Search Results

Sleep CheckRx is indicated to record a patient's respiratory pattern during sleep for the purpose of pre-screening patients for obstructive sleep apnea (OSA) syndrome.

The device is designed for use in home-screening of adults (≥ 22 years of age) with suspected possible sleep breathing disorders. Results can be 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.

SleepCheckRx is a software application used by healthcare providers to pre-screen adults at home for the risk of Obstructive Sleep Apnea (OSA). The application is accessed via a compatible smartphone and uses the device's inbuilt microphone to record breathing and snore sounds while the user is asleep, over a minimum duration of 6 hours.

This audio recording, in conjunction with basic information about the user, is analyzed by locked machine learnt software algorithms to provide a risk assessment of the presence of OSA. Prior to use, the patient installs SleepCheckRx on a compatible smartphone and activates the application by entering a code issued to their Healthcare Professional (HCP) through a secure cloud server portal.

The patient enters basic information including date of birth, biological sex, height, weight, and neck circumference. The patient is also required to answer a STOP-Bang questionnaire. The phone is placed on a nightstand as directed, and when the user is ready to go to sleep, they initiate the software that begins a recording.

SleepCheckRx then captures breathing and snore sounds continuously throughout the night until the user stops the recording once they have awoken in the morning (a minimum of 6 hours of recording is required).

In the event of a successful recording, SleepCheckRx provides the user with a binary outcome of either 'Minimal to Mild Risk of OSA' (AHI<15) or 'Moderate to Severe Risk of OSA' (AHI ≥15).

SleepCheckRx requires a healthcare professional (HCP) to access a secure cloud server portal to provide the patient with an access code to use the app downloaded from the Apple App Store.

The results of the patient's recording and the STOP-Bang questionnaire are shared with the patient and the HCP, for the HCP to then determine if further investigation and evaluation is required.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Acceptance Criteria and Reported Device Performance

1. Sample Sizes and Data Provenance

• Test Set Sample Size: 228 adult analyzable subjects initially, with results reported for n=220.
• Data Provenance: Prospective, multi-center study. The text does not explicitly state the country of origin, but the submitter is "ResApp Health" from "Brisbane, Queensland 4000 Australia," implying the study may have been conducted there or involved Australian sites.

2. Number of Experts and Qualifications for Ground Truth

• Number of Experts: Two (2) independent PSG scorers.
• Qualifications: "Qualified independent sleep scorer." The text does not provide specific details on their years of experience or precise certifications beyond "qualified."

3. Adjudication Method for the Test Set

• The text states "PSG diagnosis was established by independent scorers," and "Each sleep study was scored by a qualified independent sleep scorer." It then refers to "clinical diagnosis (using 2 independent PSG scorers)." This implies that both scorers independently scored the PSG studies. However, it doesn't explicitly state an adjudication method (like 2+1 or 3+1) if their scores differed. It simply says the "agreement" between SleepCheckRx and "clinical diagnosis (using 2 independent PSG scorers)." It's possible that if there were discrepancies, they were resolved or averaged, but this is not detailed.

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

• No, a multi-reader multi-case (MRMC) comparative effectiveness study was not reported. The study focused on the standalone performance of the SleepCheckRx algorithm against a gold standard (PSG). The text does not describe human readers using the AI and then comparing their performance to human readers without AI assistance.

5. Standalone Performance

• Yes, a standalone (algorithm only without human-in-the-loop performance) study was done. The results presented (sensitivity and specificity) are explicitly for the SleepCheckRx algorithm's performance when compared to PSG diagnosis.

6. Type of Ground Truth Used

• Expert Consensus / Objective Data: The ground truth was established by independent scoring of Polysomnography (PSG) by qualified sleep scorers, in accordance with the Type II (in-home) American Academy of Sleep Medicine (AASM) 2017 Guidelines. PSG is considered the gold standard for diagnosing sleep apnea.

7. Sample Size for the Training Set

• The text does not explicitly state the sample size used for the training set. It mentions the "locked machine learnt software algorithms" and the clinical study on 228 subjects for performance evaluation, but the training data size is not provided.

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

• The text does not explicitly state how the ground truth for the training set was established. It only refers to the algorithm being "machine learnt." Given the nature of the device, it's highly probable that the training data's ground truth was also established using PSG, similar to the test set, but this is not detailed in the provided excerpt.

Ask a specific question about this device