(50 days)
The NightOwl is a wearable device intended for use in the recording, analysis, displaying, exporting, and storage of biophysical parameters to aid in the evaluation of sleep-related breathing disorders of adult patients suspected of sleep apnea.
The device is intended for the clinical and home setting use under the direction of a Healthcare Professional (HCP).
The NightOwl is prescribed by a Health Care Professional for the patient to use in the home as a 'home sleep apnea test' (HSAT).
The NightOwl comprises a sensor that is worn on the fingertip (the "NightOwl Sensor") over-night whilst the subject is sleeping and cloud-based analysis software (the "NightOwl Software").
The NightOwl Sensor has a small biocompatible enclosure. The sensor has 2 LEDs, one in the red spectrum and the other in the infrared spectrum, and an accelerometer. The sensor is attached to the fingertip by single-use biocompatible adhesive tape, with the sensor window applied against the fingerprint area of the fingertip. The sensor measures the reflected red/infrared signals to record the photoplethysmograph (PPG) signal. The accelerometer is used to detect movement.
The data recorded by the NightOwl Sensor can either be stored in on-board memory ("Offline" mode) or streamed via a Bluetooth link to an Ectosense app on a smartphone ("Streaming" mode)
- if the data is stored on the device, the data is retrieved when the NightOwl sensor . is returned to the prescribing HCP and passed up to a cloud-based signal processing suite, the NightOwl Software.
- If the device is used in Streaming mode, the data is stored by the Ectosense app . on the smartphone during the recording. At the end of the recording, it is then passed directly up to the cloud-based signal processing suite.
- The NightOwl Software signal processing algorithms produce a number of sleep . and sleep-disordered breathing related traces and parameters. The trace and parameter information are passed to a company-managed database for storage and access by the prescribing Health Care Professional in the Ectosense Dashboard.
The provided text describes the 510(k) premarket notification for the NightOwl device, focusing on a modification that includes a new algorithm tuning (1B rule) for calculating the probable Apnea-Hypopnea Index (pAHI). The document outlines the device's technical characteristics, intended use, and performance data from a clinical study comparing the modified device's 1B rule performance to the predicate device's 1A rule performance against polysomnography (PSG).
Here's an analysis of the acceptance criteria and the study proving the device meets those criteria, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The acceptance criteria are implicitly defined by the performance metrics reported in the "Clinical Study" section, comparing the modified device's 1B rule performance to the predicate device's 1A rule performance. The goal is to demonstrate substantial equivalence, which implies that the 1B rule performance is comparable to or better than the 1A rule performance, and both are clinically acceptable against the gold standard.
| Endpoint Parameters | Acceptance Criteria (Implied: Clinically acceptable and comparable to Predicate K191031) | Reported Device Performance (NightOwl K213463 - 1B rule) | Reported Predicate Performance (NightOwl K191031 - 1A rule) |
|---|---|---|---|
| Sensitivity at AHI cutoff 5 | N/A (Comparison to predicate is key) | 1.000 | 0.936 |
| Specificity at AHI cutoff 5 | N/A (Comparison to predicate is key) | 0.823 | 0.727 |
| Sensitivity at AHI cutoff 15 | N/A (Comparison to predicate is key) | 0.973 | 0.978 |
| Specificity at AHI cutoff 15 | N/A (Comparison to predicate is key) | 0.886 | 0.704 |
| Sensitivity at AHI cutoff 30 | N/A (Comparison to predicate is key) | 0.840 | 0.964 |
| Specificity at AHI cutoff 30 | N/A (Comparison to predicate is key) | 0.979 | 0.844 |
| pAHI correlation | N/A (Comparison to predicate is key) | 0.946 | 0.909 |
Note: The document states that the new 1B rule tuning "does not alter the device's intended use and does not introduce any change to the safety and effectiveness of the originally cleared device (predicate device)." The acceptance criteria are therefore implicitly met if the performance characteristics of the 1B algorithm are demonstrated to be clinically acceptable and substantially equivalent to the already cleared 1A algorithm, which the data suggests.
2. Sample Size Used for the Test Set and Data Provenance
The document states, "The clinical validation of the NightOwl performance using 1B rule was compared to the gold standard polysomnography (PSG) in the US population."
- Sample Size: The document does not explicitly state the sample size used for the clinical validation test set.
- Data Provenance: The data provenance is from the US population. The study type is retrospective, as it describes a "clinical validation" comparing the device's output against established PSG data.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
The document does not provide information on the number or qualifications of experts used to establish the ground truth (e.g., scoring of PSG studies). It only mentions that the comparison was against "gold standard polysomnography (PSG)." Typically, PSG studies are scored by trained polysomnographic technologists and/or interpreted by sleep physicians.
4. Adjudication Method for the Test Set
The document does not specify any adjudication method (e.g., 2+1, 3+1, none) for the test set's ground truth.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
An MRMC study was not conducted as described in the provided text. The study focuses on comparing the algorithmic performance of the device against a gold standard (PSG) and comparing the performance of the new algorithm (1B) to the predicate's algorithm (1A). There is no mention of human readers assisting with the AI or their improved performance with AI assistance.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
Yes, a standalone performance study was conducted. The reported "Sensitivity," "Specificity," and "pAHI correlation" values are direct measurements of the NightOwl's algorithm (both 1A and 1B tunings) against the PSG gold standard without human intervention or interpretation as part of the performance metrics. The device provides "traces and parameters" to be accessed by a "Healthcare Professional (HCP)," implying the algorithm generates these outputs independently, for the HCP to use in evaluation.
7. Type of Ground Truth Used
The type of ground truth used was expert-scored polysomnography (PSG). PSG is widely considered the gold standard for diagnosing sleep-related breathing disorders. The reference to "AASM's '1A Rule'" and "AASM's '1B Rule'" for hypopnea scoring indicates that the PSG studies would have been scored according to these established clinical criteria.
8. Sample Size for the Training Set
The document does not explicitly state the sample size for the training set. The clinical study described appears to be a validation study for the pre-trained algorithm.
9. How the Ground Truth for the Training Set Was Established
The document does not provide information on how the ground truth for any potential training set was established. It only discusses the ground truth for the clinical validation test set (PSG).
§ 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).