 or more recent. The application relies on a Bluetooth Class 1 radio connection to a Trilogy ventilator. With the exception of low level communication protocol information (i.e., handshake connection), the Trilogy device does not accept any data, commands, or controls from the CCC Application. The Trilogy device functionality is not changed in any manner by connecting to the CCC Application. The Trilogy device simply sends information to the CCC Application on a periodic basis.

The provided text describes the acceptance criteria and study information for the "Care Cycle Connect" software application.

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not explicitly state the numerical sample size for the test set used in "Software Verification and Validation Testing" or "Usability Testing." It mentions "complete system level testing" and "usability testing was completed," implying a sufficient set of tests were performed.

• Data Provenance: Not explicitly stated as retrospective or prospective patient data. The testing appears to be primarily laboratory/bench testing and simulated use, as it focuses on software verification, validation, and usability with the device itself, rather than clinical patient outcomes. The origin is implicitly related to the manufacturer's testing facilities (Respironics Inc., USA).

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

The document does not specify the number of experts or their qualifications used to establish ground truth for the test set. The ground truth for the testing described seems to be based on compliance with international standards (IEC, ISO) and the device's functional design specifications, rather than expert consensus on medical images or diagnoses.

4. Adjudication Method for the Test Set

The document does not mention an adjudication method for the test set. The testing described focuses on discrete pass/fail criteria against engineering requirements and established standards.

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

No. The document explicitly states: "Clinical tests were not required to demonstrate the substantial equivalence of Care Cycle Connect. Product functionality has been adequately assessed by non-clinical tests." Therefore, an MRMC comparative effectiveness study was not performed.

6. Standalone Performance (Algorithm Only without Human-in-the-Loop Performance)

Yes, a standalone performance assessment was effectively done. The "Software Verification and Validation Testing" and "Non-Clinical Tests" describe the evaluation of the Care Cycle Connect application's functionality, adherence to software life cycle processes, alarm system compliance, and usability independent of a clinical human-in-the-loop study. These tests evaluate the algorithm's (software's) performance against its design requirements and relevant standards.

7. Type of Ground Truth Used

The ground truth used for the testing of Care Cycle Connect appears to be:

• Compliance with International Standards: e.g., IEC 62304, IEC 60601-1-6, IEC 60601-1-8, IEC 60601-1-11, IEC 62366, ISO 14971.
• Product Requirements/Design Specifications: The software was tested against "product requirements" and various listed functionalities (device pairing, login, information display, alarm signals, etc.).
• Guidance Documents: Adherence to FDA guidance documents (e.g., for software, human factors, mobile medical apps, cybersecurity, wireless technology, home use devices).

Essentially, the "ground truth" is a combination of regulatory compliance, engineering specifications, and validated functional behavior.

8. Sample size for the Training Set

Not applicable. The document describes the verification and validation of a software application for remote monitoring and data display for a medical device. It does not mention any machine learning or AI components that would require a dedicated "training set." The software appears to be rule-based or deterministic, rather than data-driven in a way that requires a training set.

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

Not applicable, as there is no mention of a training set for machine learning/AI.

Ask a specific question about this device

This mask is intended to provide an interface for application of non-invasive ventilation to patients. The mask is for single patient use in the home and multi-patient use in the hospital/institutional environment. The mask is to be used on patients greater than 10 kg/22 lbs (>10 kg/22 lbs) for whom non-invasive ventilation has been prescribed. Use of this mask is limited by the indications for use of the compatible therapy device with respect to patient weight.

The Simple T Pediatric Nasal Mask is intended to be used with positive airway pressure devices. For use of this mask with a CPAP therapy device, the patient population is limited by the intended use of the device (e.g. > 30 kg). In other words, this mask can be used with a variety of therapy devices which may have their own limitations on patient population. If the therapy device itself is limited to patients greater than 10 kg (e.g. 30 kg), then the use of this mask does not expand the intended use of that therapy device.

The mask provides a seal such that positive pressure from the positive pressure source is directed into the patient's nose. It is held in place with a fabric frame and an adjustable headgear. The cushion contains an adjustment dial that can be engaged to reduce minor leaks around the nose. The mask may be cleaned in the home (single-patient use) or reprocessed by the professional in the hospital/institutional environment through high-level disinfection processes (multi-patient use).

This document is a 510(k) Summary for the Simple T Pediatric Nasal Mask (K151120). It details the substantial equivalence of the new device to previously cleared predicate devices. Unfortunately, the document does not contain specific acceptance criteria or study data in the format requested for AI/ML device testing.

The document discusses performance testing, but this refers to engineering tests on the physical mask (e.g., intentional leak, total mask leak, CO2 rebreathing, cleaning validation), not to the performance of an AI model. There is no mention of an algorithm or AI component in this device.

Therefore, I cannot provide the requested information regarding:

1. A table of acceptance criteria and reported device performance for an algorithm.
2. Sample size for a test set, data provenance, number of experts, or adjudication method for an AI/ML model.
3. Multi-reader multi-case (MRMC) comparative effectiveness study or AI assistance effect size.
4. Standalone (algorithm only) performance.
5. Type of ground truth (expert consensus, pathology, outcomes data) for an AI/ML model.
6. Sample size for the training set or how ground truth for the training set was established.

This document is for a physical medical device (a nasal mask) and outlines its substantial equivalence based on material, design, and non-clinical performance testing. It explicitly states: "Clinical tests were not required to demonstrate the safety and effectiveness of the Simple T Pediatric Nasal Mask. Product functionality has been adequately assessed by non-clinical tests." This further confirms the absence of AI/ML or clinical efficacy studies as would be required for such devices.

Ask a specific question about this device

This Mask is intended to provide a patient interface for application of noninvasive ventilation. The mask is to be used as an accessory to ventilators which have adequate alams and safety systems for ventilation failure, and which are intended to administer CPAP or positive pressure ventilation for treatment of respiratory insufficiency or obstructive sleep apnea. The mask is for single use in the hospital/institutional environment only. The mask is to be used on patients (>40lbs/20kg) who are appropriate candidates for noninvasive ventilation.

The AF541 SE Full Face Mask is an oral-nasal full face mask that is available in two cushion configurations. The AF541 SE Full Face has two cushion configurations, an Over the Nose (OTN) cushion and an Under the Nose (UTN) cushion. The AF541 SE Full Face Mask will have interchangeable cushions that attach to a common frame. There will be four sizes available for the over the nose option (S, M, L, XL). The UTN option will have three sizes available (A, B, C). The AF541 SE will include a 4 point headgear and capstrap to allow for oral access with either headgear option.

The provided text is a 510(k) Summary for a medical device called the "AF541 SE Full Face Mask." This type of document is for demonstrating substantial equivalence to a predicate device, not for proving that a device meets specific clinical performance acceptance criteria in the way an AI diagnostic device would.

Therefore, the document does not contain the information requested in your prompt regarding:

• A table of acceptance criteria and reported device performance for an AI model.
• Sample sizes, data provenance, number of experts, adjudication methods, MRMC studies, or standalone performance for an AI model.
• Ground truth details for test or training sets of an AI model.

The document describes non-clinical performance and biocompatibility tests for a physical medical device (a mask) and compares it to a predicate device.

However, to address some elements from your prompt based on the provided text, and distinguish them from what is not present (AI-specific criteria):

Acceptance Criteria and Device Performance (Non-Clinical for a Physical Mask Device):

The document states that "Design verification tests were performed on the AF541 SE Full Face Mask. All tests were verified to meet the required acceptance criteria." It also notes that "Performance testing was performed before and after cleaning treatments to verify that the device modifications did not raise new safety and effectiveness concerns of the subject device."

The specific acceptance criteria values or the reported performance data are not provided in this summary. It only states that the tests met the required acceptance criteria.

Types of Non-Clinical Performance Testing Performed:

• Total Mask Pressure Drop: The device was tested to ensure the pressure drop across the mask meets certain specifications for proper ventilation. (Specific criteria/results not provided).
• Total Mask Leak: The device was tested for leakage to ensure effective delivery of ventilatory pressure. (Specific criteria/results not provided).
• Deadspace: The dead space within the mask was measured to ensure it is within acceptable limits for effective ventilation. (Specific criteria/results not provided).

Biocompatibility Testing (for materials in contact with tissue):

New materials used in the mask were classified as external communicating, tissue contact, with a contact duration C (> 30 days cumulative). The following biocompatibility tests were completed and presumably met their acceptance criteria:

• Muscle Implantation Study in Rabbits (4 Weeks)
• Muscle Implantation Study in Rabbits (12 Weeks)
• Genotoxicity: Bacterial Reverse Mutation Study
• Genotoxicity: Mouse Lymphoma Assay
• Genotoxicity: Mouse Peripheral Blood Micronucleus Study
• Intracutaneous Injection Test
• Kligman Maximization Test
• Agar Diffusion Test (Direct Contact)

Regarding the AI-specific questions from your prompt:

1. Table of acceptance criteria and the reported device performance: Not applicable/Not present. This document is for a physical medical device (mask), not an AI diagnostic/analytic device. It states non-clinical tests met acceptance criteria, but no specific values or a table are provided.
2. Sample size used for the test set and the data provenance: Not applicable/Not present. No test set for an AI model.
3. Number of experts used to establish the ground truth... and qualifications: Not applicable/Not present. No ground truth for an AI model.
4. Adjudication method: Not applicable/Not present. No adjudication method for an AI model.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done...: Not applicable/Not present. No MRMC study for an AI model.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable/Not present. No algorithm performance.
7. The type of ground truth used: Not applicable/Not present.
8. The sample size for the training set: Not applicable/Not present.
9. How the ground truth for the training set was established: Not applicable/Not present.

Conclusion from the document:

The manufacturer concluded that the new AF541 SE Full Face Mask is substantially equivalent to the predicate device (AF531 SE Full Face Mask - K101129) based on similar intended use, operating principle, design, materials (with biocompatibility testing for new materials), and manufacturing process, and that non-clinical performance and design verification tests (Total Mask Pressure Drop, Total Mask Leak, Deadspace) were successfully met, raising no new safety or effectiveness concerns. Clinical tests were explicitly stated as "not required."

Ask a specific question about this device

AF541 EE Leak 1 Mask

This Mask is intended to provide an interface for application of CPAP or bi-level therapy to patients. The mask is for single use in the hospital/institutional environment only. The mask is to be used on patients (>40lbs/20kg) for whom CPAP or bi-level therapy has been prescribed.

AF541 EE Leak 2 Mask

This Mask is intended to provide an interface for application of CPAP or bi-level therapy to patients. The mask is for single use in the hospital/institutional environment and single patient use in the home. The mask is to be used on patients (>40lbs/20kg) for whom CPAP or bi-level therapy has been prescribed.

The AF541 EE Full Face Mask is an oral-nasal full face mask that is available in various configurations (cushions and elbows). The AF541 EE Full Face has two cushion configurations, an Over the Nose (OTN) cushion and an Under the Nose (UTN) cushion. The following elbow configurations are available: EE Leak 1 and EE Leak 2. The Leak 1 and Leak 2 elbows have an anti-asphyxia valve. In addition, the Leak 2 elbow has built in exhalation to provide intentional leak when needed.

The AF541 EE Full Face Mask will have interchangeable cushions that attach to a common frame. There will be four sizes available for the nose option (S, M, L, XL). The UTN option will have three sizes available (A, B, C).

The AF541 mask will include a 4-point headgear and capstrap to allow for oral access with either headgear option. There will be 22 mm female mask frame. The AF541 OTN and UTN will be compatible with the EE Leak 1 and EE Leak 2 elbow.

The provided text is a 510(k) Summary for the AF541 EE Full Face Mask. This type of submission focuses on demonstrating substantial equivalence to a predicate device, primarily through non-clinical performance and biocompatibility testing, rather than extensive clinical studies as seen with novel medical devices or AI-driven diagnostics.

Therefore, many of the requested categories related to clinical studies, AI performance, ground truth, and expert evaluation are not applicable or detailed in this document. The information available focuses on engineering and material performance.

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

1. Table of Acceptance Criteria and Reported Device Performance

The document states that "Design verification tests were performed on the AF541 EE Full Face Mask. All tests were verified to meet the required acceptance criteria." However, it does not explicitly list specific numerical acceptance criteria for each performance test. It only lists the tests performed and implicitly confirms that the device met the (unspecified) acceptance criteria.

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

The document does not specify a "test set" in the context of patient data or clinical imaging. The tests performed are engineering-focused on the device itself.

• Sample Size for performance testing: Not specified. It refers to the physical device being tested.
• Data Provenance: The nature of the tests (engineering performance, biocompatibility) implies laboratory testing of the device and its materials, not patient data from a specific country or retrospective/prospective study.

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

Not applicable. The ground truth for engineering performance tests is typically established by engineering standards and specifications, not expert clinical consensus.

4. Adjudication Method for the Test Set

Not applicable. This concept is relevant for studies involving human interpretation or subjective assessments, which are not detailed for these engineering tests.

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

No, an MRMC comparative effectiveness study was not done. The document explicitly states: "Clinical tests were not required to demonstrate the substantial equivalence of the AF541 EE Full Face Mask. Product functionality has been adequately assessed by non-clinical tests."
This device is a face mask, not an AI diagnostic tool that would typically undergo such a study.

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

Not applicable. This device is a medical mask, not an algorithm or software.

7. The Type of Ground Truth Used

For the performance tests, the "ground truth" would be the established engineering and safety standards (e.g., ISO specifications) to which the device was compared.
For biocompatibility, the ground truth is the absence of adverse biological reactions as defined by toxicology and material science standards (e.g., ISO 10993-1).

8. The Sample Size for the Training Set

Not applicable. This device does not involve a "training set" in the context of machine learning or AI.

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

Not applicable as there is no training set for this device.

Ask a specific question about this device