Search Results

The Bleep™ DreamPort nasal adhesive mask is intended to provide an interface from a Continuous Positive Airway Pressure (CPAP) or bi-level system. The mask to be used by adult patients (>66 lbs. / 30 kg, for whom positive airway pressure has been prescribed. The mask is for single-patient reuse in the home, hospital/institutional environment.

The Bleep™ DreamPort nasal adhesive mask is similar to standard nasal pillow CPAP mask for use with patients using CPAP and bi-level equipment for the treat of OSA. The Bleep™ DreamPort nasal adhesive mask is comprised of 2 sub-assemblies: Nasal Port assembly and Airflow management assembly. The device uses single use foam tape to create the seal at the nostrils. This allows the interface to be used without head gear. There is a reusable interface which connects the nasal adhesive to the circuit of the CPAP equipment. It includes integrated exhalation ports.

The provided text describes the Bleep™ DreamPort nasal adhesive mask and its acceptance criteria for FDA clearance, comparing it to a predicate device (Resmed Swift LT). The study primarily focuses on non-clinical performance testing and a limited user study to demonstrate substantial equivalence, rather than a typical multi-reader multi-case (MRMC) or standalone AI performance study. Therefore, some of the requested information, particularly regarding AI-specific criteria, human reader improvement, and extensive expert ground truth establishment, is not applicable to this device's clearance process as described.

Here's an analysis based on the provided document:

Acceptance Criteria and Reported Device Performance

The acceptance criteria are generally framed around demonstrating substantial equivalence to the predicate device (Resmed Swift LT, K073638) and compliance with international standards like ISO 17510-2:2015 and ISO 10993-1.

Study Information:

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

   • User study (Clinical Testing): The document states a "user study was performed," but does not explicitly mention the sample size (number of participants/patients).
   • Non-clinical performance testing (Bench Tests): This refers to the physical device being tested against standards (e.g., CO2 washout, exhaust flow). No "test set" in the sense of patient data is applicable here; tests are performed on the device itself.
   • Data Provenance: Not explicitly stated for the user study (e.g., country of origin, specific clinics). The user study was conducted over "2 nights" for each participant. It's implicitly prospective as it's a "user study" where performance was compared.

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

   • User Study (Clinical Testing): The document does not specify the number or qualifications of experts involved in establishing ground truth (e.g., reading sleep study data). It mentions "mean AHI during use" was compared, implying that existing clinical methods for AHI calculation would be the "ground truth." This is not an AI-specific ground truth establishment (like image annotation by multiple radiologists).
   • Non-clinical performance testing: Ground truth here are the engineering standards and measurements, not expert consensus.

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

   • User Study (Clinical Testing): The document does not specify any adjudication method for the clinical/user study results (e.g., for AHI measurements or leak rates). The comparison was seemingly direct or averaged.
   • Non-clinical performance testing: Not applicable.

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 done. This device is a medical accessory (mask) and not an AI-powered diagnostic tool, so such a study is not relevant to its clearance.

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

   • No, not applicable. This is a physical medical device, not an algorithm. Bench testing is the "standalone" performance for the device itself.

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

   • User Study: The "ground truth" for the user study appears to be clinical measurements such as leak rates and AHI, which are standard metrics in sleep apnea therapy. This would typically be derived from objective CPAP machine data and sleep study results, often interpreted by sleep physicians. It is not described as involving extensive expert consensus or pathology data.
   • Non-clinical performance testing: The ground truth is engineering measurements against established ISO standards.

7. The sample size for the training set:

   • Not applicable. This device is not an AI/machine learning product and therefore does not have a "training set" in that sense. It's a manufactured product whose performance is demonstrated through physical and limited user testing.

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

   • Not applicable. See point 7.

Ask a specific question about this device