Search Results

DROWZLE is indicated to record a patient's respiratory pattern during sleep for the purpose of prescreening patients for obstructive sleep apnea (OSA) syndrome. The device is designed for use in home-screening of adults with suspected possible sleep breathing disorders. Results are used to assist the healthcare professional in determining the need for further diagnosis and evaluation. The system is not intended as a substitute for full polysomnography when additional parameters such as sleep stages, limb movements, or EEG activity are required.

DROWZLE is a mobile software used to collect symptom data for sleep apnea risk, including severity of daytime sleepiness and personal chronic disease risk factors. DROWZLE also records sleep breathing patterns and sends the sound files to secure servers in the cloud. DROWZLE then analyzes and interprets the sleep breathing results, along with the profile data provided by the individual, to measure and track sleep-related health risks over time.

DROWZLE is a stand-alone software medical device. It operates on a mobile computing device with an Apple iPhone 7, iPhone 8 or iPhone X using iOS v10.0 or later. Breathing sounds during sleep are recorded using the microphone within the mobile device. The sound file is uploaded to a cloud server for analysis using the results of standard questionnaires and a proprietary algorithm. A report is generated and provided to the individual and/or their healthcare provider. Reports are provided within the mobile application and/or via email.

Here's a breakdown of the acceptance criteria and the study proving the Drowzle sleep apnea prescreening device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document primarily focuses on the clinical performance against Polysomnography (PSG) rather than explicit acceptance criteria in a tabular format. However, the key performance metrics are stated:

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

• Sample Size for Test Set: Sound recordings from 242 individuals.
• Data Provenance:
  • Country of Origin: United States. The study was conducted in "three AASM accredited laboratories in the United States."
  • Retrospective/Prospective: Prospective. The study "collected as part of an IRB-approved clinical study" during which "Each subject had sound recordings from one or more consumer mobile computing device placed on the bedside during PSG." This indicates data was collected specifically for this study.

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

The document does not specify the number of experts or their qualifications used to establish the ground truth for the test set. It states that DROWZLE was "tested against the results of in-lab PSG." Polysomnography (PSG) is the gold standard for sleep apnea diagnosis, and it is typically scored by trained polysomnography technologists and interpreted by board-certified sleep physicians. While the number and expertise of these individuals are not explicitly listed, the "AASM accredited laboratories" designation implies that qualified personnel were involved in generating the PSG ground truth.

4. Adjudication Method for the Test Set

The document does not describe an adjudication method for the test set beyond stating that results were compared against in-lab PSG. Given that PSG itself is the ground truth, an explicit adjudication of the PSG results is not typically needed in this context, assuming standard clinical practices were followed.

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

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly mentioned or detailed in the provided text. The study described compares the device's performance to PSG, not the improvement of human readers with AI assistance.

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

Yes, a standalone performance evaluation was done. The study assesses the DROWZLE algorithm's ability to identify sleep apnea risk by analyzing sound recordings and comparing its output (sensitivity and specificity) directly against PSG results. The device "analyzes and interprets the sleep breathing results, along with the profile data provided by the individual," implying an automated, algorithm-only performance.

7. The Type of Ground Truth Used

The ground truth used was Polysomnography (PSG), which is the clinical gold standard for diagnosing sleep disordered breathing.

8. The Sample Size for the Training Set

The document states: "Separate recording cohorts were used to develop and validate the algorithm used in DROWZLE." However, it does not provide the specific sample size for the training set. It only mentions the total number of individuals from whom sound recordings were collected for the entire study (242), which may have been split into training and validation cohorts.

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

The document implies that the ground truth for both the training and validation cohorts was established using Polysomnography (PSG). It states, "Each subject had sound recordings from one or more consumer mobile computing device placed on the bedside during PSG." This suggests that for both the development and validation of the algorithm, the PSG data served as the reference standard.

Ask a specific question about this device