(137 days)
AcuPebble SA100 is indicated to sense, record, and interpret a patient's physiological signals (including respiratory pattern) during sleep for the purpose of prescreening patients for obstructive sleep apnea (OSA) syndrome. The designed for use in home-screening of adults with suspected possible sleep breathing disorders (although it can also be used in clinic). Results are used to assist the healthcare professional's in the patient's 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.
AcuPebble SA100 comprises a sensor that is worn on the front of the neck around the suprasternal notch area (the "AcuPebble SA100 sensor"), a mobile device app that guides the patient through the steps of the test, collects the data from the sensor, and uploads them in the "AcuPebble SA100 app"), and a cloud-based analysis software (the "AcuPebble SA100 algorithms". The "AcuPebble SA100 Sensor" consists of a small biocompatible enclosure with very low power sensors and electronics inside. It is attached to the front of the neck (somewhere between the Adam's apple and the suprasternal notch area) by single-use biocompatible adhesive tape. The sensor measures physiological body sounds. The data sensed is streamed via a Bluetooth link to the "AcuPebble SA100 app" on a smart device (mobile phone/tablet). The data can be uploaded into the cloud where it is analyzed, any time after the sleep study test is finished at the tap of a button in the app. AcuPebble SA100 signal processing algorithms produce a number of OSA diagnostic traces and parameters. These can be accessed by the Health Care Professional through a healthcare professional portal, which can be accessed from any computer or smart device with an Internet connection.
AcuPebble SA100 is not intended to be used with patients with pacemakers or other implantable devices, or with patients with known or suspected arrhythmias. This device has not been validated in patients with congestive heart failure or patients with neuromuscular disorders. Patients with significant cardiopulmonary or neurological disorders need to be excluded from using the device.
Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:
Device Name: AcuPebble SA100
Intended Use: To sense, record, and interpret a patient's physiological signals (including respiratory pattern) during sleep for the purpose of prescreening patients for obstructive sleep apnea (OSA) syndrome. Designed for home-screening of adults with suspected possible sleep breathing disorders to assist healthcare professionals in patient evaluation. Not a substitute for full polysomnography.
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state pre-defined "acceptance criteria" with numerical thresholds for diagnostic accuracy (PPV, NPV, LR+, LR-). Instead, it presents the results of the clinical validation study for several diagnostic indices (AHI3, AHI4, ODI3, ODI4) and heart rate accuracy. The implicit acceptance is that these values demonstrate substantial equivalence to the predicate device.
Implicit Acceptance Criteria (Performance Benchmarks from Predicate/Context): Not explicitly stated with numerical targets in the provided text. The submission focuses on demonstrating substantial equivalence to the predicate (Drowzle, K173974) and reference devices (NightOwl, K191031; Sleep Strip II, K112822). The reported values in the table are the result of meeting the substantial equivalence standard, rather than being against pre-set numerical acceptance criteria.
Reported Device Performance:
| Diagnostic Index | Positive Predictive Value (PPV) | Negative Predictive Value (NPV) | Positive Likelihood Ratio (LR+) | Negative Likelihood Ratio (LR-) |
|---|---|---|---|---|
| AHI3 (for airflow reductions and 3% desaturations) | 94.44% (CI 84.78%- 98.11%) | 95.83% (CI 89.94%- 98.34%) | 29.36 (CI 9.62 to 89.64) | 0.08 (CI 0.03 to 0.19) |
| AHI4 (for 4% desaturations) | 94.00% (CI 83.69%- 97.95%) | 98.00% (CI 92.65% to 99.48%) | 32.29 (CI 10.58 to 98.59) | 0.04 (CI 0.01 to 0.16) |
| ODI3 (considering 3% desaturations) | 93.42% (CI 85.87%- 97.07%) | 90.54% (CI 82.48%- 95.11%) | 13.11 (CI 5.61 to 30.62) | 0.10 (CI 0.05 to 0.20) |
| ODI4 (considering 4% desaturations) | 85.71% (CI 75.50%- 92.11%) | 98.94% (CI 93.03%- 99.85%) | 12.37 (CI 6.35-24.08) | 0.02 (CI 0.00-0.15) |
Heart Rate Accuracy:
| Bias (µ) ≤ ±1 bpm | Bias (µ) ≤ ±3 bpm | Bias (µ) ≤ ±5 bpm | Standard Deviation (σ) ≤ 2 bpm | Standard Deviation (σ) ≤ 5 bpm | Standard Deviation (σ) ≤ 8 bpm |
|---|---|---|---|---|---|
| 62.0% | 94.0% | 98.7% | 28.7% | 93.3% | 98.7% |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: 150 consecutive evaluation patients.
- Data Provenance: Not specified in terms of country of origin. The study was a "Clinical Investigation," conducted in accordance with ISO 14155:2011 and 21 CFR 812.28(a)(1) (GCP for clinical investigations). This implies a prospective study design for data collection, as it refers to "consecutive evaluation patients."
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
- The document does not specify the number or qualifications of experts used to establish the ground truth. It states that the ground truth for diagnostic accuracy was based on "the AASM for airflow reductions and desaturations" and "established thresholds, for OSA (i.e. 5, 15 and 30)". For heart rate, the ground truth was the "PPG signal of the polygraphy system." This implies that the ground truth was derived from a gold-standard PSG (Polysomnography) system, rather than expert interpretation of the device's output alone.
4. Adjudication Method for the Test Set
- The document does not mention any specific adjudication method (e.g., 2+1, 3+1, none) for the test set. Ground truth appears to be derived from the gold standard PSG, rather than expert review of the device's output.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done
- No, an MRMC comparative effectiveness study involving human readers with and without AI assistance was not described. The clinical validation focuses on the device's accuracy compared to a polysomnography system, not on assisting human readers.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was Done
- Yes, the clinical validation study appears to be a standalone performance evaluation. The device (AcuPebble SA100) generates diagnostic indices (AHI, ODI) and heart rate output, and these are compared directly against a polygraphy system, which serves as the ground truth. The role of a human healthcare professional is described as using the results to "assist" in patient evaluation, implying the device provides direct outputs.
7. The Type of Ground Truth Used
- Type of Ground Truth: The ground truth for OSA diagnostic indices (AHI, ODI) was established using definitions from the "AASM" (American Academy of Sleep Medicine) for airflow reductions and desaturation criteria (3% and 4%). This indicates comparison against polysomnography (PSG), which is the gold standard for sleep apnea diagnosis. For heart rate, the ground truth was "the heart rate obtained from the PPG signal of the polygraphy system," further confirming PSG as the reference.
8. The Sample Size for the Training Set
- The document does not specify the sample size used for the training set. The clinical validation section only refers to the "150 consecutive evaluation patients" used for the accuracy validation clinical study (i.e., the test set).
9. How the Ground Truth for the Training Set Was Established
- The document does not specify how the ground truth for the training set was established, as the training set details are not provided.
§ 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).