(267 days)
The NicoletOne EEGPSG software performs recording, displaying, analysis, printing and storage of physiological signals to assist in the diagnosis of various neurological disorders and sleep related respiratory disorders. It is intended to monitor the state of the brain by recording and displaying EEG signals and can receive and display a variety of third party signals such as ECG, EMG, Oxygen Saturation or Respiration for patients of all ages.
NicoletOne software allows:
· Automated analysis of physiological signals that is intended for use only in adults.
· An optional Audio/visual alert for user defined threshold on calibrated DC input. These alerts are not intended for use as life support such as vital signs monitoring or continuous medical surveillance in intensive care units.
· Sleep report templates are provided which summarize recorded and scored sleep data using simple measures including count, average, maximum and minimum values as well as data ranges for trended values.
This device does not provide any diagnostic conclusion about the patient's condition and is intended to be used only by qualified and trained medical practitioners, in research and clinical environments.
The NicoletOne application is a software product for digital electroencephalography, long term monitoring in Epilepsy, intensive care unit (ICU) monitoring, and polysomnography that runs on a panel PC, desktop or laptop computer. It is a Windows based application used by trained medical professionals to investigate brain function and sleep disorders.
The NicoletOne application collects and displays continuous physiological waveform data (via a Natus digital amplifier), and digital audio/video (via standard audio/video equipment). After collecting and saving the signals, it provides tools and analyze the signals, which aid in the interpretation of an EEG or PSG study. The software consists of four main functional areas:
- Data Acquisition & Display Real time collection of EEG. PSG and other physiological ● parameters. The data is stored and displayed in real time by the NicoletOne software on the acquisition computer and made available for subsequent review by a trained medical professional.
- Scoring/Review & Analysis The NicoletOne software application has features that facilitate ● study navigation, event marking, scoring, review of synchronized digital video, and data trends required by medical professionals in order to properly analyze and interpret the study data. In addition to allowing users to manually mark events for both electroencephalography (EEG) and polysomnography (PSG) studies the NicoletOne software also provides optional computer assisted event marking analyzers for certain events.
- Report Generation - Once the digital electroencephalography (EEG) or polysomnography (PSG) data has been acquired scored and reviewed by medical professionals the NicoletOne and NicVue software is used to generate a report of the study. The generated reports are associated with the patient in the patient database. NicoletOne also includes the ability to customize report templates to conform to individual facilities standards and policies.
- . Archiving & Data Management - Once the digital electroencephalography (EEG) or polysomnography (PSG) data has been acquired scored and reviewed by medical professionals the NicoletOne and Nic Vue software is used to generate a report of the study. The generated reports are associated with the patient in the patient database. NicoletOne also includes the ability to customize report templates to conform to individual facilities standards and policies.
Here's a summary of the acceptance criteria and the study proving the device meets them, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The acceptance criteria for the NicoletOne assisted-scoring analyzers were implicitly set as performance levels comparable to the manual markings of expert reviewers and clinical equivalence to the reference standard (majority rule), similar to results reported in literature and for other commercially available devices. The specific metrics used were Positive Percent Agreement (PPA) and False Detection Rate per hour (FD/h).
| Event | Acceptance Criteria (Implicit: Comparable to expert majority, similar to predicate/literature) | Reported Device Performance (Mean PPA) | 95% CI (PPA) | Reported Device Performance (Mean FD/h) | 95% CI (FD/h) |
|---|---|---|---|---|---|
| Central Apnea | Comparable to expert majority | 99.1% | 98.8% to 99.5% | 0.6 | 0.37 to 1.07 |
| Mixed Apnea | Comparable to expert majority | 99.6% | 99.3% to 99.8% | 0.3 | 0.15 to 0.66 |
| Obstructive Apnea | Comparable to expert majority | 98.6% | 97.5% to 99.3% | 0.2 | 0.11 to 0.48 |
| Hypopnea | Comparable to expert majority | 86.8% | 84.1% to 89% | 9.0 | 7.41 to 10.89 |
| Limb Movement | Comparable to expert majority | 93.3% | 90.9% to 95.3% | 3.7 | 2.01 to 4.64 |
2. Sample Size for Test Set and Data Provenance
- Sample Size for Test Set: 49 PSG sleep studies for respiratory and limb movement events.
- Data Provenance: Retrospective. The patient data were collected from adult patients (32-85 years old) with a clinical indication for a sleep study, then de-identified and applied as subject data. The country of origin is not explicitly stated in the provided text.
3. Number of Experts and Qualifications
- Number of Experts: Three (3)
- Qualifications: "experienced and certified PSG specialists, including one board certified sleep specialist."
4. Adjudication Method for Test Set
The adjudication method was a majority rule (2+1). For respiratory events, a majority rule meant at least 2 out of 3 manual expert scorers agreed on the type of event(s) in an epoch or the absence of an event. For limb movement, it meant at least 2 out of 3 manual expert scorers agreed on the presence of the event type in the epoch.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No MRMC comparative effectiveness study comparing human readers with AI assistance versus without AI assistance was mentioned. The study focused on the standalone performance of the AI algorithms compared to a reference standard established by human experts. The description states that the automated analysis is "intended for use only in adults" and that generated reports provide summaries, but clarifies that "This device does not provide any diagnostic conclusion about the patient's condition and is intended to be used only by qualified and trained medical practitioners". The phrase "All automatic detection tools are provided as time saving aids to assist trained medical practitioners in the review and analysis of vast amounts of data. Each computer-assisted analyzer runs a specific type of event marking or numeric value processing in the study and each can be enabled individually as needed at the discretion of the user. The parameters used in the computer-assisted analyzers depend on available input signals in the study as well as user defined settings. All output from computer assisted analyzers require medical professional review and acceptance," further suggests that AI is intended for assistance rather than standalone diagnosis.
6. Standalone (Algorithm Only) Performance
Yes, a standalone performance study was conducted. The "NicoletOne assisted-scoring analyzers" were evaluated against the "Reference standard" (expert majority rule) on an epoch basis. The reported PPA and FD/h values are for the algorithm's performance without human-in-the-loop during the evaluation itself, although the system is intended for human review and acceptance in clinical use.
7. Type of Ground Truth Used
The ground truth used was expert consensus, specifically a majority rule (2 out of 3) of expert scorers who independently marked events of interest in each 30-second epoch based on AASM (American Academy of Sleep Medicine) criteria.
8. Sample Size for Training Set
The document does not specify the sample size for the training set used to develop the NicoletOne assisted-scoring analyzers. The studies described are for validation of the ready-to-use device.
9. How Ground Truth for Training Set Was Established
The document does not describe how the ground truth for the training set was established, as it focuses on the clinical validation study of the already developed 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).