Search Results

The VPAP Tx is indicated for the treatment and titration of patients weighing more than 66 Ib (> 30 kg) with obstructive sleep apnea (OSA), respiratory insufficiency, central or mixed apneas, or periodic breathing,

The VPAP Tx is intended to be used in a clinical environment.

The modified VPAP Tx device has a similar operating principle, and the same technology and manufacturing process as the VPAP Tx (K092186). The hardware (electromechanical operation and materials) also remain unchanged from the predicate VPAP Tx (K092186). The therapy modes contained in the predicate VPAP Tx (K092186) provides CPAP, Auto-titrating, Bilevel, VAuto and ASV modes to treat OSA and/or respiratory insufficiency, central or mixed apneas or periodic breathing in patients weighing more than 66 lb. The device contains a micro-processor controlled blower system that generates as required to maintain an "air splint" for effective treatment of OSA and/or respiratory insufficiency, central or mixed apneas or periodic breathing.

The change to the modified VPAP Tx device includes the addition of the ASVAuto therapy mode. The modified VPAP Tx system comprises the flow generator, patient tubing, mask (patient interface) and optional HumidAire 2i humidifier.

The performance and functional characteristics of the modified VPAP Tx includes all the clinician and user friendly features of the predicate device VPAP Tx (K092186).

Here's an analysis of the provided text regarding the VPAP Tx device, focusing on acceptance criteria and study details.

It's important to note that the provided text describes a 510(k) premarket notification for a medical device. This process aims to demonstrate substantial equivalence to a legally marketed predicate device, rather than to establish new safety and effectiveness through extensive, de novo clinical trials with predefined acceptance criteria for the new device's performance against a specific disease outcome. The "acceptance criteria" here refer more to meeting design specifications and demonstrating non-inferiority to the predicate device in terms of performance.

Acceptance Criteria and Reported Device Performance

Study Details:

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

   • Test Set Sample Size (Clinical Trial): 21 subjects.
   • Data Provenance: Not explicitly stated, but it's a clinical trial comparing the enhanced device to a predicate, conducted by ResMed. It can be inferred as prospective, as it "documented the outcome" of the new feature. The country of origin is not specified, but ResMed Ltd is in Australia and ResMed Corp in the USA.

2. 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 document does not specify the number or qualifications of experts used to establish a "ground truth" for the clinical trial test set. The clinical trial focused on comparing the suppression of respiratory events between two ASV treatments, rather than evaluating an algorithm's performance against a manually adjudicated ground truth in a diagnostic context. The assessment of "respiratory events" would likely rely on standard polysomnography scoring, which itself involves trained technologists and/or physicians, but these details are not provided here.

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

   • Not specified. The clinical trial compared the outcomes of two different therapy modes (Enhanced ASV vs. Predicate ASV). The evaluation of respiratory events would typically follow established sleep study scoring guidelines, but the specific adjudication method for event scoring is not detailed.

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 involving human readers/interpreters with and without AI assistance was not performed. This study directly compared the performance of an "Enhanced ASV" algorithm (a software change) to a "predicate ASV" treatment in suppressing respiratory events in patients. It's a comparison of device performance, not an assessment of human reader improvement with AI.

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

   • Yes, the clinical trial essentially evaluated the "Enhanced ASV" algorithm as a standalone component within the device, comparing its therapeutic effect to the predicate ASV. The "Enhanced ASV" is described as a software change (ASVAuto algorithm), and its performance was directly assessed in suppressing respiratory events. The overall device operation (including the software) is independent once initiated.
   • The non-clinical bench testing also directly evaluated the ASVAuto algorithm alone ("ResMed conducted extensive bench testing using both closed-loop and open-loop test scripts from patient models designed to verify that the ASVAuto algorithm in the VPAP Tx performs to specification.").

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

   • The term "ground truth" isn't directly applicable in the same way as it might be for a diagnostic AI device. In this context, the "ground truth" for evaluating the clinical effectiveness of ASV treatments would be the quantification of respiratory events (e.g., apneas, hypopneas, periodic breathing occurrences) as measured by standard clinical methods (presumably polysomnography or similar monitoring) in patients receiving treatment. The study's objective was to demonstrate non-inferiority in suppressing these events.

7. The sample size for the training set:

   • Not applicable / Not provided. This document describes a 510(k) submission for a device featuring an "ASVAuto algorithm" (a software change). It does not provide details about the development or training of this algorithm, including any potential "training set" of data that might have been used to develop the algorithm itself prior to verification and clinical testing. The focus is on the verification of the enhanced algorithm's performance.

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

   • Not applicable / Not provided. As mentioned above, details about the algorithm's development/training, and therefore the establishment of ground truth for any training data, are not included in this regulatory summary.

Ask a specific question about this device

The S9 VPAP ST is indicated for the treatment of Obstructive Sleep Apnea.(OSA).in.patients.weighing. . more than 66 lb (30 kg). The S9 VPAP ST is intended for use in the hospital and home.

S9 VPAP ST System (S9 VPAP ST with H5i) is similar to the predicate device(s), using a blower based positive pressure system with an integrated heated humidifier and heater controller. The device platform, both hardware and firmware come from the S8 Aspen with H4i Plus (K091947) and contains a micro-processor controlled blower system that generates controlled positive airway pressure between 3-25 cmH2O as required to maintain an "air splint" for effective treatment of OSA. The system comprises the flow generator, patient tubing, mask (patient interface) and humidifier. The S9 VPAP ST contains treatment modes that come from earlier versions of ResMed Bilevel devices, these modes are known as Spontaneous (S Mode), Timed (T Mode), Spontaneous/Timed (S/T Mode) and VAuto Mode. Therapy modes come from the VPAP Tx system (K092186), VPAP ST (K080131) for S, S/T, T and VAuto and CPAP Mode comes from the S8 Aspen (K091947).

This document is a 510(k) summary for the ResMed S9 VPAP ST, a non-continuous ventilator intended for the treatment of Obstructive Sleep Apnea (OSA). It outlines the device's substantial equivalence to predicate devices and the non-clinical testing performed.

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

1. Table of Acceptance Criteria and Reported Device Performance

The provided document doesn't explicitly state quantitative acceptance criteria in a table format with specific performance metrics and their corresponding values for each test. Instead, it broadly states that "All bench tests confirmed the predetermined acceptance criteria." The performance is generally reported as meeting these criteria through various tests against predicate devices.

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

The document indicates that clinical data for the S9 VPAP ST is not required. Therefore, there is no human patient test set as the device's safety and effectiveness were established through comparison to predicate devices and bench testing.

• Sample Size: Not applicable for a human test set. Bench tests were performed on the device itself.
• Data Provenance: Not applicable for patient data. The tests were non-clinical (bench testing) and likely performed internally by ResMed.

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

As no clinical data was required and testing was done non-clinically, there was no expert adjudication process to establish ground truth for a patient test set. The "ground truth" for the non-clinical tests would have been the specifications and performance characteristics of the predicate devices and relevant engineering standards.

4. Adjudication Method for the Test Set

Not applicable, as there was no patient test set requiring expert adjudication.

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 data for the S9 VPAP ST is not required as the predicate devices have been subjected to clinical trial requirements or validated patient simulation models have been used during the bench testing phases."

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

The S9 VPAP ST is a physical medical device (a ventilator), not a software algorithm providing diagnostic or treatment recommendations. Therefore, the concept of "standalone performance" in the context of an algorithm's without-human-in-the-loop performance is not directly applicable. The device itself performs its intended function (delivering positive airway pressure). Its performance was evaluated through non-clinical bench testing.

7. The Type of Ground Truth Used

For the non-clinical testing, the "ground truth" was based on:

• The performance specifications and established safety/effectiveness of the predicate devices.
• Engineering parameters and requirements defined by international standards (IEC, ISO) and internal design requirements.
• Validated patient simulation models used during bench testing.

8. The Sample Size for the Training Set

The device is a hardware-based medical device with integrated software, not a machine learning algorithm that undergoes a "training phase" with a distinct "training set" of data in the typical AI/ML sense. Therefore, no specific sample size for a training set is applicable or mentioned. Its design and functionality are based on established engineering principles and prior device iterations, not statistical learning from a dataset.

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

As there is no "training set" in the context of machine learning, this question is not applicable. The device's functionality and "knowledge" are engineered into its design, operating principles, and firmware, validated against industry standards and predicate device performance.

Ask a specific question about this device