(205 days)
ApLab is intended for use in recording respiratory nasal pressure during sleep. The device is intended for use as a screening device to determine the need for clinical diagnosis and evaluation by polysomnography based on the patient's score.
The ApLab is a re-usable, respiratory pressure sensor system intended to provide a recording of respiratory pressure during sleep. This physician prescribed device will provide a screening index for and aid in the diagnosis of obstructive sleep apnea syndrome. The device is about the size of a common beeper that contains proprietary electronic circuitry and embedded software. The ApLab utilizes a disposable, lightweight plastic nasal cannula that can be conveniently worn while sleeping at home. At completion of a sleep study the device is returned for data analysis and report generation.
ApLab™ Ventilatory Effort Recorder - Acceptance Criteria and Study Details
Here's a breakdown of the acceptance criteria and study information for the ApLab™ device, based on the provided 510(k) summary:
1. Table of Acceptance Criteria and Reported Device Performance
The provided document does not explicitly state pre-defined "acceptance criteria" in the traditional sense before the study was conducted. Instead, it presents the results of clinical tests and compares them to a manually scored Polysomnography (PSG) and an auto-scored PSG. The "acceptance" can be inferred by the FDA's substantial equivalence determination, which implicitly accepts the reported performance as sufficient compared to predicate devices.
| Metric (Criterion) | Reported ApLab™ Performance | Comparison to Predicate/Manual PSG |
|---|---|---|
| Accuracy (Mean AHI) | The ApLab™ and PSG were equivalent in mean AHI. | Equivalent to manually scored PSG (SomnoStar α). |
| Sensitivity (Apnea & Hypopnea Event Count vs. Manual PSG) | 69% | Auto-scored PSG sensitivity was 21% (ApLab™ statistically superior). |
| Positive Predictive Value (PPV) (Apnea & Hypopnea Event Count vs. Manual PSG) | 65% | ApLab™ and auto-scored PSG statistically equivalent on PPV (auto-scored PSG PPV was 58%). |
| Sensitivity (Detection of OSAS - AHI >= 10 vs. Manual PSG) | 89% | When compared to an industry standard AHI of 10. |
| Positive Predictive Value (PPV) (Detection of OSAS - AHI >= 10 vs. Manual PSG) | 100% | When compared to an industry standard AHI of 10. |
| Breath-by-breath accuracy | Equivalent on a breath-by-breath basis at all three time intervals. | Equivalent to PSG. |
| Completeness of breathing record | Provides a complete record of breathing to confirm the AHI scoring. | Implied to be sufficient for AHI scoring. |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: Not explicitly stated as a single number for the "test set" or clinical study. The document mentions "Nine patients wore the ApLab for an average of 4.46 hours" in the safety results section, which likely refers to the clinical study population. It's unclear if this is the entire "test set" used for efficacy analysis, or if efficacy analyses were conducted on a larger, unspecified dataset.
- Data Provenance: Not explicitly stated (e.g., country of origin). The study appears to be retrospective or a single prospectively collected small cohort, given the limited patient count mentioned. However, the document does not specify whether the data was collected retrospectively or prospectively.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
- Number of Experts: Not explicitly stated. The ground truth was established by a "manually scored SomnoStar α PSG" which implies interpretation by a trained professional.
- Qualifications of Experts: Not explicitly stated (e.g., "radiologist with 10 years of experience"). However, manual scoring of PSG is typically performed by trained polysomnographic technologists or sleep physicians.
4. Adjudication Method for the Test Set
The document states that "Breath by breath accuracy was verified manually on both systems." This suggests a direct comparison, but no explicit adjudication method (like 2+1 or 3+1 consensus) is described for reconciling discrepancies or establishing the definitive ground truth where opinions might differ. The "manually scored SomnoStar α PSG" serves as the reference, implying a single authoritative scoring.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
- No: A multi-reader multi-case (MRMC) comparative effectiveness study was not conducted. The study compares the ApLab™ (and auto-scored PSG) to a single manual PSG score. There is no mention of multiple human readers or an analysis of how AI assistance impacts human reader performance.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
- Yes: The reported "ApLab™ sensitivity" and "ApLab™ PPV" are measures of the device's standalone algorithm performance when compared to a manually scored PSG. The focus is on the device's ability to automatically detect apnea and hypopnea events and identify OSAS.
7. The Type of Ground Truth Used
- Expert Consensus (implied single expert): The primary ground truth used was a "manually scored SomnoStar α PSG." This represents expert interpretation of polysomnographic data, likely by a trained polysomnographic technologist or sleep physician. It is not pathology or direct outcomes data.
8. The Sample Size for the Training Set
- Not Provided: The document does not specify any information regarding a training set or its sample size. This suggests the device's algorithms were either developed using proprietary data not disclosed in this summary, or it relies on principles and technologies that do not require a separate, extensive, and explicitly documented training phase in the context of this 510(k) submission. Given the 2003 date, deep learning techniques with large training sets may not have been as prevalent.
9. How the Ground Truth for the Training Set Was Established
- Not Applicable / Not Provided: Since no information about a training set is given, the method for establishing its ground truth is also 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).