Search Results

The ApneaLink™ Air device is indicated for use by Health Care Professionals (HCP), where it may aid in the diagnosis of sleep disordered breathing for adult patients. ApneaLink Air records the following data: patient respiratory nasal airflow, snoring, blood oxygen saturation, pulse, respiratory effort and body position during sleep. The device uses these recordings to produce a report for the HCP that may aid in the diagnosis of sleep disordered breathing or for further clinical investigation. The device is intended for home and hospital use under the direction of a HCP.

The ApneaLink Air recorder is a 5-channel battery-powered respiratory pressure sensor and oximetry system. ApneaLink Air provides recordings of respiratory pressure, respiratory effort, pulse rate, oxygen saturation and body position during sleep. The physician prescribed device will help to recognize sleep-related respiratory disorders. The ApneaLink Air recorder and the respiratory effort sensor must be fastened with the re-usable belt on the patient's chest parallel to the spine. All relevant respiratory information during sleep will be collected via nasal cannula, pulse oximetry module and respiratory effort sensor. The disposable plastic nasal cannula is connected to the ApneaLink Air recorder and fixed at the patient's nose. The oximetry sensor is connected to the Xpod and fixed at the patient's finger. The Xpod is connected to the ApneaLink Air recorder. The respiratory effort sensor is connected to the ApneaLink Air recorder and held in place by the belt. LED's indicate if the sensors are attached correctly. A Test complete light advises at the end of a recording if sufficient data for analysis was recorded during the night. After recording, the ApneaLink Air recorder must be returned to the physician. With the ApneaLink Software the physician can generate a report with the recorded and analyzed data (respiratory pressure, respiratory effort, pulse rate, oxygen saturation) to aid in diagnosis. The body position data is stored as an EDF+ file on the recorder. It is accessible on a computer via USB connection using an EDF viewer.

The provided text describes the ApneaLink Air device, its indications for use, and a comparison to predicate devices, but it contains limited details regarding acceptance criteria for clinical performance and specific studies proving those acceptance criteria for the diagnosis of sleep-disordered breathing. The document focuses more on demonstrating substantial equivalence based on technical specifications and mechanical/electrical safety testing, particularly highlighting the addition of body position recording.

Here's an analysis based on the information provided in the text, structured according to your request:

1. Table of Acceptance Criteria and Reported Device Performance

Based on the provided text, the device's clinical performance acceptance criteria and reported performance for aiding in the diagnosis of sleep-disordered breathing are not explicitly stated as quantitative metrics (e.g., sensitivity, specificity, accuracy).

The document states:

• "Detection of respiratory events and reported indices was cleared under K083575 (ApneaLink Plus) and remained unchanged in ApneaLink Pro (K131932) and ApneaLink Air." This implies that the clinical performance related to detecting respiratory events (and thus deriving indices like AHI) is considered equivalent to the predicate ApneaLink Plus (K083575). However, the specific acceptance criteria and performance data for ApneaLink Plus are not detailed in this document.
• Regarding the new feature, body position recording: "Clinical data with regard to body position recording are not required as the body position data do not alter or influence any of the indices (like e.g. AHI or Apnea Index) or data generated by the testing and bench testing is sufficient to prove that body position recording results are as accurate as specified." And "Additional side by side testing has been performed by using a protractor to show the defined position around the body axis for ApneaLink Air and Nox T3."

Given this, a table summarizing explicitly stated acceptance criteria and performance for the diagnostic aid function cannot be fully constructed from the provided text. The document infers equivalence to predicate devices for its core diagnostic function and relies on bench testing for the new body position feature.

2. Sample Size for the Test Set and Data Provenance

• Sample Size (Test Set): Not specified for clinical performance related to sleep-disordered breathing diagnosis. For the new body position recording feature, "Additional side by side testing has been performed by using a protractor" suggests direct comparison, but no specific number of subjects or samples is given.
• Data Provenance: Not explicitly stated for any clinical data mentioned or inferred. The document refers to "bench testing" and "side by side testing" without specifying if these involved human subjects or geographical origin. The device manufacturer is ResMed Germany Inc.

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

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified. This information would typically be part of a clinical study report, which is not fully provided here.

4. Adjudication Method

• Adjudication Method: Not specified.

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

• MRMC Study: No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study evaluating human readers' improvement with AI vs. without AI assistance was not mentioned in this document. The device itself is an assessment tool, not an AI-assisted diagnostic aid for human readers in the context of this submission.
• Effect Size: Not applicable, as no such study was described.

6. Standalone (Algorithm Only) Performance Study

• Standalone Performance Study: The document states, "Detection of respiratory events and reported indices was cleared under K083575 (ApneaLink Plus) and remained unchanged in ApneaLink Pro (K131932) and ApneaLink Air." This implies that the algorithm's performance for detecting respiratory events and generating indices was established in prior submissions (K083575), and its performance remains unchanged. However, no specific details of that standalone study (e.g., metrics, study design) are provided in this document.

7. Type of Ground Truth Used

• For Detection of Respiratory Events and Indices (inherited from predicates): Not explicitly stated in this document. Typically, full polysomnography (PSG) interpreted by sleep specialists is considered the gold standard for ground truth in sleep-disordered breathing diagnosis.
• For Body Position Recording (new feature): The new body position feature relies on "bench testing" and "using a protractor to show the defined position around the body axis." This indicates a physical measurement/reference standard for ground truth for the sensor's accuracy, not a clinical ground truth like pathology or outcomes data.

8. Sample Size for the Training Set

• Sample Size (Training Set): Not specified. This document pertains to regulatory submission for a device, not the development or training of an algorithm. The core functionality and algorithms are "unchanged" from a prior cleared device (K083575), so any training data for those algorithms would have been part of that earlier submission.

9. How Ground Truth for Training Set Was Established

• Ground Truth for Training Set: Not specified in this document. As above, any ground truth establishment for algorithm training would have been part of the previous K083575 submission.

Ask a specific question about this device

The ApneaLink™ Pro device is indicated for use by Health Care Professionals (HCP), where it may aid in the diagnosis of sleep disordered breathing for adult patients. ApneaLink Pro records the following data: patient respiratory nasal airflow, snoring, blood oxygen saturation, pulse and respiratory effort during sleep. The device uses these recordings to produce a report for the HCP that may aid in the diagnosis of sleep disordered breathing or for further clinical investigation. The device is intended for home and hospital use under the direction of a HCP.

The ApneaLink Pro recorder is a 4-channel battery-powered respiratory pressure sensor and oximetry system. ApneaLink Pro provides recordings of respiratory pressure, respiratory effort, pulse rate and oxygen saturation during sleep. The physician prescribed device will help to recognize sleep-related respiratory disorders. The patient may perform the recording at home by himself. The Apnealink Pro recorder and the respiratory effort sensor must be fastened with the re-usable belt on the patient's chest. All relevant respiratory information during sleep will be collected via nasal cannula, pulse oximetry module and respiratory effort sensor. The disposable plastic nasal cannula is connected to the ApneaLink Pro recorder and fixed at the patient's nose. The oximetry sensor is connected to the Xpod and fixed at the patient's finger. The Xpod is connected to the ApneaLink Pro recorder. The respiratory effort sensor is connected to the ApneaLink Pro recorder and held in place by the belt. LED's indicate if the sensors are attached correctly. A Test complete light advises at the end of a recording if sufficient data for analysis was recorded during the night. After recording, the ApneaLink Pro recorder must be returned to the physician. With the ApneaLink Software installed on a personal computer the physician can generate a report with the recorded and analyzed data to aid in diagnosis. The recordings and the report can be sent via email to further clinical investigation.

The ApneaLink Pro is a ventilatory effort recorder intended to aid healthcare professionals in diagnosing sleep-disordered breathing in adult patients.

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

1. Table of Acceptance Criteria and Reported Device Performance

The provided document describes a "side-by-side testing of the detection of respiratory events and reported indices" to demonstrate substantial equivalence to the predicate device, ApneaLink Plus (K083575). The "acceptance criteria" appear to be that the ApneaLink Pro's performance for detecting and classifying respiratory events is substantially equivalent to that of the predicate device.

• Pulse/saturation detection
• Apnea/hypopnea according to classic definition
• Snoring detection
• Cheyne-Stokes breathing detection
• Hypopnea detection
• Apnea classification (obstructive, mixed, central)
• Central apnea determination according to threshold apnea/effort pause | Confirmed Substantially Equivalent to ApneaLink Plus (K083575): "side-by-side testing... used to demonstrate that the ApneaLink Pro is Substantially Equivalent to the ApneaLink Plus (K083575). In the side-by-side testing, the detection of all respiratory events is compared. The recorded, analyzed, displayed values and reported apnea classification... are compared to those of the ApneaLink Plus." |
  | Recorded, analyzed, displayed values | Substantially Equivalent to ApneaLink Plus (K083575) | Confirmed Substantially Equivalent to ApneaLink Plus (K083575): "The recorded, analyzed, displayed values... of Apneal.ink Pro are compared to those of the ApneaLink Plus." |
  | Reported apnea classification (obstructive/mixed/central) | Substantially Equivalent to ApneaLink Plus (K083575) | Confirmed Substantially Equivalent to ApneaLink Plus (K083575): "reported apnea classification of obstructive/mixed/central apneas of Apneal.ink Pro are compared to those of the ApneaLink Plus." |
  | Meeting predetermined acceptance criteria and relevant standards | All internal and external tests confirm compliance with predetermined acceptance criteria and requirements of relevant standards. (This is a broader statement, encompassing electrical safety, EMC, mechanical, and environmental tests, in addition to the clinical performance comparison). This implies numerical or qualitative thresholds for each specific test, though these are not detailed in the provided text. | Confirmed: "All internal and external tests confirmed that the product meets the predetermined acceptance criteria and the requirements of the relevant standards." |
  | Biocompatibility | No additional testing required as no changes from the predicate device in patient-contacting components. | Confirmed: "No additional biocompatibility testing was required as none of the components in contact with patients have changed from the predicate." |

2. Sample Size and Data Provenance for the Test Set

• Sample Size: The document does not explicitly state the sample size (number of patients or recordings) used for the side-by-side testing. It simply refers to "side-by-side testing... of the detection of all respiratory events."
• Data Provenance: The document does not specify the country of origin of the data or whether the study was retrospective or prospective.

3. Number of Experts and Qualifications for Ground Truth

• The document does not mention the number of experts used to establish ground truth or their specific qualifications. The study methodology described as "side-by-side testing" against a predicate device suggests that the predicate device's output itself served as a reference point for comparison, rather than an independent expert-established ground truth.

4. Adjudication Method for the Test Set

• The document does not describe any specific adjudication method (e.g., 2+1, 3+1, none). Given that the comparison is "side-by-side" against a predicate device, it's likely that the predicate's output was considered the de facto reference, and no separate human adjudication process is detailed for this comparison.

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

• No MRMC study described: The document does not describe a multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance. The study focuses on comparing the new device (ApneaLink Pro) to an existing device (ApneaLink Plus) in terms of its ability to detect and report physiological events. The ApneaLink Pro is a recording and analysis device, not an AI-assisted diagnostic tool for human readers in the context of improving their performance.

6. Standalone (Algorithm Only) Performance

• Standalone performance was the focus: The primary study described is a "side-by-side testing of the detection of respiratory events and reported indices" where the ApneaLink Pro's analytical software output is compared directly to the ApneaLink Plus's output. This is a form of standalone performance evaluation for the device's analytical capabilities, as it does not involve human interpretation of the raw data from the new device beyond what the predicate already provided. The device aids in diagnosis by producing a report; the reported performance is of the device's ability to generate this report.

7. Type of Ground Truth Used

• Predicate Device Output: The ground truth for this comparison study was effectively the performance and outputs ("recorded, analyzed, displayed values and reported apnea classification") of the legally marketed predicate device, ApneaLink Plus (K083575). The goal was to establish "substantial equivalence," not necessarily absolute accuracy against a gold standard like polysomnography or pathology, within the scope of this particular submission.

8. Sample Size for the Training Set

• The document does not mention a "training set" in the context of device development or performance evaluation. The ApneaLink Pro is described as a successor model with hardware and software changes, and the testing described is a comparison to a predicate, not a machine learning model requiring a training set.

9. How Ground Truth for the Training Set Was Established

• Since no training set is described for a machine learning algorithm, there is no information on how ground truth for a training set was established. The device's "technology" section implies updates to a microprocessor and software for data handling, not necessarily a learning algorithm.

Ask a specific question about this device

The device is intended to provide ventilation for non-dependent, spontaneously breathing adult and pediatric patients (30 lb / 13 kg and above) with respiratory insufficiency or respiratory failure, with or without obstructive sleep apnea. The device is for non-invasive use, or invasive use (with the use of the ResMed Leak Valve). Operation of the device includes both stationary, such as in hospital or home, or mobile, such as wheelchair usage.

The Stellar 150 is a pressure controlled ventilator using a single limb vented circuit, product code MNT, and is substantially equivalent to the already marketed Stellar 150 device (K113640). The device contains a microprocessor controlled blower that generates the required airway pressure. CPAP and Bi-level modes are implemented and the device is suitable for patients weighing above 30 lbs (13 kg) for CPAP and Bi-level modes. The device also includes a volume assured pressure support mode (iVAPS), indicated for patients above 66 lbs (30 kg).

This submission updates the Stellar 150 to include a new Remote Alarm (optional) accessory. The Remote Alarm generates an audible and visual signal when an alarm is triggered on the ventilator. For the connection of this new Remote Alarm, the Stellar 150 requires an additional connector on the back of the device as well as electronics and software support for this additional port. This new Remote Alarm triggers this 510[k].

This is a 510(k) premarket notification for a minor modification (addition of a remote alarm accessory) to an existing medical device, the Stellar 150 ventilator. The submission primarily relies on demonstrating substantial equivalence to predicate devices rather than conducting extensive new clinical studies to establish novel performance metrics. As a result, many of the requested elements for a study proving device acceptance criteria in a typical AI/diagnostic device context are not directly applicable or explicitly detailed in this document.

However, I can extract and infer information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

For the Stellar 150 ventilator itself, the acceptance criteria are implicitly that it performs as well as the prior cleared Stellar 150 (K113640) and meets applicable standards. For the new Remote Alarm accessory and its integration, the acceptance criteria are implicitly that it performs as well as the predicate Respironics Trilogy series Remote Alarm (K111610) and functions correctly with the Stellar 150. Specific numerical performance metrics (e.g., sensitivity, specificity, accuracy) are not presented as this is not a diagnostic device and the submission focuses on safety and performance equivalence.

• "Design and system verification testing in regards to mechanical and environmental testing according to IEC 60601-1-11:2010, electrical safety testing according to IEC 60601-1:2005, EMC testing according to IEC 60601-1-2:200, etc. was performed."
• "A regression analysis identified the features which were changed and which test cases needed to be repeated. End-to-end testing on the appropriate test cases has been performed."
• "The tests as well as the existing data from the K113640 submission, demonstrate that the Stellar 150 meets the predetermined acceptance criteria and is substantially equivalent to the predicate device (K113640)." |
  | Remote Alarm | Perform comparably to the Respironics Trilogy series Remote Alarm (K111610).
  Interoperate safely and effectively with the Stellar 150. | - "The Remote Alarm was compared to the Respironics Trilogy series Remote Alarm (K111610). The result of this comparison is that the Remote Alarm is substantially equivalent to the Trilogy Remote Alarm (K111610)."
• "The compatibility of Stellar 150 with the Remote Alarm was tested and confirmed."
• "In addition verification testing for the Remote Alarm was performed and demonstrated that it met the predetermined acceptance criteria." |

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

The document does not specify a "sample size" in terms of patient data for a test set. This submission relies on engineering verification and validation testing (e.g., mechanical, electrical safety, EMC, software regression testing) rather than a clinical study with patient data. Therefore, the concept of data provenance (country of origin, retrospective/prospective) related to patient data is not applicable here.

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

Not applicable. Ground truth in the context of this submission would refer to the expected performance of the device under various engineering tests, which is established by engineering specifications, regulatory standards (like IEC 60601-1), and comparison to predicate device performance, not by expert consensus on clinical cases.

4. Adjudication Method for the Test Set

Not applicable. There is no mention of a human adjudication process for interpreting test results. Device performance is determined by meeting pre-defined engineering and regulatory standards during verification and validation testing.

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

Not applicable. This is not an AI-assisted diagnostic or imaging device, and no MRMC study was performed.

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

The Stellar 150 is a medical device, not an algorithm in the AI sense. Performance testing was done on the device (and its new accessory) as a standalone system to ensure it met its specifications and regulatory standards. The "standalone" performance here refers to the device itself operating as intended, independent of direct interaction during the test, but it's not "algorithm-only" performance as one might see in AI/ML submissions.

7. The Type of Ground Truth Used

The "ground truth" for this type of submission is established through:

• Engineering specifications and design requirements: Derived from the predicate device and relevant standards.
• Regulatory standards: Such as IEC 60601-1, IEC 60601-1-2, IEC 60601-1-11.
• Performance of the predicate devices: The Stellar 150 (K113640) for the main device and the Respironics Trilogy series Remote Alarm (K111610) for the new accessory.
• Functional tests: Ensuring the device and accessory perform their intended functions (e.g., alarm triggers correctly, connectivity works).

There is no mention of pathology, expert consensus on clinical cases, or outcomes data as the primary ground truth for this technical verification and validation.

8. The Sample Size for the Training Set

Not applicable. This is not a machine learning or AI device that requires a "training set."

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

Not applicable, as no training set was used.

Ask a specific question about this device

The device is intended to provide ventilation for non-dependent, spontaneously breathing adult and pediatric patients (30 lb / 13 kg and above) with respiratory insufficiency or respiratory failure, with or without obstructive sleep apnea. The device is for non-invasive use, or invasive use (with the use of the ResMed Leak Valve). Operation of the device includes both stationary, such as in hospital or home, or mobile, such as wheelchair usage.

The Stellar 150 is a pressure controlled ventilator using a single limb vented circuit, product code MNT and is substantially equivalent to the already marketed Stellar 150 device (K103167). For both devices as they are substantial equivalent, it is essential that a microprocessor controlled blower generates the required airway pressure. CPAP and Bi-level modes are implemented. With ongoing technological progress, the device is further suitable to include a population above 30 lbs (13 kg) for CPAP and Bilevel modes. The device also includes a volume assured pressure support mode (iVAPS), indicated for patients above 66 lbs (30 kg). The Stellar 150 in combination with the new developed ResMed Leak Valve supports the invasive use therapy. The ResMed Leak Valve incorporates a leak port as well as an integrated anti-asphyxia valve.

The provided document describes a 510(k) submission for the ResMed Stellar 150 ventilator, focusing on a change in the indication for use to include invasive therapy with a new ResMed Leak Valve. The submission asserts substantial equivalence to a previously cleared device (K103167).

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

1. Table of Acceptance Criteria and Reported Device Performance

• ISO 5356-1 Anaesthetic and respiratory equipment Conical connectors Part 1: Cones and sockets
• ASTM F 1246-91 Specification for Electrically Powered Home Care Ventilators, Part 1 - Positive-Pressure Ventilators and Ventilator Circuits |
  | System Verification (Stellar 150 + Leak Valve): | "System verification testing was performed as well as bench testing. The side-by-side testing demonstrated that there is no significant difference in delivering invasive therapy using the new ResMed Leak Valve (leak port with integrated anti-asphyxia valve) and therefore the Stellar 150 is Substantially Equivalent to the predicate device."
  "Performance and side-by-side testing demonstrated that there is no significant difference in [safety and effectiveness] between the ResMed Leak Valve and the new ResMed Leak Valve (leak port with integrated anti-asphyxia valve)." (likely a typo, intended to compare the new system to the predicate or non-invasive system) |

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

• Sample Size: Not explicitly stated. The document mentions "performance testing," "system verification testing," and "bench testing," but does not provide specific numbers of units tested, test runs, or patient data (as this appears to be a device performance and safety study, not a clinical trial with patient data).
• Data Provenance: Not explicitly stated. Given it's a submission for regulatory clearance of a medical device, the studies are typically conducted by the manufacturer (ResMed) in a controlled environment. The nature of the tests (bench and system verification) suggests laboratory-based testing rather than patient data from a specific country. This is retrospective in the sense that it relies on previously established performance for the core device and new testing for the new component.

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

• The document does not describe a ground truth established by human experts for a test set in the context of diagnostic accuracy. This submission is for a ventilator, and the performance criteria are based on engineering standards (ISO, ASTM) and functional comparisons, not expert interpretation of diagnostic output.

4. Adjudication Method for the Test Set

• Not applicable as there is no "test set" requiring expert adjudication in the context of diagnostic accuracy. The performance is assessed against engineering standards and functional equivalence.

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

• No, an MRMC comparative effectiveness study was not done. This is a regulatory submission for a continuous ventilator, not an AI-powered diagnostic tool. The concept of "human readers" and "AI assistance" is not relevant to this device.

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

• This is not an algorithm-only device. The device itself (ventilator) operates as a standalone unit in delivering therapy. The performance tests described (ISO, ASTM, bench testing) are standalone in the sense that they evaluate the device's functional attributes, not human interaction with an algorithm's output.

7. The Type of Ground Truth Used

• The "ground truth" for the performance evaluation of the new ResMed Leak Valve and the combined system is based on:
  • Engineering Standards: Compliance with ISO 5356-1 and ASTM F 1246-91.
  • Functional Equivalence: Demonstrated "no significant difference" in delivering invasive therapy when compared side-by-side to the predicate device/system.
  • Predetermined Acceptance Criteria: The core Stellar 150 device already met these from its prior clearance (K103167).

8. The Sample Size for the Training Set

• Not applicable. This is not an AI/machine learning device that requires a training set.

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

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

Ask a specific question about this device

The Stellar 150 is intended to provide ventilation for non-dependent, spontaneously breathing adult and pediatric patients (30 lb / 13kg and above) with respiratory insufficiency or respiratory failure, with or without obstructive sleep apnea. The device is for non-invasive use, or invasive use with an uncuffed or deflated tracheostomy. Operation of the device includes both stationary, such as in hospital or home, or mobile, such as wheelchair usage.

The Stellar 150 is a pressure controlled ventilator using a single limb vented circuit, product code MNT. A microprocessor controlled blower generates the required airway pressure between 3-40 cm H2O. Comparing to previous ResMed devices, CPAP and Bi-level modes are implemented as in VPAP III ST-A / Kidsta mask system, which is indicated for patients above 40 lb (18 kg). With ongoing technological progress, the new device is further suitable to include a population above 30 lb (13 kg) for CPAP and Bilevel modes, which is comparable to Draeger Carina Home. The new device also includes a volume assured pressure support mode, indicated for patients above 66 lb (30 kg), which is substantially equivalent to Breas Vivo 40.

Here's a breakdown of the acceptance criteria and the study information for the Stellar 150 device, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document does not explicitly present a table of specific numerical acceptance criteria with corresponding performance data for the Stellar 150. Instead, it states that "All tests confirmed the predetermined acceptance criteria." The performance is described in terms of compliance with established standards and substantial equivalence to predicate devices.

• Complies with IEC 60601-1:1988 (and its amendments) and IEC 60601-1-2:2007.
• Complies with ISO 10651-6:2004.
• Complies with FDA guidance documents: "Draft Reviewer Guidance for Ventilators (July 1995)" and "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices (May 11, 2005)". |
  | Risk Analysis Outcomes | - Design and Verification activities performed as a result of risk analysis.
• All tests confirmed predetermined acceptance criteria (implying risks were mitigated and performance met safety thresholds). |
  | Pressure Performance | - Performance testing comprises pressure performance.
• Microprocessor controlled blower generates required airway pressure between 3-40 cm H2O. |
  | Trigger and Cycling | - Performance testing comprises trigger and cycling. |
  | Volume Assured Pressure Support Ventilation | - Performance testing comprises volume assured pressure support ventilation. |
  | Substantial Equivalence | - Side-by-side testing demonstrated substantial equivalence to predicate devices (BREAS VIVO 40 SYSTEM, ResMed VPAP III ST-A/KIDSTA MASK SYSTEM, Draeger Carina Home) in terms of:
  • Same intended use
  • Same operating principle
  • Similar technologies
  • Same manufacturing process |
    | Indication Expansion (CPAP/Bi-level) | - New device further suitable for patients above 30 lb (13 kg) for CPAP and Bi-level modes, comparable to Draeger Carina Home. |
    | Indication (Volume Assured Pressure Support) | - New device includes a volume assured pressure support mode for patients above 66 lb (30 kg), substantially equivalent to Breas Vivo 40. |

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

The document does not specify a "test set" in the context of clinical data or a specific cohort of patients for testing. The performance data described refers to engineering verification and validation activities conducted on the device itself.

• Sample Size: Not applicable/not specified for a clinical test set. The testing refers to device units.
• Data Provenance: Not applicable/not specified in terms of patient data. The provenance is from internal design, verification, and validation activities.

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

This information is not provided in the document. The study described is not a clinical study involving expert ground truth for patient outcomes.

4. Adjudication Method for the Test Set

This information is not provided in the document, as it does not describe a clinical study requiring adjudication of patient cases.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Its Effect Size

No MRMC comparative effectiveness study is mentioned in the document. The study described focuses on technical performance and substantial equivalence to predicate devices, not on human reader performance with or without AI assistance.

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

The device itself is a continuous ventilator, not explicitly an "algorithm" in the sense of an AI diagnostic tool. The performance described is inherent to the device's operation. Therefore, a standalone algorithm performance study is not directly applicable or described. The performance data reflects the device operating as intended without human intervention in its core functions (like pressure generation, trigger, and cycling).

7. The Type of Ground Truth Used

The "ground truth" for this device's performance is established through:

• Engineering Specifications and Design Requirements: The device was designed and tested against predetermined acceptance criteria derived from risk analysis and product design requirements.
• International Standards (ISO, IEC): Compliance with these standards serves as a benchmark for safety and performance.
• FDA Guidance Documents: Adherence to FDA guidelines is a form of regulatory "ground truth" for manufacturing and submission.
• Predicate Device Performance: Substantial equivalence claims are based on comparing the Stellar 150's performance and characteristics to those of legally marketed predicate devices.

8. The Sample Size for the Training Set

This information is not applicable. The Stellar 150 is a hardware-based medical device with microprocessor control, not an AI/ML algorithm that requires a "training set" of data in the typical sense. Its control logic and parameters are developed through engineering design and testing, not statistical learning from a large dataset.

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

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

Ask a specific question about this device

The ApneaLink™ Plus device is indicated for use by Health Care Professionals (HCP), where it may aid in the diagnosis of sleep disordered breathing for adult patients. Apneal ink Plus recred the following data: patient respiratory nasal airflow, snoring, blood oxygen saturation, pulse and respiratory effort during sleep. The device uses these recordings to produce a report for the HCP that may aid in the diagnosis of sleep disordered breathing or for further clinical investigation.

The performance and functional characteristics of ApneaLink Plus includes all the user-friendly features of the predicate devices. The ApneaLink Plus is a further development of the previously submitted device Apneal.ink (K070263). This submission addresses the expanded Indications for Use of Apnealink by including AASM criteria for detecting hypopneas and a respiratory effort sensor to differentiate between central, obstructive and mixed apneas.

The ApneaLink Plus recorder is a 3-channel battery-powered respiratory pressure sensor and oximetry system. ApneaLink Plus provides recordings of respiratory pressure, respiratory effort, pulse rate and oxvaen saturation during sleep. The phvsician prescribed device will help to recognize sleep-related respiratory disorders and lead to comprehensive clinical diagnosis and therapy. The patient may perform the recording at home by himself. The ApneaLink Plus recorder and the respiratory effort sensor must be fastened with the re-usable belt on the patient's chest. All relevant respiratory information during sleep will be collected via nasal cannula, pulse oximetry module and respiratory effort sensor. The disposable plastic nasal cannula is connected to the ApneaLink Plus recorder and fixed at the patient's nose. The oximetry sensor is connected to the XPOD and fixed at the patient's finger. The XPOD is connected to the ApneaLink Plus recorder. The respiratory effort sensor is connected to the ApneaLink Plus recorder and held in place by the belt. After recording, the ApneaLink Plus recorder must be returned to the physician. With the ApneaLink Plus Software installed on a personnel computer the physician can generate a report with the recorded and analyzed data to aid in the diagnosis of sleep disordered breathing. The recordings and the report can be sent via email to further clinical investigation.

The provided 510(k) summary for KOS-3575 (ApneaLink Plus) does not contain a detailed study with acceptance criteria and reported device performance in the format requested. The document primarily focuses on demonstrating substantial equivalence to predicate devices and expanding the indications for use.

While it states "All tests confirmed the predetermined acceptance criteria," it does not provide the specific criteria or the results of these tests. It also lacks information regarding the sample size, data provenance, ground truth establishment for test and training sets, expert qualifications, adjudication methods, or MRMC studies.

Therefore, many of the requested fields cannot be filled directly from the provided text.

Here is a summary of what can be extracted and what is missing:

1. Table of acceptance criteria and the reported device performance

• Missing: The document states "All tests confirmed the predetermined acceptance criteria," but does not list these criteria or the specific performance metrics achieved.

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

• Missing: No information regarding the sample size or provenance of data used for testing is provided.

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: No information on experts or ground truth establishment for a test set is provided.

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

• Missing: No information on adjudication methods is provided.

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

• Missing: There is no mention of an MRMC comparative effectiveness study. The device is intended to "aid in the diagnosis," implying it produces a report for a healthcare professional, but there's no study on human reader improvement with the device.

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

• Missing: While the device analyzes data and produces a report, the document does not present a standalone performance study in terms of diagnostic accuracy against a ground truth. Its role is described as aiding diagnosis by a healthcare professional.

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

• Missing: No information regarding the type of ground truth used for any testing is provided.

8. The sample size for the training set

• Missing: No information regarding a training set sample size is provided. The document describes the device's functionality rather than a machine learning model's training.

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

• Missing: No information regarding ground truth establishment for a training set is provided.

Information that is available (from the prompt, not directly in the requested format):

• Device: ApneaLink Plus
• Intended Use: To aid in the diagnosis of sleep-disordered breathing for adult patients by recording respiratory nasal airflow, snoring, blood oxygen saturation, pulse, and respiratory effort during sleep, and producing a report for healthcare professionals.
• Expanded Indications: The submission addresses expanded indications by including AASM criteria for detecting hypopneas and a respiratory effort sensor to differentiate between central, obstructive, and mixed apneas.
• Predicate Devices: ApneaLink (K070263) and Respironics Stardust II (K021845).
• Compliance: The device complies with various standards and regulations (e.g., FDA Guidance, IEC, ISO).

Ask a specific question about this device

ApneaLink records patient respiratory nasal pressure and blood oxygen saturation during sleep. The device is intended for use as a screening device to determine the need for further clinical diagnosis based on the patient's test score. ApneaLink reports apneas, hypopneas, flow limitation, snoring, SpO2 and the probability of Cheyne-Stokes respiration breathing patterns within the recording.

The performance and functional characteristics of the ApneaLink includes all the user-friendly features of the predicate device. The ApneaLink is a further development of the previous submitted device ApneaLink (K061405). This submission addresses the expanded indications for use of the Apneal.ink by analyzing the flow signal for periods of Cheyne-Stokes respiration breathing patterns.

The ApneaLink recorder is a two-channel battery-powered respiratory pressure sensor and oximetry system and provides recordings of respiratory flow, pulse rate and oxygen saturation during sleep. The physician prescribed device will help to recognize sleep-related respiratory disorders and lead to comprehensive clinical diagnosis and therapy. The patient may perform the recording at home by himself. The ApneaLink recorder must be fastened with the re-usable belt on the patient's chest. All relevant respiratory information during sleep will be collected via nasal cannula and pulse oximetry module. The disposable plastic nasal cannula is connected to the ApneaLink recorder and fixed at the patient's nose. The oximetry sensor is connected to the XPOD and fixed at the patient's finger. The XPOD is connected to the ApneaLink recorder, After recording, the Apneal.ink recorder is returned to the physician. With the Apneal.ink Software installed on a personnel computer the physician has the possibility to generate a report with the recorded and analyzed data. For further clinical diagnosis the physician has the possibility to send the recording and the report via email to the sleep laboratory/hospital.

The provided text is a 510(k) Premarket Notification for the ApneaLink device, primarily focused on establishing substantial equivalence to a predicate device for an expanded indication (analysis of Cheyne-Stokes respiration breathing patterns). It does not contain detailed information about specific acceptance criteria, performance studies, or ground truth establishment in the way typically expected for a dedicated performance study report.

Here's a breakdown of the available information based on your request, highlighting what is present and what is missing:

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

This information is not explicitly provided in the given text.
The document states: "Design and Verification activities were performed on the ApneaLink as a result of the risk analysis and product requirements. All tests confirmed the product met the predetermined acceptance criteria." However, it does not list these criteria or the specific performance metrics achieved.

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

This information is not provided in the given text.

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 in the given text.

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

This information is not provided in the given text.

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

This information is not provided in the given text. The document refers to the device as a "screening device to determine the need for further clinical diagnosis" and generating a report for a physician to use for "further clinical diagnosis," suggesting a human-in-the-loop scenario, but no MRMC study or effectiveness data is presented. This is an algorithm-only device (standalone) that reports data to a physician.

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

Yes, based on the description, the ApneaLink operates as a standalone device that records and analyzes data to generate a report. The text states:

• "ApneaLink reports apneas, hypopneas, flow limitation, snoring, SpO2 and the probability of Cheyne-Stokes respiration breathing patterns within the recording."
• "With the ApneaLink Software installed on a personnel computer the physician has the possibility to generate a report with the recorded and analyzed data."

This implies the algorithm performs the analysis autonomously to produce the report. However, no specific standalone performance metrics (e.g., sensitivity, specificity against a reference standard) are provided in this document.

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

This information is not provided in the given text.

8. The sample size for the training set

This information is not provided in the given text.

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

This information is not provided in the given text.

Ask a specific question about this device

ApneaLink records patient respiratory nasal pressure and blood oxygen saturation during sleep. The device is intended for use as a screening device to determine the need for clinical diagnosis and evaluation by polysomnography based on the patient's test score.

The ApneaLink recorder is a two-channels battery-powered respiratory pressure sensor and oximetry system and provides recordings of respiratory pressure, pulse rate and oxygen saturation during sleep. The physician prescribed device will help to recognize sleep-related respiratory disorders and lead to comprehensive clinical diagnosis and therapy. The patient may perform the recording at home by himself. The ApneaLink recorder must be fastened with the re-usable belt on the patient's chest. All relevant respiratory information during sleep will be collected via nasal cannula and pulse oximetry module. The disposable plastic nasal cannula is connected to the ApneaLink recorder and fixed at the patient's nose. The oximetry sensor is connected to the XPOD and fixed at the patient's finger. The XPOD again is connected to the ApneaLink recorder. After recording, the ApneaLink recorder must be returned to the physician. With the ApneaLink Software installed on a personnel computer the physician has the possibility to generate a report with the recorded and analyzed data.

Acceptance Criteria and Study Details for ApneaLink (K061405)

The provided document (K061405) for the ApneaLink device is a 510(k) Premarket Notification. This type of submission focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than presenting detailed clinical study data to prove the device meets specific acceptance criteria in the way a de novo or PMA submission might.

The document states: "Design and Verification activities were performed on the ApneaLink as a result of the risk analysis and product requirements. All tests confirmed the product met the predetermined acceptance criteria." However, it does not explicitly list the specific acceptance criteria or provide the detailed results of these tests that would typically be presented in a clinical performance study.

Given the context of a 510(k) for a "Ventilatory Effort Recorder" and its intended use as a screening device for sleep apnea, the "acceptance criteria" would likely relate to the device's ability to accurately record respiratory nasal pressure and blood oxygen saturation, and to provide a "test score" that can be used to determine the need for clinical diagnosis. The substantial equivalence argument relies on the device being similar in intended use, operating principle, and technology to the predicate devices (microMESAM Basic-Set K040576 and Compass M10 System K041724).

Therefore, based solely on the provided text, a table of acceptance criteria and reported performance cannot be fully constructed with quantitative measures as they are not detailed in this public summary. The document focuses on regulatory compliance and substantial equivalence rather than a clinical performance study with specific metrics.

Here's an attempt to answer the questions based on the available information, noting where information is not provided:

1. Table of Acceptance Criteria and Reported Device Performance

As noted above, the specific quantitative acceptance criteria and their corresponding reported performance are not explicitly detailed in the provided 510(k) summary. The document broadly states that "All tests confirmed the product met the predetermined acceptance criteria." These criteria would likely be related to the accuracy and reliability of measuring respiratory nasal pressure and blood oxygen saturation for screening purposes, consistent with predicate devices.

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

The document does not specify a sample size for a clinical "test set" or its data provenance (country of origin, retrospective/prospective). The submission describes "Design and Verification activities" and "All tests," which typically refer to internal engineering and functional testing, rather than a clinical performance study with human subjects.

3. Number of Experts and Qualifications for Ground Truth

The document does not mention the use of experts to establish ground truth for a test set in the context of a clinical performance study. For a 510(k), ground truth for performance claims is often established through comparison to a well-accepted and legally marketed predicate device, or by relying on existing scientific literature for the underlying technology.

4. Adjudication Method

As no clinical test set requiring expert ground truth is described, an adjudication method for such a set is not mentioned.

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

There is no mention of an MRMC comparative effectiveness study in the provided document. The submission focuses on substantial equivalence of the device itself (hardware and basic functionality) as a screening tool, not on the impact of AI assistance on human readers.

6. Standalone Performance Study (Algorithm Only)

The provided text does not describe a standalone algorithm-only performance study. While the device does generate a "test score" based on recorded data, the details of how this score is derived and its standalone diagnostic performance are not elaborated. The submission is for a "Ventilatory Effort Recorder" used as a "screening device to determine the need for clinical diagnosis and evaluation by polysomnography," implying the output is for physician interpretation, not a definitive diagnosis by the device itself.

7. Type of Ground Truth Used

The type of "ground truth" for the device's main function (recording respiratory nasal pressure and blood oxygen saturation) would typically be established by comparison to reference gold standard sensors or established polysomnography (PSG) equipment during the device development and verification stages. However, this specific detail is not provided in the 510(k) summary. Given the device's intention to screen for the need for PSG, PSG itself would be the ultimate clinical ground truth for sleep apnea diagnosis.

8. Sample Size for the Training Set

The document does not specify a sample size for a "training set." The ApneaLink is a device that records physiological signals; it is not explicitly described as employing a machine learning algorithm that requires a dedicated training set in the context of this 510(k) summary. The "test score" it generates is likely based on pre-defined algorithms rather than a trained AI model.

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

Since no explicit "training set" or AI/ML algorithm requiring one is described in the provided summary, the method for establishing its ground truth is not applicable/not provided.

Ask a specific question about this device