(30 days)
The SomnoStar a Series Sleep System is intended to assist the user in diagnosing patients with sleep disorders by collecting physiological data from a sleeping patient, assisting the user in performing analysis of sleep data, and printing a hard-copy report of these data.
The SomnoStar a Series Sleep System is indicated for use to assist the user(s) In diagnosing patients with sloep disorders; by collecting physiological data from a sleeping patient, assisting the user(s) in performing analysis of sleep data and printing a hard copy of these data. The data is collected, staged and scored with a computerassisted program.
The SomnoStar a Sleep System receive Input from bio-physical amplifiers, analyze these data according to software programs designed for use on computer systems included in the system configuration and output data in the form of reports generated by the printer option to the systems. Various components of the systems can be designed into already-existing sleep laboratories. A more detailed description is contained in the Operator's Manual.
In use, the SomnoStar a Series Sleep System receives input from optional bloghysical amplifiers, up to 32 channels in each, which is converted from analog to digital data and stored in a computer storage medium.
The provided document is a 510(k) premarket notification for the SomnoStar Alpha Series Sleep System. It mainly focuses on demonstrating substantial equivalence to a predicate device and does not contain detailed information on specific acceptance criteria and a study proving those criteria.
However, based on the provided text, here's what can be inferred and what is explicitly stated:
1. A table of acceptance criteria and the reported device performance
The document does not provide a table of acceptance criteria or specific performance metrics. The primary claim is substantial equivalence to the SensorMedics 4000 Series Sleep System (K915856). The key difference mentioned is the inclusion of an optional bio-physical amplifier, the Cephalo Pro, which replaces either the AmpStar or Dynagraph II bio-physical amplifiers.
Reported Device Performance:
"Because there are no performance differences caused by using the Caphalo Pro, no additional clinical or non-clinical tests were performed or submitted in the premarket notification."
This implies that the performance of the new device (SomnoStar Alpha Series with Cephalo Pro) is considered to be the same as the predicate device (SensorMedics 4000 Series Sleep System). Therefore, the "reported device performance" is essentially that it functions equivalently to the established predicate.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
Not applicable. The document explicitly states: "Because there are no performance differences caused by using the Caphalo Pro, no additional clinical or non-clinical tests were performed or submitted in the premarket notification." This means there was no new test set generated for this 510(k) submission. The equivalence relies on the established performance of the predicate device.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
Not applicable, as no new test set was generated or evaluated. The ground truth would have been established for the predicate device, but details are not provided here.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable, as no new test set was generated or evaluated.
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
Not applicable. This device is a sleep analysis system, not an AI-assisted diagnostic tool for human readers in the context of an MRMC study. It collects and assists in analyzing physiological data.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
This refers to the device's ability to collect and display data, and "assisting the user in performing analysis of sleep data." The device itself is a "Sleep Analysis System." The claim of "no performance differences" implies that its standalone function (data collection, analysis assistance, reporting) is equivalent to the predicate device. However, a dedicated standalone study proving this for the new iteration is stated as not performed since the change was a component swap with no performance impact.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
For the predicate device, the implied "ground truth" would likely involve expert consensus among sleep specialists (polysomnographers) for the proper staging and scoring of sleep data, validated by clinical use and potentially comparisons to established sleep disorder diagnoses. However, for this 510(k), no new ground truth was established as no new tests were performed.
8. The sample size for the training set
Not applicable. This is not a machine learning or AI-driven device in the sense of needing a "training set" for an algorithm to learn from data. It's a system for collecting and analyzing pre-defined physiological signals.
9. How the ground truth for the training set was established
Not applicable, as there is no "training set" in the context of this device.
§ 882.1400 Electroencephalograph.
(a)
Identification. An electroencephalograph is a device used to measure and record the electrical activity of the patient's brain obtained by placing two or more electrodes on the head.(b)
Classification. Class II (performance standards).