Search Results

The Apnea Risk Evaluation System (ARES), Model 620 is indicated for use in the diagnostic evaluation by a physician of adult patients with possible sleep apnea. The ARES can record and score respiratory events during sleep (e.g., apneas, hypopneas, mixed apneas and flow limiting events). The device is designed for prescription use in the patient's home to aid a physician in diagnosing adults with possible sleep-related breathing disorders.

The Apnea Risk Evaluation System (ARES™) includes a battery powered patient worn device called a Unicorder (Model 620). The Unicorder is worn by a patient for one to three nights, each night recording up to 7 hours of data. Data recorded includes oxygen saturation, snoring level, head movement, head position, and airflow. Additionally, the Unicorder 620 allows collection of data from ARES compatible peripheral devices. The device monitors signal quality during acquisition and notifies the user via voice messages when adjustments are required. A standard USB cable connects the Unicorder to a USB port on a host computer when patient data is to be uploaded or downloaded. The USB cable provides power to the Unicorder during recharging from the host computer or from a USB wall charger. The Unicorder cannot record nor can it be worn by the patient when connected to the host computer or the wall charger. Software, residing on a local PC or a physical or virtual server controls the uploading and downloading of data to the Unicorder, processes the sleep study data and generates a sleep study report. The ARES™ can auto-detect positional and non-positional obstructive and mixed apneas and hypopneas similarly to polysomnography. It can detect sleep/wake and REM and non-REM. After the sleep study has been completed, data is transferred off the Unicorder is prepared for the next study. The downloaded sleep study record is then processed with the ARES ™ Insight software to transform the raw signals and derive and assess changes in oxygen saturation (SpO2), head movement, head position, snoring sounds, airflow, and EEG or respiratory effort. The red and IR signals are used to calculate the SpO₂. The actigraphy signals are transformed to obtain head movement and head position. A clinician can convert an auto-detected obstructive apnea to a central apnea based on visual inspection of the waveforms. ARES "" Screener can predict pre-test probability of obstructive sleep apnea (OSA). The ARES "" data can also assist the physician to identify patients who will likely have a successful OSA treatment outcome, including CPAP and oral appliance therapies. ARES™ can help identify patients who would benefit from a laboratory PAP titration.

The provided text does not contain detailed information about a study proving the device meets acceptance criteria. Instead, it focuses on demonstrating substantial equivalence to a predicate device through a comparison of specifications and non-clinical testing. Therefore, I cannot fully answer all aspects of your request as the specific study details, sample sizes, expert qualifications, and ground truth methodologies for performance evaluation are not present.

However, I can extract the available information regarding acceptance criteria and reported device performance from the comparison table.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly defined by the "Performance" section of the comparison table between the predicate device (ARES Model 610) and the proposed device (ARES Model 620). For most parameters, the goal is "Identical" or "Equivalent," meaning the new device should perform at least as well as the predicate.

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

The document describes "Comparative testing between the Predicate Device ARES Model 610, K111194 as cleared on 07/07/2011 and the proposed ARES Model 610 demonstrates substantial equivalence." However, it does not specify the sample size (number of patients or recordings) used for this comparative testing or the data provenance (e.g., country of origin, retrospective/prospective nature).

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

This information is not provided in the document. The document refers to "nonclinical and clinical tests" but does not detail how ground truth was established for these tests, nor the involvement or qualifications of any experts.

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

This information is not provided in the document.

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:

The document does not describe an MRMC comparative effectiveness study involving human readers or AI assistance effect size. The comparison is between two devices, not human performance with and without AI.

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

The document states, "The ARES™ can auto-detect positional and non-positional obstructive and mixed apneas and hypopneas similarly to polysomnography. It can detect sleep/wake and REM and non-REM." This implies a standalone algorithmic performance for detecting and scoring respiratory events. However, no specific standalone performance metrics (e.g., sensitivity, specificity, accuracy) are reported for this automated detection/scoring. The "SpO2" and other sensor accuracy values are "device performance" but not necessarily "standalone algorithm performance" in the context of diagnostic output.

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

This information is not explicitly stated. Given that the device "can auto-detect positional and non-positional obstructive and mixed apneas and hypopneas similarly to polysomnography," it is highly probable that Polysomnography (PSG) was used as the ground truth. However, the document does not explicitly confirm this or specify how the PSG data was analyzed to establish ground truth (e.g., by experts, automated scoring, etc.).

8. The sample size for the training set:

The document describes comparative testing and verification/validation but does not mention a "training set" or its size, which would typically be associated with machine learning model development. This implies the comparison is more about hardware and firmware functionality and existing algorithms rather than the development of a new AI model requiring a separate training set.

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

Since no training set is mentioned (see point 8), there is no information on how its ground truth was established.

Ask a specific question about this device