(358 days)
DynaDx Sleep Quality is intended for use on adult patients only as a screening device to determine the need for clinical diagnosis and evaluation by polysomnography based on the patient's score. The ECG recording may be obtained at any location specified by a physician including home, hospital or clinic. Subjects screened for sleep apnea should have periods of sleep of at least 4 hours duration during which the ECG is predominantly sinus rhythm in nature.
Sleep Quality is a software system, which can probe the dynamical interactions between heart rate and respiratory variability during sleep by using a single lead Electrocardiogram (ECG) recording. It is designed to support FDA approved Holter Monitor devices on the market. Sleep Quality system takes text format ECG recording as input. It requires that supported Holter devices are able to export their recording into ASCII data format. Most of the commencially available Holter Monitors devices have this capability. ECG recording data is first collected by a standard Holter devices na subject's sleep, is converted into ASCII data format, and is then analyzed by the Sleep Quality system. By recognizing episodes of Sleep Disordered Breathing (SDB), the software indicates that apneic events have occurred and estimated the Apnea-Hypopnea Index (AH). To detect SDB, the algorithm derives both RR Interval and ECG-Derived Respiratory (EDR) information from the ECG recording.
The DynaDx Sleep Quality device is intended as a screening tool for sleep apnea in adult patients, determining the need for further clinical diagnosis and evaluation by polysomnography. The ECG recordings can be obtained in various settings (home, hospital, clinic) from subjects with at least 4 hours of sleep and predominantly sinus rhythm in their ECG.
The acceptance criteria for the DynaDx Sleep Quality device and its reported performance are presented below, along with a comparison to its predicate device, Lifescreen Apnea.
1. Table of Acceptance Criteria and Reported Device Performance
| Product Parameter | Acceptance Criteria (Predicate: Lifescreen Apnea) | Reported Device Performance (DynaDx Sleep Quality) |
|---|---|---|
| Per-subject Sensitivity | 85.0% | 95.0% |
| Per-subject Specificity | 83.3% | 90.0% |
| Per Subject Accuracy | 84.3% | 92.9% |
| Per Subject Positive Predictivity | 87.1% | 92.7% |
| Per-minute sensitivity | 80.9% | 84.5% |
| Per-minute specificity | 78.1% | 83.0% |
| Per-minute Accuracy | 79.5% | 83.8% |
| Per-minute Positive Predictivity | 78.7% | 83.3% |
| Sleep Length for Test (minutes) | 26,100 minutes | 26,100 minutes |
The DynaDx Sleep Quality device demonstrated performance metrics (Sensitivity, Specificity, Accuracy, Positive Predictivity) that met or exceeded those of the predicate device, Lifescreen Apnea, for both per-subject and per-minute analyses.
2. Sample Size Used for the Test Set and Data Provenance
The document does not explicitly state the sample size used for the test set specifically or data provenance (e.g., country of origin, retrospective/prospective). It does, however, provide "Sleep Length for Test" as 26,100 minutes for both the submission device and the predicate device, suggesting a total duration of ECG recordings used for evaluation. This value alone does not specify the number of individual patients.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
This information is not provided in the submitted text.
4. Adjudication Method for the Test Set
This information is not provided in the submitted text.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
A multi-reader multi-case (MRMC) comparative effectiveness study was not mentioned in the provided text. The submission focuses on the standalone performance of the algorithm without human-in-the-loop performance evaluation.
6. Standalone (Algorithm Only) Performance Study
Yes, a standalone study was performed. The reported performance metrics (Sensitivity, Specificity, Accuracy, Positive Predictivity) for "DynaDx Sleep Quality (Submission Device)" reflect the performance of the algorithm itself in detecting apneic events and estimating the Apnea-Hypopnea Index (AHI) from ECG recordings. This is evident from the fact that it's a software system analyzing ECG data to produce these metrics.
7. Type of Ground Truth Used
The document states that the device is intended "to determine the need for clinical diagnosis and evaluation by polysomnography based on the patient's score." This strongly implies that the ground truth for evaluating the device's performance (i.e., whether a patient needs clinical diagnosis and evaluation by polysomnography, or the occurrence of apneic events and AHI) would be established by polysomnography (PSG). PSG is the gold standard for diagnosing sleep disordered breathing, including sleep apnea.
8. Sample Size for the Training Set
This information is not provided in the submitted text. The document focuses on the performance of the device rather than the specifics of its training.
9. How the Ground Truth for the Training Set Was Established
This information is not provided in the submitted text. However, similar to the test set, it is highly probable that if a training set were used, its ground truth would also be established by polysomnography.
§ 868.2375 Breathing frequency monitor.
(a)
Identification. A breathing (ventilatory) frequency monitor is a device intended to measure or monitor a patient's respiratory rate. The device may provide an audible or visible alarm when the respiratory rate, averaged over time, is outside operator settable alarm limits. This device does not include the apnea monitor classified in § 868.2377.(b)
Classification. Class II (performance standards).