Automated analysis of Sleep and Vigilance
Physip proposes a comprehensive portfolio of technologies for the automated analysis of sleep and vigilance based on the electroencephalogram (EEG) for industrial applications.
Our solutions for the analysis of EEG:
- MEEGAWAKE® – Vigilance
- Evaluation of drowsiness
- MEEGAFIT® – Vigilance
- Evaluation of sleep pressure
- ASEEGA® – Sleep
- Automatic sleep staging: real-time and offline
Method and Expertise
To support R&D project involving EEG, Physip offers unique methodology and expertise:
- Qualification of EEG devices (amplifiers, sensors)
- Qualification of study conditions
- Study protocol
- Study monitoring
We aim at securing studies involving EEG, at producing reliable and clear results. EEG is a rich but fragile signal, which requires a minimum initial investment to obtain clear data and clear results.
Is EEG measurement feasible in a complex cockpit environment?
What is the appropriate recording system for the study objectives and environment?
Evaluation study of the automatic sleep scoring algorithm in a pharma context
Frequently Asked Questions
Does ASEEGA® analyse EOG and EMG signals?
No, ASEEGA® analyses EEG signals exclusively. However, for practical purposes, if you have recorded PSG traces, you can send the entire trace and we will perform for you the extraction of the EEG channel, which we will then analyse.
Why use CzPz?
Our approach consists of simplifying the EEG, hence the choice to reduce the number of sensors used. In light of this, and in light of the work pursued by Dr Odile Benoit, CzPz has proven to be the most favourable channel. The analysis was developed and validated using this channel. Using CzPz guarantees that the highest degree of reliability can be achieved for the analysis.
How should I configure my device to ensure that the recorded EEG data can be analysed by ASEEGA® ?
You must find the menu allowing configurations to be performed prior to the recording, and the CzPz channel must be configured to correspond with the criteria. Please do not hesitate to contact us to find out more information about how to perform this configuration.
What happens if I send traces that do not fulfil these criteria?
Two scenarios: If you have subscribed to the “security” option, then you will not be charged for any non-compliant traces you send us. If you have subscribed to the “independence” option, then you will be charged for all the traces sent, even the non-compliant files that may have escaped your notice.
📃 Berthomier C. et al., Real-Time Automatic Measure of Drowsiness based on a Single EEG Channel, Journal of Sleep Research, 2008
Berthomier C, Muzet A, Berthomier P, Prado J, Mattout J, Real-Time Automatic Measure of Drowsiness based on a Single EEG Channel, Journal of Sleep Research, Vol 17/suppl.1,P434, 2008
19th Congress of the European Sleep Research Society (ESRS)
September 9-13, 2008, Glasgow, UK
📃 Berthomier C. et al., Automatic Analysis of Single-Channel Sleep EEG: Validation in Healthy Individuals, Sleep, 2007
Berthomier C; Drouot X; Herman-Stoïca M; Berthomier P; Prado J; Bokar-Thire D; Benoit O; Mattout J; d’Ortho MP., Automatic Analysis of Single-Channel Sleep EEG: Validation in Healthy Individuals, Sleep 2007;30(11):1587-1595.
STUDY OBJECTIVE: To assess the performance of automatic sleep scoring software (ASEEGA) based on a single EEG channel comparatively with manual scoring (2 experts) of conventional full polysomnograms.
DESIGN: Polysomnograms from 15 healthy individuals were scored by 2 independent experts using conventional R&K rules. The results were compared to those of ASEEGA scoring on an epoch-by-epoch basis.
SETTING: Sleep laboratory in the physiology department of a teaching hospital.
PARTICIPANTS: Fifteen healthy volunteers.
MEASUREMENTS AND RESULTS: The epoch-by-epoch comparison was based on classifying into 2 states (wake/sleep), 3 states (wake/REM/ NREM), 4 states (wake/REM/stages 1-2/SWS), or 5 states (wake/REM/ stage 1/stage 2/SWS). The obtained overall agreements, as quantified by the kappa coefficient, were 0.82, 0.81, 0.75, and 0.72, respectively. Furthermore, obtained agreements between ASEEGA and the expert consensual scoring were 96.0%, 92.1%, 84.9%, and 82.9%, respectively. Finally, when classifying into 5 states, the sensitivity and positive predictive value of ASEEGA regarding wakefulness were 82.5% and 89.7%, respectively. Similarly, sensitivity and positive predictive value regarding REM state were 83.0% and 89.1%.
CONCLUSIONS: Our results establish the face validity and convergent validity of ASEEGA for single-channel sleep analysis in healthy individuals. ASEEGA appears as a good candidate for diagnostic aid and automatic ambulant scoring.